Shinetell Plus™ Digital Early Pregnancy Test is intended for the qualitative detection of human chorionic gonadotropin (hCG) in urine, as an aid in early detection of pregnancy, in some cases as early as five (5) days before the expected period, i.e., as early as six (6) days before the day of the missed period.

Shinetell Plus™ Digital Early Pregnancy Test is used for in vitro qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine, and is designed to be tested in dip or midstream mode. The test device consists of a single test strip assembled in a plastic housing, with an absorbent tip. The device is in a ready-to-use format.

Shinetell Plus™ Digital Early Pregnancy Test uses lateral flow immunoassay and light reflection for the detection of the HCG in urine specimens. The test would detect the light intensity by using the LED as the light source. After that, the result can be displayed on the display screen.

Here's a breakdown of the acceptance criteria and study information for the Shinetell Plus™ Digital Early Pregnancy Test, based on the provided 510(k) clearance letter:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA clearance letter does not explicitly state "acceptance criteria" as a separate, quantitative table. However, we can infer the acceptance criteria from the performance studies presented, particularly the sensitivity and agreement rates. The primary criterion is demonstrating a sensitivity of 10 mIU/mL and high agreement with professional results and the predicate device.

2. Sample Sizes and Data Provenance

• Analytical Performance (Precision/Reproducibility/Sensitivity):

  • Test Set Sample Size: For each hCG concentration (0, 3, 5, 7.5, 8, 10, 25, 50 mIU/mL), 10 replicates were tested per day for 5 days for each of 3 device lots, by 3 different operators. This sums to (8 concentrations * 10 replicates/day * 5 days * 3 lots) = 1200 tests for Midstream and another 1200 tests for Dip Testing.
  • Data Provenance: Not explicitly stated, but typically these are laboratory-controlled, prospective studies with spiked samples. The hCG standard is traceable to the 5th WHO.

• Specificity (Non-pregnant females):

  • Test Set Sample Size: 300 urine samples (100 from pre-menopausal, 100 from peri-menopausal, 100 from post-menopausal women).
  • Data Provenance: Not explicitly stated, but implies prospectively collected urine samples from healthy non-pregnant females.

• Method Comparison Study (vs. Predicate):

  • Test Set Sample Size: Urine samples from 200 women suspected to be pregnant in the early stage (

Ask a specific question about this device

FaStep Pregnancy Rapid Test Cassette is used for qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in the early detection of pregnancy. For over-the-counter use.

The Fastep HCG Rapid Test Cassette is a rapid visual immunoassay for the qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in the early detection of pregnancy. The test kits are for health care professionals use including professionals at physician's office labs (POLs).

The FaStep Pregnancy Rapid Test Cassette and the Fastep HCG Rapid Test Cassette are the same device with the first intended for over-the counter use and the second for prescription use. The devices contain individually wrapped pouches containing the device, instructions for use, and pipette droppers.

The devices utilize a combination of antibodies to detect hCG in urine as well as to serve as a run control. The result is displayed to the user in the test window as two lines for a 'Pregnant' positive result and one line for a 'Not Pregnant' negative result.

Here's an analysis of the acceptance criteria and study details for the FaStep Pregnancy Rapid Test Cassette and Fastep HCG Rapid Test Cassette, based on the provided document:

Acceptance Criteria and Device Performance

The document doesn't explicitly state "acceptance criteria" for all performance aspects in a separate table. However, the reported device performance implicitly defines the criteria that were met for substantial equivalence. The key performance indicators for a qualitative pregnancy test are its sensitivity (ability to detect low levels of hCG), specificity (absence of false positives), and agreement with a predicate device/professional results.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes and Data Provenance

• Analytical Performance (Precision/Reproducibility/Sensitivity):
  • Test Set Size: 9 hCG concentrations (0, 10, 12.5, 15, 17.5, 20, 50, 100, 200 mIU/mL) x 10 replicates/day for 5 days x 3 device lots x 3 operators = 1350 data points (for positive/negative determination).
  • Data Provenance: Not explicitly stated, but typically these studies are conducted in a controlled lab environment. No country of origin is mentioned, and it's a prospective lab study.
• Hook Effect Test:
  • Test Set Size: 7 hCG concentrations (25000 to 2000000 mIU/mL) x 5 replicates x 3 lots x 3 operators = 315 data points.
  • Data Provenance: Prospective lab study.
• Interfering Substances:
  • Test Set Size: 3 hCG concentrations (0, 10, 20 mIU/mL) x 3 replicates x 3 lots x 3 operators x 32 substances = 864 data points.
  • Data Provenance: Prospective lab study.
• Cross-reactivity:
  • Test Set Size: 3 hCG concentrations (0, 10, 20 mIU/mL) x 3 replicates x 3 lots x 3 operators x 3 cross-reactants = 81 data points.
  • Data Provenance: Prospective lab study.
• hCG ß-core fragment:
  • Test Set Size: 4 hCG concentrations (0, 10, 20, 20000 mIU/mL) x 3 replicates x 3 lots x 3 operators x 4 hCGBcf concentrations = 108 data points.
  • Data Provenance: Prospective lab study.
• Urine pH:
  • Test Set Size: 3 hCG concentrations (0, 10, 20 mIU/mL) x 3 replicates x 3 lots x 3 operators x 6 pH values = 162 data points.
  • Data Provenance: Prospective lab study.
• Urine Density:
  • Test Set Size: 3 hCG concentrations (0, 10, 20 mIU/mL) x 3 replicates x 3 lots x 3 operators x 8 density values = 216 data points.
  • Data Provenance: Prospective lab study.
• Method Comparison Study:
  • Test Set Size: 112 urine samples from women.
  • Data Provenance: Samples collected from 112 women aged 18 to 50 at "three clinical sites." Approximately half were early-stage pregnant. Implies prospective collection for this study, likely within the US given the FDA submission.
• Lay Person Study:
  • Test Set Size: 112 female subjects.
  • Data Provenance: Conducted at "three sites" with females aged 18-50. Implies prospective collection for this study, likely within the US.
• Specificity Study (False Positives):
  • Test Set Size: 300 urine samples from non-pregnant females (100 per age group: pre-menopausal, peri-menopausal, post-menopausal).
  • Data Provenance: Samples collected from non-pregnant females at "three sites." Implies prospective collection for this study, likely within the US.

3. Number of Experts and Qualifications for Ground Truth

• Analytical Performance Studies (Sensitivity, Hook Effect, Interfering Substances, etc.): Ground truth is established by the known, spiked concentrations of hCG or other substances. The "experts" performing the tests were "operators" (3 different operators for each study involving replicates across lots), but their specific qualifications are not detailed beyond "operator." These are typically trained lab personnel.
• Method Comparison Study: The ground truth for comparative purposes was established by the predicate device results, as read by a "separate professional" at each of the three test sites. Their specific qualifications are not detailed beyond "professional."
• Lay Person Study: The ground truth was established by professional testing of the same urine samples as used by the lay users. The specific qualifications of these "professionals" are not detailed.
• Specificity Study (False Positives): The ground truth (non-pregnant status) was based on the source of the samples (non-pregnant women across different age groups). The results were read by the device itself; no explicit external expert ground truthing beyond sample collection criteria is mentioned.

4. Adjudication Method for the Test Set

• Analytical Performance Studies: No formal adjudication method like 2+1 or 3+1 is mentioned. Each replicate/lot/operator result was recorded. Discrepancies (e.g., in the sensitivity study where partial positivity was seen) were simply reported as the percentage of positive/negative readings.
• Method Comparison Study: Three professional operators read the candidate device, with a different operator at each of the three test sites. A separate professional tested samples using the predicate. It's unclear if there was any adjudication process if different professionals at the same site (if there were multiple for one device) read differently, or if discrepancies between devices were adjudicated. The results table shows perfect agreement, suggesting either no discrepancies or an unstated adjudication process.
• Lay Person Study: Lay user results were compared to "professional test results." The agreement was 100%, implying robust ground truth or an unstated adjudication process if disagreements occurred.
• Specificity Study (False Positives): No false positives were observed. Therefore, no adjudication was necessary.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC comparative effectiveness study was explicitly performed to quantify human reader improvement with AI vs. without AI assistance. The device is a rapid visual immunoassay for qualitative detection of hCG and does not involve AI.
• The "Method Comparison Study" and "Lay Person Study" compare device performance to a predicate or to professional results, but not with an AI component or a quantifiable "improvement" of human readers with AI.

6. Standalone Performance

• Yes, standalone performance was extensively done. All analytical performance studies (sensitivity, hook effect, interfering substances, cross-reactivity, pH, density) evaluate the device's inherent performance.
• The "Lay Person Study" also assesses the standalone performance of the device when used by the intended over-the-counter users.
• The device is designed for qualitative visual interpretation, so its standalone performance is its primary mode of operation.

7. Type of Ground Truth Used

• Analytical Performance Studies (Precision/Sensitivity, Hook Effect, Interfering Substances, Cross-reactivity, hCG ß-core fragment, pH, Density): Ground truth was established using spiked samples with known concentrations of hCG or other substances, traceable to WHO International Standard.
• Method Comparison Study: Ground truth for comparison was the results of the predicate device.
• Lay Person Study: Ground truth was the results of professional testing of the same urine samples.
• Specificity Study (False Positives): Ground truth was the known non-pregnant status of the study participants.

8. Sample Size for the Training Set

• The document describes performance studies, which are analogous to a "test set" for demonstrating effectiveness.
• The document does not provide details about a "training set" for the device itself. This is a qualitative immunoassay, not a machine learning or AI-driven device that requires a training set in the typical sense. The manufacturing process and quality control would be "trained" or optimized during development, but this is not typically disclosed in a 510(k) summary as a "training set."

9. How the Ground Truth for the Training Set Was Established

• Since there is no explicit "training set" identified for an AI/ML context, this question is not applicable to the information provided in the document. The device's underlying chemistry and biology are its "training" or design principles.

Ask a specific question about this device

Synthgene Home Test HCG Test Midstream is used for the qualitative detection of human chorionic gonadotropin in urine to aid in the early detection of pregnancy.

Synthqene Home Test HCG Test Cassette is used for the qualitative detection of human chorionic gonadotropin in urine to aid in the early detection of pregnancy.

Synthqene Home Test HCG Test Strip is used for the qualitative detection of human chorionic gonadotropin in urine to aid in the early detection of pregnancy.

Synthgene Home Test HCG Test is used for the qualitative detection of human chorionic gonadotropin in urine to aid in the early detection of pregnancy. The test devices are in three different formats: Strip, Cassette and Midstream. Each test kit contains the individually packaged test pen/strip/cassette, medical waste bag, urine cup and instructions for Use. The cassette format also contains a dropper. The device is in a readyto-use format and does not require assembly before use.

The provided text describes the performance characteristics and acceptance criteria for the "Synthgene Home Test HCG Test" (Strip, Cassette, and Midstream formats) for qualitative detection of human chorionic gonadotropin in urine. This is a medical device for home use, so the study focuses on analytical performance and comparison with a predicate device, as well as a lay-user study for ease of use. This is not an AI/ML powered device, so "human readers improve with AI vs without AI assistance" or "algorithm only without human-in-the-loop performance" are not applicable.

Here's a breakdown of the requested information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a "table of acceptance criteria" in the same format as an AI/ML performance study with specific sensitivity/specificity targets. Instead, it describes various analytical performance tests and method comparison studies to demonstrate that the device performs as intended and is substantially equivalent to a predicate device.

However, based on the studies conducted, we can infer the performance:

Inferred Acceptance Criteria & Reported Performance:

• 0, 12.5, 18.75 mIU/mL: 0% positive results (100% negative).
• 22.5 mIU/mL: High positivity (e.g., Dip: 87.3%, Midstream: 84.9%, Cassette: 86.2%, Strip: 85.11%). This demonstrates the detection threshold is around 25 mIU/mL.
• 25, 50, 100, 200 mIU/mL: 100% positive results. The sensitivity is demonstrated to be 25 mIU/mL. |
  | Precision/Reproducibility | Consistent results across different lots, operators, sites, and times of day. | No significant differences in performance were observed between lots, operators, sites, or times of day. The sensitivity data (Table 9.1.a) shows consistent results for each concentration across 3 different lots. |
  | Cross-Reactivity/Specificity | No interference from tested concentrations of LH, FSH, TSH, and hCG β-core fragment. | No interference observed at 500 mIU/mL LH, 1000 mIU/mL FSH, 1000 mIU/L TSH, and 2,000,000 pmol/L hCG β-core fragment, for both negative and positive urine samples. |
  | Interfering Substances | No interference from a list of common exogenous and endogenous substances at specified concentrations. | No interferences observed from the comprehensive list of 30 tested substances (e.g., Acetaminophen, Aspirin, Vitamin C, Ethanol, Bilirubin, Glucose) at their specified concentrations for both negative and positive urine samples. |
  | Effects of Urine pH | No interference in hCG detection across a physiological pH range. | Changes in pH range of 4-9 do not interfere with results for either positive (25 mIU/mL) or negative (0 mIU/mL) hCG urine samples. |
  | Effects of Specific Gravity | No interference in hCG detection across a range of urine specific gravities. | Urine samples with a specific gravity between 1.000-1.035 do not interfere with results for either positive (25 mIU/mL) or negative (0 mIU/mL) hCG urine samples. |
  | Hook Effect | No false negative results at very high hCG concentrations. | No hook effect observed at hCG concentrations ranging from 2325 to 1,860,000 mIU/mL; all tested concentrations gave a positive result. |
  | Method Comparison with Predicate Device | Substantial agreement (e.g., high positive and negative agreement) with the legally marketed predicate device. | All formats (Midstream-Dip, Midstream-Midstream, Cassette, Strip) showed 100% positive agreement and 100% negative agreement with the predicate device (HIGHTOP Pregnancy Rapid Test).
• Midstream (Dip): 38 Positive, 23 Negative (61 total) - 100% agreement.
• Midstream (Midstream): 40 Positive, 20 Negative (60 total) - 100% agreement.
• Cassette: 60 Positive, 49 Negative (109 total) - 100% agreement.
• Strip: 54 Positive, 49 Negative (103 total) - 100% agreement. |
  | Lay-User Comprehension & Performance | Users can adequately understand and use the instructions for use, perform the test, and interpret results correctly. | 333 subjects participated across three sites. The results from the lay-user study for each device format mirrored the 100% agreement found in the method comparison study.
  Questionnaire results indicated consumers found the test easy to use, and had no trouble understanding labeling or interpreting results. |

2. Sample sizes used for the test set and the data provenance

• Analytical Performance (Sensitivity/Reproducibility):

  • Sample Size: For each HCG concentration level (0, 12.5, 18.75, 22.5, 25, 50, 100, 200 mIU/mL), and for each of the three device formats (Dip, Midstream, Cassette, Strip), a total of 450 replicates were tested. This translates to (3 lots * 3 operators * 10 runs/day * 5 days = 450 replicates per concentration per format).
  • Data Provenance: The document does not explicitly state the country of origin for the samples used in the analytical performance studies. It mentions "Negative urine collected from females" and "Negative urine samples were spiked with varying hCG concentrations." This suggests controlled laboratory-prepared samples. It's an analytical study, not a clinical trial with patient samples. The manufacturer is based in China.
  • Retrospective/Prospective: These analytical studies appear to be prospective, controlled laboratory experiments designed specifically for device validation.

• Method Comparison Study & Lay-User Study (combined in the document):

  • Sample Size: Urine samples were collected from 333 women aged 18-49.
    • Synthgene Home Test HCG Test Midstream: 121 samples (61 dip, 60 midstream)
    • Synthgene Home Test HCG Test Cassette: 109 samples
    • Synthgene Home Test HCG Test Strip: 103 samples
    • Note: The sum of samples for each format (121+109+103 = 333) matches the total number of women, suggesting that each woman typically provided a sample tested by one specific format, or multiple samples which were divided among the different test formats. The samples were randomly collected.
  • Data Provenance: "Urine samples were collected from 333 women aged 18 - 49 who presented for pregnancy testing at 3 sites." The document does not specify the country of origin for these clinical samples or the sites. Given the manufacturer's location, China is a possibility, but not explicitly stated.
  • Retrospective/Prospective: The samples were "collected at various times throughout the day and blinded," which suggests a prospective clinical performance study.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• For the analytical performance studies, the ground truth was established by the known concentrations of spiked hCG in urine. This falls under controlled laboratory conditions, not requiring expert readers for ground truth.
• For the method comparison study, the predicate device (HIGHTOP Pregnancy Rapid Test) serves as the comparator, essentially establishing a "ground truth" relative to a legally marketed device. The document states "tested by professionals using the candidate devices and the predicate device." It does not specify the number or qualifications of these "professionals."
• For the lay-user study, the "ground truth" (actual pregnancy status, i.e., presence or absence of hCG) was likely based on the results from the predicate device that the professionals used, or potentially a reference lab method. The study's primary purpose was to assess the lay user's ability to use and interpret the device, rather than to establish a new ground truth.

4. Adjudication method for the test set

• Analytical Performance: Not applicable, as the ground truth is defined by the known spiked concentration.
• Method Comparison and Lay-User Studies: The document does not describe an explicit adjudication method (e.g., 2+1, 3+1). The comparison is direct, stating that samples were "blinded before being tested by professionals using the candidate devices and the predicate device." The results show 100% agreement, suggesting no need for further adjudication or dispute resolution between readers/methods.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• This question is not applicable as the device (HCG Test Strip/Cassette/Midstream) is a rapid diagnostic test and not an AI/ML-powered medical device. It does not involve human readers interpreting images with or without AI assistance. The "reader" in this context is the lay user or a professional reading a visual line on a test strip.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• This question is not applicable as the device is not an AI/ML algorithm. Its performance is inherent to its biochemical reaction and visual readout, which is then interpreted by a human user.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)

• Analytical Performance: Ground truth was established by known, spiked concentrations of hCG in urine, controlled in a laboratory setting.
• Method Comparison and Lay-User Studies: The ground truth for presence/absence of hCG was established by comparison to a legally marketed predicate device (HIGHTOP Pregnancy Rapid Test), used by professionals, and inferred from the women "who presented for pregnancy testing."

8. The sample size for the training set

• This document describes performance studies for market clearance (510(k)), not the development or training of an AI/ML model. Therefore, there is no "training set" in the context of machine learning. The studies described are validation and verification studies of a finished product.

9. How the ground truth for the training set was established

• This question is not applicable as there is no training set for an AI/ML model in this context.

Ask a specific question about this device

FaStep Early Pregnancy Rapid Test Strip is used for qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the day of the missed period, (i.e. as early as five (5) days before the day of the expected period). For over thecounter use.

FaStep Early Pregnancy Rapid Test Cassette is used for qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the day of the missed period, (i.e. as early as five (5) days before the day of the expected period). For over thecounter use.

FaStep Early Pregnancy Rapid Test Midstream is used for qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the day of the missed period, (i.e. as early as five (5) days before the day of the expected period). For overthe-counter use.

FaStep Early Pregnancy Rapid Test will be sold in Strip, Cassette and Midstream format. The Strip format is a single test strip. The Cassette format consists of a single test strip assembled in a plastic housing. The Midstream format consists of a single test strip assembled in a plastic housing with an absorbent tip, and is designed to be tested in dip or midstream mode.

FaStep Early Pregnancy Rapid Test Strip, FaStep Early Pregnancy Rapid Test Cassette and FaStep Early Pregnancy Rapid Test Midstream each contains a pouch with the device and instructions, and in addition, cassette format is packaged with pipette dropper.

The devices utilize a combination of antibodies to detect hCG in urine as well as to serve as a run control. Each device contains mouse monoclonal anti-ß-hCG antibody colloidal gold conjugate pre-dried on the sample pad. Mouse monoclonal anti-a-hCG antibody (on the Test Line) and goat anti mouse IgG polyclonal antibody (on the Control Line) are coated and immobilized on a nitrocellulose membrane. The result is displayed to the user in the test window as two lines for a 'Pregnant' positive result and one line for a 'Not Pregnant' negative result.

The provided document describes the performance and acceptance criteria for the FaStep Early Pregnancy Rapid Test Strip, Cassette, and Midstream devices.

Here's an analysis of the acceptance criteria and the study proving the device meets them:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly derived from the performance claims made for the device and the comparison to the predicate device. The primary performance metrics revolve around sensitivity (detection limit for hCG) and accuracy (agreement with professional testing and predicate devices, and lack of interference/cross-reactivity).

2. Sample Size and Data Provenance

• Test Set Sample Sizes:

  • Analytical Sensitivity (Precision/Reproducibility): For each format (Strip, Cassette, Midstream), 9 hCG concentrations tested. Each concentration had 10 replicates per day for 5 days, across 3 device lots, with 3 different operators. This sums to (9 concentrations * 10 replicates * 5 days * 3 lots * 3 operators = 1350 tests per format and per method for Midstream). More simply, the tables show 150 total results for each concentration level (50 per operator/lot). So, 9 concentrations * 150 results = 1350 tests per format.
  • Hook Effect: Multiple hCG concentrations (6,250 to 200,000 mIU/mL). Specific number of replicates not stated, but results demonstrated.
  • Interfering Substances: 3 hCG concentrations (0, 5, 10 mIU/mL) spiked with 25 substances. Number of replicates per substance not stated.
  • Cross-reactivity: 3 hCG concentrations (0, 5, 10 mIU/mL) spiked with 3 cross-reactants. Number of replicates per cross-reactant not stated.
  • hCG ß-core fragment effect: 4 hCG concentrations (0, 5, 10, 20,000 mIU/mL) spiked with 4 hCGBcf concentrations.
  • Urine pH effects: 3 hCG concentrations (0, 5, 10 mIU/mL) tested at 6 pH values.
  • Urine Density effects: 3 hCG concentrations (0, 5, 10 mIU/mL) tested at 8 density values.
  • Method Comparison: 321 urine samples collected from women.
    • Strip format: 110 samples.
    • Cassette format: 105 samples.
    • Midstream format (dip): 106 samples.
    • Midstream format (in-stream): 106 samples.
  • Lay Person Study (First Study - direct comparison): Total of 321 females.
    • Strip format: 110 subjects.
    • Cassette format: 105 subjects.
    • Midstream format (dip): 53 subjects.
    • Midstream format (in-stream): 53 subjects.
  • Lay Person Study (Second Study - spiked samples): Total of 300 laypersons (100 per device format). Each tested 4 blind-labeled samples. So, 400 tests per format.
  • Early Pregnancy Detection Study: 68 pregnant women provided 680 early pregnancy urine samples (from day -9 to 0 relative to expected period, presumably 10 samples per woman across these days). Each sample was tested with each format.
  • Specificity Study (False-Positive Rate): 900 urine samples collected from non-pregnant females. 300 participants per age group (pre-menopausal, peri-menopausal, post-menopausal). For each age group, 100 tested strip, 100 tested cassette, 100 tested midstream (method not specified, but likely implies dip or in-stream was representative, or it was split). Three batches of each format were used.

• Data Provenance:

  • Country of Origin: Not explicitly stated, but clinical studies were conducted at "three clinical sites," which typically implies the country where the manufacturer is located or seeking approval (likely USA given FDA submission).
  • Retrospective or Prospective:
    • Analytical studies (sensitivity, interference, etc.) are inherently prospective as they involve specific preparation and testing of samples.
    • Method comparison, lay person studies, early pregnancy detection study, and specificity study likely involved prospective collection of samples and testing as described (e.g., "Urine samples were collected from 321 women... at three clinical sites," "A lay user study was performed at three sites," "680 early pregnancy urine samples... were collected from 68 pregnant women," "900 urine samples were collected from non-pregnant females").

3. Number of Experts and Qualifications for Ground Truth

• Ground Truth for Analytical Studies (Sensitivity, Interfering substances, etc.): The ground truth for hCG concentration was established by spiking negative female urine with hCG standard traceable to the 5th WHO (World Health Organization) standard. This indicates a highly standardized and globally recognized reference. The "operators" who performed the tests are not explicitly described as "experts" in establishing ground truth, but rather trained personnel conducting the tests.
• Ground Truth for Method Comparison & Lay Person Studies (First Study): Ground truth was established by professional testing (laboratory professionals) and comparison to a predicate device. The document refers to "at least one professional at each site using the candidate device and by one professional at each site using the predicate device." Their specific qualifications are not detailed beyond "professional."
• Ground Truth for Lay Person Study (Second Study - Spiked Samples): The samples were blind labeled by the person who prepared the samples (and did not take part in testing). The ground truth for the spiked samples was their known hCG concentration. These spiked urine samples were also tested by professionals to generate professional results for comparison with layperson results.
• Ground Truth for Early Pregnancy Detection Study: The "positive results of B-ultrasound" (beta-ultrasound) served as the definitive ground truth for confirmed pregnancy at specific days relative to the expected menstrual period (EMP). This is a widely accepted clinical method for confirming pregnancy and gestational age.
• Ground Truth for Specificity Study: "Non-pregnant females" were tested. The ground truth for "non-pregnant" would inherently be established by clinical assessment, possibly including absence of a positive ultrasound and absence of HCG in other clinical tests at the time of study enrollment.

4. Adjudication Method for the Test Set

• No explicit "adjudication method" like 2+1 or 3+1 is mentioned for reconciling discordant results in the human studies.
• For the analytical studies (e.g., sensitivity), reproducibility involves comparing results across multiple operators and lots.
• For the method comparison and lay person studies, results are simply compared to the professional result or predicate device result. For the second lay person study, samples were "blind-labeled" with known concentrations, minimizing the need for adjudication of ground truth, but discrepancies between layperson and professional results are simply reported (e.g., "Percent Agreement").
• For the early pregnancy detection study, results were correlated with B-ultrasound findings, which serves as a definitive clinical ground truth, reducing the need for consensus-based adjudication of the test results themselves.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC comparative effectiveness study was done. This device is a rapid diagnostic test (HCG test strip/cassette/midstream) for direct visual reading by a single user (professional or layperson), not an imaging device that would typically involve multiple readers interpreting complex images. Therefore, a study comparing human readers with and without AI assistance is not applicable.

6. Standalone (Algorithm Only) Performance

• This is not an AI/algorithm-based device. It is a visually read immunoassay. Therefore, a standalone performance study of an algorithm is not applicable. The device's performance is inherently tied to the user's visual interpretation, even for "professional" use. However, the "Analytical performance" section could be considered the "standalone" performance in the sense of the device's inherent capability under controlled conditions, demonstrating sensitivity and specificity based on the chemical reaction.

7. Type of Ground Truth Used

The types of ground truth used varied by study:

• Known hCG concentrations: For analytical sensitivity, hook effect, interfering substances, cross-reactivity, and effects of pH/density. These were generated in a lab setting by spiking negative urine samples with certified hCG standards.
• Results from a legally marketed predicate device: For the method comparison study.
• Professional testing/interpretation: For comparison in the lay person studies.
• B-ultrasound (beta-ultrasound): For the early pregnancy detection study, serving as the definitive clinical confirmation of pregnancy.
• Clinical status of "non-pregnant": For the specificity study, based on a cohort of non-pregnant females.

8. Sample Size for the Training Set

• This document describes a 510(k) premarket notification for an in vitro diagnostic (IVD) test kit, not an AI/ML software device. As such, there is no "training set" in the context of machine learning model development. The data presented here are for validation/testing of the device's performance against its claims to establish substantial equivalence.

9. How the Ground Truth for the Training Set was Established

• As explained in point 8, there is no "training set" for an AI/ML model for this type of IVD device. The various ground truths used for the validation studies are described in point 7.

Ask a specific question about this device

The iHealth® Early Pregnancy Test is an OTC in vitro diagnostic test used to assess early pregnancy by detecting the presence of the hCG (human chorionic gonadotropin) hormone in urine. The test device is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the missed period, i.e., as early as five (5) days before the day of the expected period.

The iHealth® Early Pregnancy Test Strip is an OTC in vitro diagnostic test used to assess early pregnancy by detecting the presence of the hCG (human chorionic gonadotropin) hormone in urine. The test device is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the missed period, i.e., as early as five (5) days before the day of the expected period.

The iHealth® Early Pregnancy Test is a lateral flow immunoassay technique device designed for the qualitative determination of human chorionic gonadotropin (hCG) concentration in human urine samples, and is indicated for use as an aid in early detection of pregnancy. The iHealth® Early Pregnancy Test is designed to detect as early as six (6) days before the day of the missed period, i.e., as early as five (5) days before the day of the expected period. Test result is displayed to the user as two lines for a 'Pregnant' result and one line for a 'Not Pregnant' result.

The iHealth® Early Pregnancy Test are in two different formats: Stick and Strip format. Two test formats use identical strips and each test strip in the device consists of: Sample pad, colloidal gold binding pad, nitrocellulose membrane, absorbent paper and PVC board, colloidal gold binding pad coated with hCG monoclonal antibody 1, test line(T Line) coated with hCG-monoclonal antibody 2 and control line(C Line) coated with goat anti-mouse IgG antibody.

Two formats have the same performance specifications. The difference is that Stick format is designed to be tested in dip or midstream method, and Strip format is tested in dip method only.

The provided document describes the iHealth® Early Pregnancy Test and iHealth® Early Pregnancy Test Strip, which are over-the-counter in vitro diagnostic devices used to detect human chorionic gonadotropin (hCG) in urine for early pregnancy detection.

Here's a breakdown of the acceptance criteria and the studies performed:

1. A table of acceptance criteria and the reported device performance:

The document doesn't explicitly state "acceptance criteria" in a separate table. However, based on the performance characteristics presented, the key acceptance criteria for this type of device would typically revolve around its analytical sensitivity (detection limit) and its ability to accurately classify pregnant and non-pregnant states. The sensitivity of hCG detection is a critical performance metric for early pregnancy tests.

Table 1: Key Performance Metrics for iHealth® Early Pregnancy Tests

2. Sample sizes used for the test set and the data provenance:

• Analytical Sensitivity (Precision):

  • Test Set Sample Size: 405 individual tests for each hCG concentration (0, 3, 5, 7.5, 10, 12.5, 15, 25 mIU/mL) for each device format (Strip, Stick-dip, Stick-midstream), totaling 8 concentrations x 405 tests = 3240 tests per device type. The total number of individual readings is significantly higher due to multiple lots and operators. For the 5 mIU/mL the total samples are 170 negative and 235 positive in the Strip format.
  • Data Provenance: Not explicitly stated, but the study was performed "at three sites" by "nine operators," suggesting a multi-site internal study. The samples were "Not-pregnant female urine was spiked with hCG traceable to the 5th WHO international standard".

• Specificity Study:

  • Test Set Sample Size: 300 urine samples (100 from premenopausal, 100 from peri-menopausal, 100 from postmenopausal women).
  • Data Provenance: Not explicitly stated, but implies collected urine samples.

• Hook Effect Test:

  • Test Set Sample Size: Not explicitly quantified, but performed on urine samples spiked with hCG at 0, 10, 1,000, 10,000, 100,000, and 1,000,000 mIU/mL.

• Cross-Reactivity & Interfering Substances:

  • Test Set Sample Size: Not explicitly quantified. Performed on negative and 10 mIU/mL hCG positive urine samples spiked with various substances.

• Method Comparison Study:

  • Test Set Sample Size: 204 pregnant and non-pregnant subjects. 109 positive samples and 95 negative samples in total across both formats. iHealth® Early Pregnancy Test Strip: 103 samples (54 positive, 49 negative). iHealth® Early Pregnancy Test Stick: 101 samples (55 positive, 46 negative).
  • Data Provenance: Not explicitly stated, but implies collected samples from subjects.

• Lay User Study (Conformity with Professional):

  • Test Set Sample Size: 204 pregnant and not pregnant women subjects. iHealth® Early Pregnancy Test Strip: 103 subjects (54 positive, 49 negative). iHealth® Early Pregnancy Test Stick: 101 subjects (55 positive, 46 negative).
  • Data Provenance: Women subjects with diverse educational and professional backgrounds and ages between 18 and 55 years old who tested their own urine samples.

• Lay User Spiked Standard Study:

  • Test Set Sample Size: 100 women.
  • Data Provenance: Women with diverse educational and professional backgrounds (18-55 years old) who performed testing using spiked samples.

• Detection of hCG in Early Pregnancy Clinical Samples:

  • Test Set Sample Size: 83 subjects for each day relative to expected missed period (-8 to +1).
  • Data Provenance: Early pregnancy urine samples collected from subjects.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Analytical Sensitivity (Precision): The results were generated by "nine operators." Their specific qualifications are not detailed, but their involvement across three sites suggests trained personnel in a laboratory or clinical setting.
• Method Comparison and Lay User Studies: The "professional testing" serves as the reference standard against which the lay user and candidate devices were compared. The number and qualifications of these "professionals" are not specified in the document.
• Detection of hCG in Early Pregnancy Clinical Samples: The "early pregnancy urine samples" themselves imply a clinical diagnosis of pregnancy, which would typically be established by medical professionals. However, the number and qualifications of these professionals are not explicitly stated.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

The document does not describe an explicit adjudication method for reconciling conflicting results, such as 2+1 or 3+1. For the analytical studies, the results are presented as counts of positive/negative outcomes, implying a direct outcome rather than expert adjudication. For the comparison studies, results are compared to a "professional" result, which acts as a gold standard, so an adjudication process for discrepancies would implicitly fall under how the "professional" result was determined.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, if so, what was the effect size of how much human readers improve with AI vs without AI assistance:

This is not applicable to the device described. The iHealth® Early Pregnancy Test is an in vitro diagnostic (IVD) device that provides a visual result (lines on a stick/strip) for human interpretation. It is not an AI-assisted diagnostic tool for human readers interpreting complex medical images or data. Therefore, an MRMC study assessing AI assistance is not relevant here.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

This is not applicable. The device provides a visual output that is then interpreted by the user (human-in-the-loop). Even the "professional testing" involves human interpretation of the device's output. The device itself is not a standalone algorithm that provides a diagnosis without human interaction/interpretation of the visual signal.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• Analytical Sensitivity (Precision): The ground truth was established by spiking not-pregnant female urine with known concentrations of hCG traceable to the 5th WHO international standard. This is a scientific, controlled ground truth.
• Specificity: The ground truth was based on urine samples from normal, non-pregnant women. Clinical status (non-pregnant) served as the ground truth.
• Method Comparison and Lay User Studies: The ground truth for these studies was the result obtained by professional testing using the candidate device or the predicate device. This implies a reference method result, likely also interpreted by professionals.
• Detection of hCG in Early Pregnancy Clinical Samples: The ground truth for "early pregnancy urine samples" implies a clinical diagnosis of pregnancy based on medical assessment, which is outcomes data (known pregnancy status) rather than just a subjective expert consensus on the device's result.

8. The sample size for the training set:

The document describes performance studies (analytical and clinical comparisons) but does not mention a training set sample size. This is expected as the iHealth® Early Pregnancy Test is a lateral flow immunoassay, which is a chemical/biological test, not a machine learning model that requires a "training set."

9. How the ground truth for the training set was established:

Since there is no "training set" in the context of a machine learning model for this device, this question is not applicable. The device's performance is intrinsically linked to the chemical properties of the antibodies and reagents used, validated through the performance studies described.

Ask a specific question about this device

The HCG Home Use Pregnancy Test Strip (Colloidal Gold) is a rapid chromatographic immunoassay for the qualitative detection of human chorionic gonadotropin (hCG) in urine to aid in the early detection of pregnancy.
The test strip is designed for over-the-counter use.
Important note regarding positive results: This test may give positive results even if you are not pregnant. All results should be confirmed by your healthcare providers, especially when making decisions about future medical care. This device is intended for home use only.

The HCG Home Use Pregnancy Test Cassette (Colloidal Gold) is a rapid chromatographic immunoassay for the qualitative detection of human chorionic gonadotropin (hCG) in urine to aid in the early detection of pregnancy. The test cassette is designed for over-the-counter use.
Important note regarding positive results: This test may give positive results even if you are not pregnant. All results should be confirmed by your healthcare providers, especially when making decisions about future medical care. This device is intended for home use only.

The HCG Home Use Pregnancy Test Midstream (Colloidal Gold) is a rapid chromatographic immunoassay for the qualitative detection of human chorionic gonadotropin (hCG) in urine to aid in the early detection of pregnancy. The test midstream is designed for over-the-counter use.
Important note regarding positive results: This test may give positive results even if you are not pregnant. All results should be confirmed by your healthcare providers, especially when making decisions about future medical care. This device is intended for home use only.

The HCG Home Use Pregnancy Test Strip (Colloidal Gold), HCG Home Use Pregnancy Test Cassette (Colloidal Gold) and HCG Home Use Pregnancy Test Midstream (Colloidal Gold) utilize a combination of antibodies including a monoclonal HCG antibody to selectively detect elevated levels of HCG. The detection method is to observe the formation of colored lines when testing urine samples with test devices. The specimen migrates via capillary action along the membrane to react with the colored conjugate. Positive specimens react with the specific antibody-HCG-colored conjugate and form a red colored line at the test line region of the membrane. The absence of this colored line suggests a negative result. To serve as a procedural control, a colored line will always appear in the control line region if the test has been performed properly. HCG Pregnancy Test will be sold in three different formats: Cassette, Strip, and Midstream. The Test Strip and Midstream format contain a test device sealed in a desiccated aluminum pouch and an Instruction. The Cassette format contains a test device, a dropper, a collection container and an Instruction. The test uses two red lines to indicate results. Two distinct red lines appear in the control region (C) and test region (T) means the test is "positive". Only one red line appears in the control region(C). No apparent line in the test region (T). means the test is "negative". If No coloured line appears in the control region (C), or if there is no color band in control region (C) even there is a band in the test region (T),this means "invalid" test result.

The provided text describes different aspects of the HCG Home Use Pregnancy Test devices, including acceptance criteria and study results. However, it does not explicitly state acceptance criteria in a dedicated section with pass/fail metrics. Instead, the performance characteristics implicitly define the acceptance criteria by demonstrating performance comparable to the predicate device and meeting expected analytical standards for a qualitative pregnancy test. I will synthesize the information to best answer your request.

1. Table of Acceptance Criteria and Reported Device Performance

Since explicit numerical acceptance criteria are not stated, I will infer them from the reported analytical performance deemed acceptable for demonstrating substantial equivalence. The predicate device's characteristics also serve as an implicit benchmark.

2. Sample Size Used for the Test Set and Data Provenance

• Analytical Performance Studies (Precision, Specificity, Interference, etc.):

  • Precision/Reproducibility (Intra-batch, Inter-batch): For each of the three device formats (Strip, Cassette, Midstream), 3 lots were tested. For each lot and each of the 6 HCG concentration levels (0, 12.5, 18.75, 25, 50, 100 mIU/mL), 20 samples were tested. Total samples: 3 formats * 3 lots * 6 concentrations * 20 samples = 1080 samples.
  • Precision/Reproducibility (Inter-day, Inter-round): For each of the three device formats, 3 lots were tested. Over 5 days, with 2 runs per day, three operators tested blinded and randomized samples. For each lot and each of the 6 HCG concentration levels, the number of tests was (5 days * 2 runs per day * 20 samples) = 200 samples. Total samples: 3 formats * 3 lots * 6 concentrations * 200 samples = 10,800 samples.
  • Inter-laboratory Precision: For each of the three device formats, tests were performed at 3 sites using 3 lots. For each site, lot, and each of the 6 HCG concentration levels, the number of tests was (3 sites * 3 lots * 20 samples (implied from the table similar to batch precision)). Total samples: 3 formats * 3 sites * 3 lots * 6 concentrations * 20 samples = 3240 samples.
  • Cross-reactivity: Tested with specific concentrations of hLH, hFSH, hTSH using 3 lots of the test kits. The exact number of individual samples tested for each reactant is not specified, but it's stated "no cross reactivity was observed."
  • Interference: Tested with various common substances at specific concentrations for urine samples containing 0, 10, and 25 mIU/mL hCG. Three batches of each format were tested. The exact number of individual samples tested for each substance is not specified.
  • High Dose Hook Effect: 10 hCG-free specimens spiked at various high concentrations (5,000 to 1,000,000 mIU/mL) were tested on three lots of devices for each format. Total samples: 10 specimens * 8 concentrations * 3 lots * 3 formats = 720 samples.
  • HCG β-core fragment: Normal non-pregnant women urine specimens (0, 10, 25 mIU/mL hCG) spiked with varying concentrations of β-core fragment. Three lots of each format were tested. The exact number of individual samples tested is not specified.

• Clinical Studies (Method Comparison and Lay User Study):

  • Method Comparison with Predicate Device: A total of 300 urine samples from females of childbearing age (18 to 48 years) were collected. These were split for the 3 device formats: 100 for Strip, 100 for Cassette, 100 for Midstream. Within each device format, 50 positive and 50 negative samples were used.
  • Lay User Study: 300 women participated (100 for each device format: Strip, Cassette, Midstream). Each woman tested her own urine sample. Within each device format, 50 positive and 50 negative samples were used.

• Data Provenance:

  • Origin: The submitter is Anhui DEEPBLUE Medical Technology Co. LTD., located in Hefei, Anhui, People's Republic of China, and the designated correspondent is in Shanghai, China. The document does not explicitly state the country of origin for the samples, but given the company's location, it is highly likely the studies were conducted in China.
  • Retrospective or Prospective: The studies (both analytical and clinical) appear to be prospective as samples were collected and tested as part of the study design ("samples were collected at various time throughout the day and were randomized prior to testing," "A total of 300 urine samples from females of childbearing age were collected in this clinical trial").

3. Number of Experts and Qualifications

• Analytical Studies: "different operator" and "three operators" are mentioned for precision studies. No specific expert qualifications (e.g., radiologist) are provided, but these would typically be laboratory technicians or trained personnel.
• Clinical Studies (Method Comparison): "laboratory professionals at 3 clinical study unit" performed testing with the candidate device. "Results reported by a laboratory professional using the predicate device" were used for comparison in the lay user study. No specific qualifications beyond "laboratory professionals" are given.
• Ground Truth Establishment: The ground truth for HCG concentrations in analytical studies was established by spiking pooled negative female urine with HCG traceable to WHO 5th International Standards. For clinical studies, the predicate device results, as interpreted by laboratory professionals, served as the comparative ground truth.

4. Adjudication Method

• The document does not describe any formal adjudication method (e.g., 2+1, 3+1) for resolving discrepancies in the test results. For the precision studies, multiple operators and lots were used to demonstrate consistency, but no specific adjudication process for conflicting results is mentioned. For the method comparison and lay user studies, results were compared directly, and 100% agreement was reported, implying no need for adjudication for those specific metrics.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC comparative effectiveness study was done. The studies compared the device's performance to established HCG concentrations (analytical) or to a predicate device (clinical), and also assessed lay user performance against professional predicate results. There is no mention of comparing human readers' performance with and without AI assistance, as these are qualitative, visually-read home-use pregnancy tests, not AI-assisted imaging devices.

6. Standalone (Algorithm Only) Performance

• Yes, the device's analytical performance (sensitivity, specificity, interference, hook effect) can be considered its "standalone" performance, as it quantifies the ability of the test strip/cassette/midstream itself to detect/react to HCG in urine according to its chemical and biological design. The "method comparison" and "lay user study" sections further demonstrate the device's performance when interpreted by either professionals or lay users. Since this is a qualitative immunoassay, the "algorithm" is the biochemical reaction itself and the visual interpretation of colored lines.

7. Type of Ground Truth Used

• Analytical Studies:
  • For sensitivity and precision, the ground truth was known HCG concentrations in urine achieved by spiking pooled negative female urine with HCG (traceable to WHO 5th International Standard).
  • For specificity and interference, the ground truth involved known concentrations of potential interfering substances or cross-reactants.
• Clinical Studies (Method Comparison and Lay User Study):
  • The ground truth was established by the results of the predicate device as interpreted by laboratory professionals. This implies that the predicate device is considered the gold standard for comparison in these studies.

8. Sample Size for the Training Set

• This document describes performance studies for a medical device (HCG Home Use Pregnancy Test Strip, Cassette, Midstream). These devices are rapid chromatographic immunoassays and do not involve machine learning or AI models, therefore, there is no concept of a "training set" in the context of the provided information. The studies described are for validation of the device's analytical and clinical performance.

9. How the Ground Truth for the Training Set Was Established

• As stated above, this device does not utilize a training set in the machine learning sense.

Ask a specific question about this device

ShinetellTM Digital Pregnancy Test is a pregnancy test. It is used for the qualitative detection of hCG in human urine as an aid in early detection of pregnancy. For in vitro diagnostic use, for over the counter use.

Shinetell™ Digital Pregnancy Test is used for in vitro qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine, and is designed to be tested in dip or midstream mode. The test device consists of a single test strip assembled in a plastic housing, with an absorbent tip. The device is in a ready-to-use format. Shinetell™ Digital Pregnancy Test uses lateral flow immunoassay and light reflection for the detection of the HCG in urine specimens. The test would detect the light intensity by using the LED as the light source. After that, the result can be displayed on the display screen.

The provided document describes the Shinetell™ Digital Pregnancy Test, a device for the qualitative detection of hCG in human urine as an aid in early detection of pregnancy, for over-the-counter use. The document focuses on demonstrating the device's performance characteristics and its substantial equivalence to a legally marketed predicate device.

Here's a breakdown of the acceptance criteria and the study that proves the device meets these criteria:

1. Acceptance Criteria and Reported Device Performance

The document doesn't explicitly list "acceptance criteria" in a separate table, but the performance characteristics evaluated serve as the de facto criteria for demonstrating substantial equivalence. The key performance metrics and their reported results are:

2. Sample Sizes Used for the Test Set and Data Provenance

• Analytical Performance (Precision/Sensitivity):

  • Sample Size: For each hCG concentration (0, 12.5, 15, 18.75, 22.5, 25, 50, 100, 200 mIU/mL), 10 replicates were tested per day for 5 days for each of 3 device lots. With 3 operators, this resulted in 50 tests per operator per lot per concentration (10 replicates/day * 5 days), totaling 150 tests per concentration per lot.
  • Overall Sensitivity Sample Size: For the sensitivity conclusions, the most critical concentrations (0, 12.5, 25, 50, 100, 200 mIU/mL) each had 300 tests (3 lots * 50 replicates * 2 methods, or summarized directly as 300 total results).
  • Data Provenance: The document does not specify the country of origin for these spiked urine samples. It implies a laboratory setting for the spiking and testing, rather than patient samples. The study is retrospective in the sense that controlled samples were created for testing.

• Specificity and Cross-Reactivity:

  • Non-pregnant females: 300 samples (100 from each age group: pre-menopausal, peri-menopausal, post-menopausal).
  • Cross-reactive substances/hCG ß-core fragment: Number of samples not explicitly stated per substance/concentration, but it involved "negative and positive female urine samples" spiked with the substances.
  • Data Provenance: Not specified, but implied to be collected samples.

• Interfering Substances:

  • Number of samples not explicitly stated per substance/concentration, but involved "urine samples containing 0, 5 and 25 mIU/mL hCG" spiked with the substances.
  • Data Provenance: Not specified, implied to be collected urine samples spiked in a lab setting.

• Method Comparison Study:

  • Sample Size: 200 women presenting to test for pregnancy, suspected to be pregnant (early stage, less than 5 weeks).
  • Data Provenance: Retrospective, collected from patients at three Point-of-Care (POC) sites. Country of origin not specified.

• Lay Person Study:

  • First Study (self-testing): 200 women (individual pregnancy status self-tested).
  • Second Study (blinded spiked samples): 100 laypersons for 5 mIU/mL hCG aliquots and 100 laypersons for 25 mIU/mL hCG aliquots.
  • Data Provenance: "Individuals with varying educational and occupational backgrounds from three sites." Country of origin not specified. The first study used patient samples (their own urine); the second used controlled, spiked samples. Both are prospective in terms of the layperson testing event.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

• Analytical Performance (Precision/Sensitivity): Ground truth was established by the known concentration of hCG spiked into the negative urine samples, traceable to the 5th WHO International Standard. No human experts were used to interpret these results beyond confirming the digital readout.
• Specificity, Cross-reactivity, Interfering Substances: Ground truth was established by the known negative status of the samples or the known spiked concentrations.
• Method Comparison Study: The predicate device served as the "ground truth" for comparison. The study states "3 different professionals using the candidate device and 1 professional using the predicate device at each site." Their qualifications are not specified beyond "professionals."
• Lay Person Study:
  • First Study (self-testing): The "professional results" served as ground truth for comparison with layperson results. The qualifications of these "professionals" are not specified.
  • Second Study (blinded spiked samples): The known spiked concentration (5 mIU/mL hCG meant to be negative, 25 mIU/mL hCG meant to be positive) acted as the ground truth. A "study administrator" was present to observe; their role was not to establish ground truth but to monitor the study.

4. Adjudication Method for the Test Set

The document does not describe a formal "adjudication method" involving multiple readers/experts to resolve discrepancies for the test sets.

• For analytical performance, ground truth was by spiking, so no adjudication needed.
• For method comparison and lay person studies, comparison was made against the predicate device results or professional results (in the case of actual patient samples). In the second layperson study, ground truth was by known concentration. Discrepancies (if any arose) or how they were handled (e.g., re-testing, exclusion) are not explicitly detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No. This is a digital pregnancy test with a clear "Pregnant" or "Not Pregnant" readout, not an imaging device requiring human interpretation for complex diagnostic decisions. Therefore, a multi-reader multi-case (MRMC) comparative effectiveness study to assess how human readers improve with AI vs. without AI assistance is not applicable to this device. The "human readers" (laypersons) are using the device to get a direct digital output, not making an interpretation with or without AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, in essence, the "Analytical Performance" section (Precision/Sensitivity, Hook Effect, Specificity, Interfering Substances) represents the standalone performance of the device, as it evaluates the device's ability to detect hCG at various concentrations and in the presence of challenging substances, independent of human interpretation variability. The digital output is the algorithm's direct result.

7. The Type of Ground Truth Used

The types of ground truth used varied depending on the performance characteristic being evaluated:

• Known Spiked Concentrations: For sensitivity, hook effect, cross-reactivity (with defined interferers), and the second layperson study. This is a highly controlled, artificial ground truth.
• Clinical (Patient) Samples with Known Status (or compared to predicate/professional): For method comparison study and the first layperson study. Here, the "ground truth" was either the result from the legally marketed predicate device or the result from a "professional" using the candidate device, implying a clinical assessment of the patient's pregnancy status (e.g., confirmatory lab tests, clinical history).

8. The Sample Size for the Training Set

The document does not provide information on the training set size because this is not an AI/ML device that requires a separate "training set" in the conventional sense. This is an immunoassay device with a digital readout mechanism based on light intensity detection. Its "design" is based on biochemical and optical principles, not on learned parameters from a large dataset. Therefore, there's no "training set" as would be seen for, say, an image-recognition AI algorithm.

9. How the Ground Truth for the Training Set Was Established

As noted in point 8, there is no "training set" for this type of device in the context of an AI/ML algorithm. The device's operational parameters (e.g., thresholds for light intensity to display "Pregnant" or "Not Pregnant") are likely established during the device's development and internal validation processes using controlled, known concentrations of hCG, similar to the analytical performance testing described.

Ask a specific question about this device

Innovita HCG Pregnancy Rapid Combo Test is a rapid chromatographic immunoassay for the qualitative detection of human chorionic gonadotropin in urine or serum to aid in the early detection of pregnancy. The test is for health care professionals use including professionals at point of care (POC).

The Innovita HCG Pregnancy Rapid Combo Test measures the presence of the hormone Human Chorionic Gonadotrophin (HCG) in human urine or serum for the early detection of pregnancy. During pregnancy, HCG is produced by the placenta shortly after the embryo attaches to the uterine lining. The test device is used as a single cassette device.

The provided text describes the performance characteristics of the Innovita HCG Pregnancy Rapid Combo Test, a rapid chromatographic immunoassay for qualitative detection of human chorionic gonadotropin (HCG) in urine or serum to aid in early detection of pregnancy.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The "Acceptance Criteria" for this device are implicitly tied to its performance characteristics, aiming to demonstrate substantial equivalence to a legally marketed predicate device (K203272, Alltest Pregnancy Rapid Combo Test Cassette). The document doesn't explicitly list "acceptance criteria" as pass/fail thresholds in a formal table, but rather presents the results of various analytical studies that collectively support the device's accuracy, precision, and reliability.

However, based on the performance data presented, here's a table summarizing the implicit criteria and the reported performance:

2. Sample Sizes and Data Provenance

• Test Set Sample Size:

  • Precision/Reproducibility/Cut-Off Value Study: For each HCG concentration, 6 replicates per day for 5 days, using 3 different lots, across 3 testing sites. This totals 90 individual tests per concentration (6 replicates * 5 days * 3 lots = 90). The number of unique samples (negative serum/urine spiked with HCG) is not explicitly stated beyond "Negative serum or urine specimens from females were spiked with varying HCG concentrations."
  • High Dose Effect Study: Spiked samples tested by 3 different lots and 3 different operators. The exact number of replicate tests is not specified, but multiple concentrations were tested.
  • Effects of hCG ß-core fragment, LH, FSH, TSH interference studies: Samples tested by 3 different lots and 3 different operators. Number of replicates not specified.
  • Interference from Common Exogenous Compounds: Each spiked sample tested using 3 different lots; number of replicates per lot not specified.
  • Effect of Urine Specific Gravity and Urine pH: Tested using 3 different lots by 3 different operators; number of replicates not specified.
  • Method Comparison Study: 108 urine samples and 102 serum samples from 210 women.

• Data Provenance:

  • No specific country of origin is mentioned for the clinical samples. The submitter is INNOVITA (Tangshan) Biological Technology Co., Ltd. in China, and the contact person is in the USA.
  • The method comparison study states: "108 urine and 102 serum samples were collected from 210 women... from three testing sites." The study is described as "A method comparison study was performed," suggesting a prospective collection of samples for the purpose of the study, rather than retrospective. The samples were from "women expecting to be pregnant, early stage at less than 5 weeks."

3. Number of Experts and Qualifications for Ground Truth

• The document states that for the Precision/Reproducibility study, tests were performed by six different operators for each sample concentration across three sites, and the interference studies were performed by three different operators.
• The "Method Comparison Study" states: "Samples were tested by different health professionals with the proposed and the predicate devices at each site."
• Qualifications of these "operators" or "health professionals" are not specified beyond their role in performing the tests. No mention is made of "experts" specifically establishing a ground truth through consensus in the studies described.
• The ground truth for the analytical studies (precision, cut-off, interference) was established by the known concentrations of spiked HCG (traceable to the 5th WHO international Standard).
• For the comparative study, the "ground truth" was essentially the result of the predicate device (K203272). The study aims to show agreement with the predicate, not necessarily against an independent clinical "true" state confirmed by external means like pathology or clinical outcomes.

4. Adjudication Method for the Test Set

• For the analytical studies (precision, cut-off, interference), the "ground truth" was the known spiked concentration of HCG. The "adjudication" was the comparison of the device's result ("-" or "+") against this known concentration. There's no mention of an expert adjudication process in this context, as results are quantitative comparisons to predefined levels.
• For the Method Comparison Study, the document states "The study result shows 100% agreement for all samples to the predicate device." This implies a direct comparison of the new device's result to the predicate device's result for each sample. There's no indication of an adjudication method (e.g., 2+1 or 3+1 expert review) for resolving discrepancies, as presumably, there were no discrepancies ("100% agreement").

5. Multi Reader Multi Case (MRMC) Comparative Effectiveness Study

• No, an MRMC comparative effectiveness study, as typically understood for evaluating AI-assisted workflows in diagnostic imaging, was not performed. This device is a rapid diagnostic test kit, not an AI or imaging device that assists human readers.
• The comparison study was between the new device and a predicate device, both read by "different health professionals." The effectiveness is measured by agreement between the devices, not by human reader performance improvement with/without AI assistance.

6. Standalone (Algorithm Only) Performance

• This question is not applicable to this device. The Innovita HCG Pregnancy Rapid Combo Test is a lateral flow immunoassay cassette, not a software algorithm or an AI system that would have a "standalone" algorithmic performance. Its performance is intrinsically linked to the physical test kit's chemical reactions and visual interpretation.

7. Type of Ground Truth Used

• For the analytical performance studies (precision, cut-off, high dose, specificity, interference, pH/SG): The ground truth was analytical truth based on known, precisely controlled concentrations of HCG (traceable to WHO international standard) and interferents spiked into negative or known positive samples.
• For the method comparison study: The ground truth was effectively the results obtained from the legally marketed predicate device (K203272). This is a common approach for demonstrating substantial equivalence for in vitro diagnostic devices. No pathology or long-term clinical outcome data was used as ground truth for this submission.

8. Sample Size for the Training Set

• Not applicable / Not explicitly stated. This is a rapid diagnostic test kit, not a machine learning model that typically requires a large "training set" of data. The "training" of such a device is in its chemical and biological design and manufacturing process, not in data-driven algorithmic learning.

9. How the Ground Truth for the Training Set was Established

• Not applicable. As above, there's no "training set" in the context of an AI/ML device. The "ground truth" for developing and manufacturing such a chemical assay would involve rigorous quality control, calibration, and R&D studies based on established biological and chemical principles, likely using purified HCG standards and clinical samples. However, the document does not detail these developmental processes.

Ask a specific question about this device

MissLan® Early Detection Pregnancy Test Strip is used for qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the day of the missed period, (i.e. as early as five (5) days before the day of the expected period). It is intended for use by people who would like to find out whether they are pregnant in a home environment. Only for use outside the body. For over-the-counter use.

Important note regarding positive results:

Because this test detects low levels of hCG, it is possible that this test may give positive results even if you are not pregnant. All results should be confirmed by your healthcare provider, especially when making decisions about future medical care.

This device is intended for home-use only.

MissLan® Early Detection Pregnancy Test Cassette is used for qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the day of the missed period, (i.e. as early as five (5) days before the day of the expected period). It is intended for use by people who would like to find out whether they are pregnant in a home environment. Only for use outside the body. For over-the-counter use.

Important note regarding positive results:

Because this test detects low levels of hCG, it is possible that this test may give positive results even if you are not pregnant. All results should be confirmed by your healthcare provider, especially when making decisions about future medical care.

This device is intended for home-use only.

MissLan® Early Detection Pregnancy Test Midstream is used for qualitative detection of Human Chorionic Gonadotropin (HCG) in human urine. This test is intended for use as an aid in early detection of pregnancy, in some cases as early as six (6) days before the day of the missed period, (i.e. as early as five (5) days before the day of the expected period). It is intended for use by people who would like to find out whether they are pregnant in a home environment. Only for use outside the body. For over-the-counter use.

Important note regarding positive results:

Because this test detects low levels of hCG, it is possible that this test may give positive results even if you are not pregnant. All results should be confirmed by your healthcare provider, especially when making decisions about future medical care.

This device is intended for home-use only.

MissLan® Early Detection Pregnancy Test will be sold in Strip. Cassette and Midstream format. The Strip format is a single test strip. The Cassette format consists of a single test strip assembled in a plastic housing. The Midstream format consists of a single test strip assembled in a plastic housing with an absorbent tip, and is designed to be tested in dip or midstream mode.

MissLan® Early Detection Pregnancy Test Strip. MissLan® Early Detection Pregnancy Test Cassette and MissLan® Early Detection Pregnancy Test Midstream each contains a pouch with the device and instructions, and in addition, cassette format is packaged with pipette dropper and urine collection cup.

The devices utilize a combination of antibodies to detect hCG in urine as well as to serve as a run control. Each device contains mouse monoclonal anti-ß-hCG antibody colloidal gold conjugate pre-dried on the sample pad. Mouse monoclonal anti-a-hCG antibody (on the Test Line) and goat anti mouse IgG polyclonal antibody (on the Control Line) are coated and immobilized on a nitrocellulose membrane. The result is displayed to the user in the test window as two lines for a 'Pregnant' positive result and one line for a 'Not Pregnant' negative result.

The provided FDA 510(k) summary describes the acceptance criteria and study results for the MissLan® Early Detection Pregnancy Test Strip, Cassette, and Midstream devices.

Here's a breakdown of the requested information:

1. Table of acceptance criteria and reported device performance

The document does not explicitly state "acceptance criteria" as a separate section with numerical targets for each performance metric. However, the performance characteristics studies demonstrate that the device meets the necessary performance for its intended use, implying that the observed results constitute the criteria it should achieve. The predicate device's performance often forms the implicit benchmark for substantial equivalence.

Based on the provided data, the implicit acceptance criteria and reported performance are as follows:

2. Sample size used for the test set and the data provenance

Analytical Performance (Precision/Reproducibility/Sensitivity):

• Sample Size: 3 lots x 3 operators x 10 replicates x 9 hCG concentrations = 810 tests per device format. Since there are 4 effective formats (strip, cassette, midstream in-stream, midstream dip), this would be 810 x 4 = 3240 individual test results for this section.
• Data Provenance: Retrospective. Negative female urine was spiked with hCG standard.

Method Comparison Study:

• Sample Size: 400 women. Samples were divided: 100 for strip, 100 for cassette, 100 for midstream (dip), 100 for midstream (in-stream).
• Data Provenance: Prospective, collected from women aged 18 to 51 at three clinical sites. Approximately half were early pregnant. Samples were collected randomly throughout the day. Country of origin not specified, but typically US or manufacturer's country due to regulatory context.

Lay Person Study (First Study - Clinical Samples):

• Sample Size: 400 females (100 for each device format/method).
• Data Provenance: Prospective, from "diverse educational and occupational backgrounds and ages ranging from 18 to 51 years old" at three sites. Country not specified.

Lay Person Study (Second Study - Spiked Samples):

• Sample Size: 300 laypersons (100 for each device format). Each tested 4 blind-labeled spiked samples, so 300 * 4 = 1200 tests.
• Data Provenance: Retrospective, using negative urine samples spiked with hCG. Country not specified.

Early Pregnancy Detection Study:

• Sample Size: 65 pregnant women, contributing 650 early pregnancy urine samples (from day -8 to day +1 relative to the day of expected menstrual period).
• Data Provenance: Prospective, collected from pregnant women. Country not specified.

Specificity Study (False-Positive Results Rate):

• Sample Size: 900 urine samples from non-pregnant females (300 pre-menopausal, 300 peri-menopausal, 300 post-menopausal). These were divided further by device format (e.g., for each age group, 100 for strip, 100 for cassette, 50 for midstream dip, 50 for midstream in-stream).
• Data Provenance: Clinical, collected from non-pregnant females at three sites. Country not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Analytical Performance (Precision/Reproducibility/Sensitivity): 3 operators performed the tests for the device, but the "ground truth" for hCG concentration was based on spiking with a standard traceable to the 5th WHO.
• Method Comparison Study: "Three professionals at each site" tested the candidate device, and "one professional at each site" tested the predicate device. Their specific qualifications are not detailed beyond "professional." It's implied they are trained laboratory personnel.
• Lay Person Study (First Study - Clinical Samples): "Professional" testing was used as ground truth for comparison with layperson results. The number of professionals is not specified, nor their detailed qualifications, but it implies a single assessment for ground truth by trained personnel.
• Lay Person Study (Second Study - Spiked Samples): "Professional" testing was used as ground truth, but the ultimate ground truth was the known hCG concentration of the spiked samples.
• Early Pregnancy Detection Study: The ground truth for pregnancy status was established by B-ultrasound and HCG levels for the 65 pregnant women/650 samples. This refers to established clinical diagnostic methods, implying expert medical interpretation of ultrasound and quantitative lab HCG results.
• Specificity Study: The samples were collected from "non-pregnant females," implying a clinical determination of non-pregnancy as ground truth.

4. Adjudication method for the test set

• The document does not explicitly describe an adjudication method (such as 2+1 or 3+1 consensus) for establishing ground truth from multiple experts.
• In studies involving comparisons (e.g., method comparison, layperson study), results from "professionals" or "known spiked concentrations" served as the reference standard (ground truth). For the early pregnancy detection study, B-ultrasound and HCG levels were the ground truth, which are typically conclusive diagnostic methods.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No, a multi-reader, multi-case (MRMC) comparative effectiveness study was not conducted, nor is this device an AI-assisted device. This device is a rapid in-vitro diagnostic (IVD) test for qualitative detection of HCG. The "readers" are either laypersons or professionals interpreting a visual line on a test strip.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

• This question is not applicable as the device is a manual, visually interpreted rapid diagnostic test, not an algorithm or software. It is inherently human-in-the-loop (for reading the result).
• However, the analytical performance studies (e.g., precision, hook effect, interfering substances) could be considered "standalone" in the sense that they assess the device's chemical and physical characteristics independent of human interpretation variability, but still involve human technicians performing the tests.

7. The type of ground truth used

• Analytical Performance Studies (Precision/Reproducibility, Hook Effect, Interfering Substances, Cross-Reactivity, HCG ß-core fragment, pH, density): Ground truth was based on known spiked concentrations of hCG (traceable to WHO standard) or interfering substances into negative urine.
• Method Comparison Study: Ground truth was established by comparison to a legally marketed predicate device (Wondfo One Step HCG Urine Pregnancy Test) and/or potentially by clinical reference methods by professionals.
• Lay Person Study (First Study): Ground truth was established by professional testing results of the same clinical urine samples.
• Lay Person Study (Second Study): Ground truth was based on known spiked concentrations of hCG and confirmed by professional testing.
• Early Pregnancy Detection Study: Ground truth was established by clinical B-ultrasound and HCG levels to confirm pregnancy status and gestational age.
• Specificity Study: Ground truth was the clinical diagnosis of non-pregnant females.

8. The sample size for the training set

• The document does not specify a separate "training set" for the device. This is typical for traditional rapid diagnostic tests, which are validated against established performance metrics rather than trained via machine learning. The studies described are validation and verification studies.

9. How the ground truth for the training set was established

• As there's no specified "training set" in the context of machine learning, this question is not directly applicable. The ground truth for validation/verification studies was established as described in point 7.

Ask a specific question about this device

The Distinct® Digital Pregnancy Test is an over-the-counter chromatographic immunoassay for the qualitative detection of human chorionic gonadotropin (hCG) in urine. It is intended for use as an aid for the early detection of pregnancy. This test can help determine if you are pregnant as early as 6 days before the day of the missed period (5 days before the day of your expected period).

Not Found

This letter is an FDA clearance letter and does not contain the detailed information necessary to answer all the questions about the acceptance criteria and the study proving the device meets them. The letter confirms that the Distinct® Digital Pregnancy Test has been found substantially equivalent to predicate devices and can be marketed.

However, based on the provided text, here's what can be extracted and what cannot:

1. A table of acceptance criteria and the reported device performance

The clearance letter does not provide a table of acceptance criteria or reported device performance metrics like sensitivity, specificity, accuracy, etc. These details would typically be found in the 510(k) submission summary or the device's labeling (instructions for use).

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

This information is not present in the FDA clearance letter.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not present in the FDA clearance letter. Since this is an over-the-counter diagnostic test for hCG in urine, the "ground truth" for a pregnancy test is typically established by laboratory methods that accurately quantify hCG levels, rather than interpretation by a panel of medical experts.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not present in the FDA clearance letter.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, if so, what was the effect size of how much human readers improve with AI vs without AI assistance

This information is not present in the FDA clearance letter. This device is a "Distinct® Digital Pregnancy Test," implying it's a test that gives a digital readout (e.g., "Pregnant" or "Not Pregnant"). It's unlikely to be an AI-assisted diagnostic tool that requires human reader interpretation in the context of an MRMC study.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

This information is not explicitly stated as an "algorithm only" study. However, as an over-the-counter digital pregnancy test, its performance is inherently standalone, meaning the user follows instructions and the device provides the result without further human interpretation beyond reading the digital display. The device itself is the "algorithm" in this context.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The ground truth for a pregnancy test like this would be established by quantitative laboratory analysis of human chorionic gonadotropin (hCG) levels in urine or blood, which is the gold standard for confirming pregnancy. The letter mentions the test is for "qualitative detection of human chorionic gonadotropin (hCG) in urine."

8. The sample size for the training set

This information is not present in the FDA clearance letter.

9. How the ground truth for the training set was established

This information is not present in the FDA clearance letter. However, similar to the test set, the ground truth for the training set (if applicable for a digital test that might use some internal calibration or digital processing) would also be established through reference methods for detecting and quantifying hCG.

Ask a specific question about this device