FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The Co-Innovation One Step HCG Test Strip is an in vitro diagnostic visual qualitative immunochromatographic assay designed for the rapid determination of human chorionic gonadotropin (hCG) in urine to aid in the early detection of pregnancy. It is intended for over-the-counter (OTC) use.

The Co-Innovation One Step HCG Test Cassette is an in vitro diagnostic visual qualitative immunochromatographic assay designed for the rapid determination of human chorionic gonadotropin (hCG) in urine to aid in the early detection of pregnancy. It is intended for over-the-counter (OTC) use.

The Co-Innovation One Step HCG Test Midstream is an in vitro diagnostic visual qualitative immunochromatographic assay designed for the rapid determination of human chorionic gonadotropin (hCG) in urine to aid in the early detection of pregnancy. It is intended for over-the-counter (OTC) use.

Device Description

Co-Innovation One Step Human Chorionic Gonadotropin (HCG) Test is a rapid sandwich immunoassay device designed for the qualitative determination of human chorionic gonadotropin (hCG) concentration in human urine samples, as an aid in the early detection of pregnancy. The test devices are in three different formats: Strip, Cassette and Midstream . Three test formats use identical strips and each test strip in the device consists of:

A conjugate pad contains colloidal gold conjugated with mouse monoclonal anti-B-HCG antibody specific to the beta subunit of hCG.
A nitrocellulose membrane which is striped with the mouse monoclonal anti-a-HCG antibody in the test line (T line) and goat anti-mouse IgG polyclonal antibody in the control line (C line).

The Cassette format has the same performance specifications as the Test Strip format. The difference is that the urine sample is dispensed by dropper onto the sample well on the cassette.

The Midstream format has the same performance specifications as the Test Strip format. The difference is that the device is placed into the urine stream or dipped into the urine collection cup for 5 seconds.

AI/ML Overview

Here's an analysis of the provided 510(k) summary, detailing the acceptance criteria and the studies conducted to demonstrate the device's performance:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally implied by the successful outcomes presented in the study results, particularly for precision and sensitivity, as no explicit numerical acceptance targets are stated (e.g., "sensitivity must be >99%"). However, the performance data clearly demonstrates that the device meets the implicit requirement for accurate qualitative detection of HCG at the clinical cut-off of 25mIU/mL.

Acceptance Criterion (Implicit)	Reported Device Performance
Precision: Consistent positive results at/above 25mIU/mL and negative results below 25mIU/mL.	Precision (Strip, Cassette, Midstream - all methods):

0mIU/mL, 12.5mIU/mL, 18.75mIU/mL: 100% negative (30/30 for each LOT and concentration).
25mIU/mL, 50mIU/mL, 100mIU/mL: 100% positive (30/30 for each LOT and concentration). |
| Sensitivity: Detect HCG at the clinical cut-off of 25mIU/mL. | Sensitivity: 25mIU/mL (derived from precision study, showing 100% detection at this concentration). |
| Specificity: No cross-reactivity with common related hormones. | Specificity: No cross-reaction observed with LH at 500mIU/mL, FSH at 1000mIU/mL, and TSH at 1000uIU/ml in urine specimens containing 0 mIU/ml and 25mIU/ml HCG. |
| Interference: No interference from common exogenous compounds. | Interference: No interferences observed from Acetaminophen, Aspirin, Ascorbic acid, Atropine, Caffeine (all at 20mg/dL), Glucose (2000mg/dL), Hemoglobin (500mg/dL), Tetracycline, Ampicillin (all at 20mg/dL), Albumin (2000mg/dL), Bilirubin (2mg/dL) for both negative and positive HCG samples. |
| HCG ß-core fragment interference: No interference from high levels of HCG ß-core fragment. | HCG ß-core fragment interference: No interference was observed when spiked at 125,000, 250,000, 500,000, and 1,000,000 pmol/mL in urine samples containing 0 and 25 mlU/ml HCG. |
| pH interference: Stable performance across a physiological pH range. | pH interference: Varying pH ranges (3 to 9 in 1 pH unit increments) did not interfere with test performance for 0mlU/ml and 25mlU/ml HCG samples. |
| Specific gravity interference: Stable performance across a physiological range of specific gravity. | Specific gravity interference: No interference was observed when specific gravity was between 1.01-1.04 for purified water and 25mIU/mL HCG spiked specimens. |
| Urinary system diseases interference: No interference from markers of urinary conditions. | Urinary system diseases interference: No interference observed from strongly positive white blood cells, urine occult blood, uric acid, and urine ketone in urine samples containing 0mlU/ml and 25mlU/ml HCG. |
| Hook effect: Maintain positive results at high HCG concentrations. | Hook effect: Generated positive results for HCG concentrations from 62,500mIU/ml to 1,000,000mIU/ml. (Note: "T line get to light as the concentration above 125000mlU/ml" indicates the test still works, but potentially with reduced band intensity, which is acceptable for qualitative detection and does not lead to false negatives at very high concentrations). |
| Method Comparison (Professional User): High agreement with predicate device results. | Professional Method Comparison (Strip, Cassette, Midstream - all methods): 100% agreement with the predicate device for all formats. (e.g., for Strip, Professional A: 38 Positive, 42 Negative; Professional B: 38 Positive, 42 Negative, all matching the predicate). |
| Method Comparison (Lay User): High agreement with professional test results. | Lay User Method Comparison (Strip, Cassette, Midstream - all methods): 100% agreement with professional laboratory results using the candidate device for all formats. (e.g., for Strip, Lay Users: 38 Positive, 42 Negative, all matching the professional results). |
| OTC User Performance: Untrained users can obtain correct results reliably. | OTC User Study:
Strip: 29/30 correct positive (31.25mIU/ml), 30/30 correct negative (18.75mIU/ml).
Cassette: 30/30 correct positive, 30/30 correct negative.
Midstream (dip): 30/30 correct positive, 30/30 correct negative.
Midstream (simulated midstream): 30/31 correct positive, 29/29 correct negative.
Conclusion: Untrained operators can get correct results. |

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

Precision Study: 30 clinical samples (normal, non-pregnant female urine) were spiked with HCG at 6 different concentrations (0mIU/ml, 12.5mIU/ml, 18.75mIU/ml, 25mIU/ml, 50mIU/ml, 100mIU/ml). Each concentration had 30 samples tested per LOT, across 3 lots, yielding 90 tests per concentration per format. The study was conducted over 10 days, 3 runs/day.
- Provenance: Clinical samples from "normal, non-pregnant females." The document does not explicitly state the country of origin, but the submitter is from Guangzhou, China, and the OTC user study sites are in Guangzhou, Shanghai, and Wuhan, suggesting a Chinese origin. The study appears to be a prospective experimental study using spiked samples.
Specificity Study: 60 urine specimens (containing 0 mIU/ml and 25mIU/ml HCG) were spiked with LH, FSH, and TSH. Tested across 3 lots.
- Provenance: Not explicitly stated, likely similar to precision study. Prospective experimental study.
Interfering Substances Study: Normal, non-pregnant female urine specimens (0 and 25 mIU/ml HCG) were spiked with 11 different compounds. 3 batches of each format were tested for each interferent.
- Provenance: Not explicitly stated, likely similar to precision study. Prospective experimental study.
HCG ß-core fragment Interference Study: Normal, non-pregnant female urine specimens (0 and 25 mlU/ml HCG) were spiked with 4 different concentrations of HCG ß-core fragment. 3 batches of each format were tested.
- Provenance: Not explicitly stated, likely similar to precision study. Prospective experimental study.
pH Interference Study: Aliquoted negative urine pool adjusted to pH 3-9, spiked with 0mlU/ml and 25mlU/ml HCG. 3 batches were tested repeatedly.
- Provenance: Not explicitly stated, likely similar to precision study. Prospective experimental study.
Specific Gravity Interference Study: Purified water and 25mlUml HCG spiked specimens formulated with specific gravity 1.01-1.04. 3 lots tested.
- Provenance: Not explicitly stated, likely similar to precision study. Prospective experimental study.
Urinary System Diseases Interference Study: Urine specimens with strongly positive markers (white blood cells, occult blood, uric acid, urine ketone) prepared with 0mlU/ml and 25mlU/ml HCG. 3 lots tested repeatedly.
- Provenance: Not explicitly stated, likely clinical samples. Prospective experimental study.
HOOK Effect Study: HCG free specimens spiked with 5 different very high HCG concentrations (62,500mIU/m1 to 1,000,000mIU/ml). Three lots tested.
- Provenance: Not explicitly stated, likely similar to precision study. Prospective experimental study.
Professional Method Comparison: 353 urine samples collected from women at a hospital laboratory. "Approximately half of the women were pregnant in the early stage of less than 5 weeks." Ages 18-45 years.
- Provenance: Clinical samples from a hospital laboratory. Not explicitly stated, but likely China given other study locations. Retrospective (samples collected, then tested) or prospective (samples collected specifically for the study) clinical study.
Lay User Method Comparison: The same 353 urine samples as the Professional Method Comparison.
- Provenance: Clinical samples, likely China. Retrospective or prospective clinical study.
- Specific breakdown for lay users: 80 using strip, 113 using cassette, 160 using midstream (actual + dip methods combined).
OTC User Performance: 240 female subjects (untrained operators, ages 18-45) tested masked spiked urine samples (120 containers of 18.75mlU/ml and 120 of 31.25mlU/ml). Each subject performed 1 test on one format/method.
- Provenance: Samples were spiked. Subjects from Guangzhou, Shanghai, and Wuhan, China. Prospective experimental study (simulated home use).

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

Precision, Specificity, Interference, pH, Specific Gravity, Urinary System Diseases, HOOK Effect Studies: The ground truth (HCG concentration, presence/absence of interferents) was established by spiking known concentrations of HCG or interfering substances, traceable to WHO standards or determined by immunoassay (ELISA). This does not involve human experts establishing ground truth for individual test samples, but rather analytical methods.
Professional Method Comparison: The "ground truth" for this study was the result obtained by the predicate device when tested by laboratory professionals. The exact number of professionals is not specified, but the study was conducted at "two laboratories (namely Professional A and Professional B)", implying at least two professionals. Their qualifications are stated as "laboratory professionals."
Lay User Method Comparison: The "ground truth" for this study was the result obtained by laboratory professionals using the candidate device. The number of laboratory professionals is not specified, but it was conducted at "a laboratory." Their qualifications are "laboratory professionals."
OTC User Performance: The "ground truth" for this study was established by masked spiked urine samples (known HCG concentrations) and independently verified by professional laboratory personnel at the manufacturer site. The number of professionals is not specified, and their exact qualifications are not detailed beyond "professional laboratory personnel."

4. Adjudication Method for the Test Set

For the analytical performance studies (Precision, Specificity, Interference, etc.), adjudication generally involves comparing the device's output to the known, spiked concentration or condition. There's no human adjudication process described beyond analytical confirmation of spike levels.
For the Professional Method Comparison and Lay User Method Comparison, the comparison is against the predicate device or professional results of the candidate device. The agreement is tabulated directly, implying no specific "adjudication" if disagreement occurred, as 100% agreement was reported.
For the OTC User Performance study, the lay users' results were compared against the "masked spiked sample professional users" results (i.e., known spiked concentration verified by professionals). Again, no specific adjudication process for discrepancies is described, as the focus is on the agreement rate.

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

There was no MRMC comparative effectiveness study done, as this device is a qualitative diagnostic test (HCG pregnancy test) not an imaging device typically analyzed by human readers with or without AI assistance. The studies involve human users (professional or lay) interpreting the test results visually, but not in a context typically requiring MRMC analysis.

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

This device is a visual qualitative immunochromatographic assay. There is no "algorithm" in the sense of a software-based AI. The performance is inherently "standalone" in that it produces a visual result (a line) and the interpretation is human-in-the-loop (reading the line). The "performance" studies are effectively standalone because they evaluate the test's ability to produce the correct visual output given an HCG concentration. The OTC user study then evaluates the human (lay user) interpretation of this visual output.

7. The Type of Ground Truth Used

Spiked Samples (Precision, Specificity, Interference, Hook Effect, pH, Specific Gravity, Urinary System Diseases, OTC User Study): The ground truth was established by laboratory control, adding known concentrations of HCG (traceable to WHO 3rd IS) or interfering substances to urine samples. This is a form of analytical or engineered ground truth.
Professional Method Comparison: The ground truth was the result from the predicate device.
Lay User Method Comparison: The ground truth was the result from professional users testing the candidate device.

8. The Sample Size for the Training Set

There is no explicit training set described in this 510(k) summary. This type of device (lateral flow immunoassay) typically does not involve a machine learning model that requires a distinct "training set." The development process for such a device relies on chemical and biological engineering principles, optimization of reagents, and initial analytical testing, rather than an iterative machine learning training process with labeled data.

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

As no explicit training set for a machine learning algorithm is mentioned, pertinent to the nature of this device, the question of how ground truth was established for a training set is not applicable. The ground truth for the performance evaluations (test sets) was established as described in section 7.

Summary

Regulation Number and Section

§ 862.1155 Human chorionic gonadotropin (HCG) test system.

(a)
Human chorionic gonadotropin (HCG) test system intended for the early detection of pregnancy —(1)Identification. A human chorionic gonadotropin (HCG) test system is a device intended for the early detection of pregnancy is intended to measure HCG, a placental hormone, in plasma or urine.(2)
Classification. Class II.(b)
Human chorionic gonadotropin (HCG) test system intended for any uses other than early detection of pregnancy —(1)Identification. A human chorionic goadotropin (HCG) test system is a device intended for any uses other than early detection of pregnancy (such as an aid in the diagnosis, prognosis, and management of treatment of persons with certain tumors or carcinomas) is intended to measure HCG, a placental hormone, in plasma or urine.(2)
Classification. Class III.(3)
Date PMA or notice of completion of a PDP is required. As of the enactment date of the amendments, May 28, 1976, an approval under section 515 of the act is required before the device described in paragraph (b)(1) may be commercially distributed. See § 862.3.