Search Results

The Nova Allegro HbA1c Assay is intended for in vitro diagnostic use on the Nova Allegro Analyzer for the quantitative determination of the glycated Hemoglobin A1c) in capillary whole blood obtained from the fingertip. The results from this assay are intended to be used for the monitoring of long-term blood glucose/metabolic control in individuals with diabetes mellitus.

The Nova Allegro Analyzer is intended for in vitro diagnostic use in clinical laboratory and near-patient testing (point-of-care) settings for the quantitative determination of Nova Allegro Assays using Nova Allegro Test Cartridges.

Nova Allegro Analyzer: The Nova Allegro Analyzer is a compact, point-of-care analyzer that features a clinically important menu of measured and calculated tests. All tests are measured with disposable, ready-to-use cartridges, and are easily performed by non-technical personnel. The analyzer supports multiple wavelengths that are used to measure the assay of interest. The analyzer consists of the following key systems/components that the user interacts with: Two analytical bays where the single use test cartridges are analyzed, Color Touchscreen Display, Barcode Scanner, Printer, Data Export Options, Ethernet Connection, USB Port.

Nova Allegro HbA1c Assay: The Allegro HbA1c Assay is a completely automated assay for the HbA1c in human whole blood and the calculation of estimated average glucose (eAG). Nova Allegro HbA1c Test Cartridges are the key element a user interacts with to obtain the HbA1c concentration in a Capillary finger-stick whole blood sample. The main components of the Test Cartridge are the Capillary that is used to obtain the Capillary finger-stick whole blood specimen and present it to the Test Cartridge and the reaction chamber. The Test Cartridge has a barcode label with lot specific information.

The provided text describes the performance testing of the Nova Allegro HbA1c Assay and Nova Allegro Analyzer for the quantitative determination of glycated Hemoglobin A1c (HbA1c) in capillary whole blood.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document describes various performance tests and their outcomes, implying that meeting these outcomes constitutes the acceptance criteria. Explicit, numerical acceptance criteria are not always stated as "acceptance criteria," but rather as the successful outcome of the test.

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

• Linearity Testing: Eleven (11) linearity specimens.
• Interference Testing: Ten (10) replicate HbA1c tests per substance on prepared hemolysate specimens. Specific number of substances tested is indicated in Table 1 (40 substances).
• Total Hemoglobin Interference Testing: Not explicitly stated, but implies multiple HGB levels were tested.
• Method Comparison: A total of 526 subjects/specimens across four clinical sites.
  • Site 1: 156 samples
  • Site 2: 154 samples
  • Site 3: 102 samples
  • Site 4: 114 samples
• Precision (20-Day Imprecision - Controls): Two control solutions, each analyzed 80 times (20 days * 2 times/day * 2 duplicates) at each of four sites.
• Repeatability (Capillary Fingerstick Blood): 524 subjects from the Method Comparison study had a second fingerstick specimen collected and measured.
• Hemoglobin Derivative and Fractions, Hemoglobin Variants: Specific sample sizes for these tests are not provided, but imply testing of prepared specimens with varying concentrations.

Data Provenance:

• Country of Origin: Not explicitly stated, but "four (4) clinical sites" and "physician's offices" for point-of-care clinical performance studies indicate real-world clinical settings. The FDA submission suggests a US-centric regulatory and approval process.
• Retrospective or Prospective: The "Method Comparison" and "Precision" studies involved collecting and measuring samples, suggesting a prospective design for these clinical performance studies. The "Bench testing" for linearity and interference would be laboratory-based and controlled.

3. Number of Experts Used to Establish Ground Truth and Qualifications

The document does not mention "experts" in the context of establishing ground truth in the way one would for image-based AI studies (e.g., radiologists reviewing images).

For this device, the "ground truth" is established by a reference method or a "NGSP Certified central laboratory reference method" for HbA1c measurements, which are analytical instruments and laboratory processes, not human experts making subjective assessments.

• Method Comparison: Compared to an "NGSP Certified central laboratory reference method." NGSP (National Glycohemoglobin Standardization Program) certification implies a high standard of analytical accuracy and traceability to a primary reference method, essentially serving as a highly precise chemical/metrological "ground truth."

4. Adjudication Method for the Test Set

Not applicable. This is a quantitative diagnostic test where the "ground truth" is established by a reference laboratory method, not by human interpretation or consensus that would require adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done. This type of study is typically performed for imaging diagnostics or other subjective interpretation tasks where human readers' performance with and without AI assistance is evaluated. This device is a quantitative assay, with performance evaluated against a reference laboratory method and through precision studies, not human reader performance.

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

Yes, the performance data presented (Linearity, Interference, Total Hemoglobin Interference, Method Comparison against a reference lab, Precision, Hemoglobin Derivative/Fractions, and Hemoglobin Variants) represents the standalone performance of the Nova Allegro HbA1c Assay and Analyzer. The results are generated directly by the device and compared to established analytical standards or reference methods. There is no human-in-the-loop component in the device's measurement process that is being evaluated in these tests.

7. The Type of Ground Truth Used

• Reference Method/NGSP Certified Central Laboratory Reference Method: For Linearity and Method Comparison studies, the device's measurements were compared against a "reference method" and an "NGSP Certified central laboratory reference method." This is an analytical ground truth based on established, highly accurate laboratory techniques.
• Prepared Samples with Known Concentrations: For Interference testing, Hemoglobin Derivative and Fractions, and Hemoglobin Variants, prepared hemolysate specimens with known concentrations of interfering substances or variants were used. This constitutes a controlled, analytical ground truth where the expected outcome is known based on the sample preparation.
• Control Solutions: For 20-Day Imprecision testing, "Nova Allegro HbA1c Control Solutions" were used, which are materials with known, stable HbA1c values, serving as an analytical ground truth for precision assessment.

8. The Sample Size for the Training Set

The document does not explicitly mention a "training set" in the context of an AI/algorithm. This device is a diagnostic assay and analyzer, not an AI algorithm that undergoes machine learning training. The "development" of such a device involves chemical and engineering optimization, and analytical validation. Therefore, the concept of a "training set" as understood in machine learning is not applicable here.

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

As noted above, the concept of a training set and its ground truth is not applicable to this type of medical device (a quantitative diagnostic assay). The device's operational range and internal calibration would be established through a process of characterization and calibration using traceable standards and reference materials, which is standard for analytical instruments.

Ask a specific question about this device

The O-Pad Test System is comprised of the O-Pad Kit and the O-Pad A1c Test.

The Q-Pad Kit is an in vitro diagnostic specimen collection and storage device intended for the collection of menstrual blood samples by individuals 18 years and older for subsequent analysis by an assay validated for use with the Q-Pad menstrual pad.

The Q-Pad A1c Test is an in vitro diagnostic device for the quantitative measurement of Hemoglobin A1C using menstrual whole blood collected onto filter paper using the Q-Pad A1c Test is for the measurement of HbA I c on whole menstrual blood which will be self-collected by lay users at home and shipped to the laboratory by mail. Measurements obtained through this method can be used for monitoring the long-term control of blood sugar (glucose) in women with diabetes.

This test is not to be used to diagnose or screen for diabetes.

The Q-Pad Test System consists of the Q-Pad Kit and the Q-Pad A1c Test. The Q-Pad Kit is an in vitro diagnostic specimen collection and storage device intended for the collection of menstrual blood samples. The Q-Pad A1c Test is an in vitro diagnostic device for the quantitative measurement of Hemoglobin A1C using menstrual whole blood collected onto filter paper using the Q-Pad Kit. The Q-Pad menstrual pad (also referred to as "Q-Pad") is a modified menstrual pad which looks, feels, and is used like a normal menstrual pad. The Q-Pad has an embedded blood collection strip (Q-Strip) which can easily be removed and shipped for analysis at a laboratory. Instructions for use and results are presented in a HIPAA compliant mobile application.

The provided text describes the acceptance criteria and study that proves the Q-Pad Test System meets the acceptance criteria. It focuses on the performance of a medical device designed for measuring Hemoglobin A1c (HbA1c) from menstrual blood samples.

Here's the breakdown of the information requested, based on the provided text:

Acceptance Criteria and Device Performance

A table summarizing the acceptance criteria and the reported device performance for several key studies:

Ask a specific question about this device

Afinion™ HbA1c is an in vitro diagnostic test for quantitative determination of glycated hemoglobin (1c, HbA1c) in venous and capillary human whole blood. The measurement of % HbA1c is recommended as a marker of longterm metabolic control in persons with diabetes mellitus.

Afinion™ 2 analyzer is a compact multi-assay analyzer for point-of-care testing, designed to analyze the Afinion™ test cartridges. Afinion™ 2 system, consisting of Afinion™ test cartridges is for in vitro diagnostic use only.

Alere Afinion™ AS100 Analyzer with Alere Afinion™ Data Connectivity Converter (ADCC) is a compact multi-assay analyzer for point-of-care testing, designed to analyze the Afinion™ Test Cartridges. The ADCC is a small device for automatic transfer of data, including patient and control assay results, from the Alere Afinion™ Analyzer to a laboratory information system or another electronic journal system.

Alere Afinion™ AS100 Analyzer System, consisting of Alere Afinion™ AS100 Analyzer with Alere Afinion™ Data Connectivity Converter (ADCC), Afinion™ Test Cartridges and Afinion™ Controls is for in vitro diagnostic use only,

The Afinion™ HbA1c is an in-vitro diagnostic test for quantitative determination of glycated hemoglobin (% hemoglobin A1c, % HbA1c) in human whole blood. The measurement of % HbA1c is recommended as a marker of long term metabolic control in persons with diabetes mellitus.

The Afinion™ HbA1c assay is designed to be used with the Afinion™ AS100 Analyzer and the Afinion™ 2 analyzer which are compact multi-assay analyzers for point-of-care testing. Quality control using the Afinion™ HbA1c Control is recommended to confirm that the system is working properly and provides reliable results.

The provided text is a 510(k) premarket notification for a medical device, specifically an in-vitro diagnostic test. It describes the device, its intended use, and compares it to predicate devices to demonstrate substantial equivalence. However, it does not contain a detailed study proving the device meets specific acceptance criteria in the manner of a clinical performance study for an AI/ML-based medical device.

The document discusses analytical performance characteristics but does not present clinical performance data with a test set, ground truth established by experts, or MRMC studies. The core of this submission is about demonstrating equivalence to existing, cleared devices rather than providing novel clinical efficacy data for a new type of device or an AI algorithm.

Therefore, I cannot provide all the requested information for an AI/ML device study. I can extract the analytical performance characteristics that serve as "acceptance criteria" for this IVD and the reported device performance within the scope of this regulatory submission.

Here's an attempt to answer the questions based on the provided document, noting the limitations of the document's content for AI/ML specific criteria:

Device: Afinion™ HbA1c, Afinion™ 2, Alere Afinion™ AS100 Analyzer

The device is an in-vitro diagnostic test for quantitative determination of glycated hemoglobin (HbA1c) in human whole blood, used as a marker for long-term metabolic control in persons with diabetes mellitus. This is a chemical assay, not an AI/ML device.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria here refer to analytical performance specifications, not clinical performance for an AI/ML algorithm. The document presents a comparison of the "Candidate Device" (Modified Afinion™ HbA1c) with predicate devices, highlighting improvements or more detailed specifications for analytical specificity and interference.

Ask a specific question about this device

The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 is intended for in vitro diagnostic use for the measurement of % hemoglobin A1c (HbA1c) (DCCT/NGSP) and mmol/mol hemoglobin A1c (IFCC) in venous whole blood specimens using ion-exchange high-performance liquid chromatography (HPLC). This test is an aid in diagnosis of diabetes and identifying patients who may be at risk for developing diabetes, and for monitoring of long-term blood glucose control in individuals with diabetes mellitus.

The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 is an automated High-Performance Liguid Chromatography (HPLC) system that separates and reports stable hemoglobin A1c (sA1c) percentage in venous whole blood. The operational portion of the G8 is composed of a sampling unit, liquid pump, degasser, column, detector, microprocessors, sample loader, smart media card, operation panel, and a printer. The Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 uses ion-exchange HPLC for rapid, accurate, and precise separation of the stable form of HbA1c (sA1c) from other hemoglobin fractions. The G8 uses a non-porous cation exchange column and separates the hemoglobin components in the blood. Separation is achieved by utilizing differences in ionic interactions between the cation and exchange group on the column resin surface and the hemoglobin components in a step gradient elution. The hemoglobin fractions (designated as A1a. A1b. F. LA1c+, SA1c, A0, and, if present, H-V0, H-V2, H-V2 and H-V3) are subsequently removed from the column by performing a step-wise elution gradient using the varied salt concentrations in the Variant Elution Buffers HSi 1, 2 and 3. The peaks, H-V0, H-V1, H-V2 and H-V3 are typically presumptive HbAD, HbAS, HbAC and HbAE respectively. The software compares the retention times of hemoglobin fractions in a sample to the expected "windows of retention" and labels each fraction that correctly elutes within a defined expected window of retention. The software designates a hemoglobin fraction as POX (where X is the order of the peak as it elutes from the column) if it does not match a defined window of retention. All automated processes in the G8 are controlled by internal microprocessors, using software downloaded via a smart media card. The result report is printed and can be stored on the instrument. The data can be transmitted to a host computer through a bi-directional interface. The result report includes the sample ID, date, percentage and retention time of each fraction of hemoglobin, sA1c percentage and total A1 percentage, along with a chromatogram of the elution pattern of the hemoglobin fractions. If a sample contains a hemoglobin variant, the column elutes the fraction depending upon its charge.

The provided text describes the non-clinical performance testing of the Tosoh Automated Glycohemoglobin Analyzer HLC-723G8 (subject device) to support its substantial equivalence to a predicate device. This document focuses on the analytical performance of a diagnostic device rather than an AI/ML powered device, so some of the specific questions regarding AI/ML study design (e.g., number of experts, adjudication methods, MRMC studies) are not applicable.

Here's the information extracted from the document:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally implied by the statement "All performance testing results met their pre-determined acceptance criteria." While explicit numerical acceptance criteria for each test are not listed in a consolidated table, the discussion throughout the "Summary of Non-Clinical Performance Testing" implicitly defines them through the methodology and results. For example, for precision/repeatability, the claim of "imprecision at ≤ 2%" was a pre-established criterion. Similarly, for hemoglobin variant interference, "Non-clinically significant interference was defined as

Ask a specific question about this device

The ADVIA® Chemistry Enzymatic Hemoglobin A1c (A1c E) assay is an in vitro diagnostic assay for the quantitative determination of mmol/mol HbA1c (IFCC) and % HbA1c (DCCT/NGSP) in human anticoagulated venous whole blood and hemolysate for use on the ADVIA® Chemistry Systems. Measurement of Hemoglobin A1c is used as an aid in the diagnosis and monitoring of long-term blood glucose control in patients with diabetes mellitus, and as an aid in the identification of patients at risk for developing diabetes mellitus.

The ADVIA® Chemistry Enzymatic Hemoglobin A1c (A1c E) assay measures hemoglobin A1c in human anticoagulated whole blood and hemolysate. The assay consists of three reagents (R1, R2, and Pretreatment Solution), which are liquid and ready to use.

The assay offers both an automated and a manual application. The automated application (A1c_E) lyses the anticoagulated whole blood specimen on the system for the automated application (A1c E). Samples may also be lysed manually using the ADVIA® Chemistry A1c_E Pretreatment Solution to obtain hemolysate for the manual application (A1c_EM). The two applications yield the same results.

The provided document is a 510(k) Summary for a medical device called the ADVIA® Chemistry Enzymatic Hemoglobin A1c (A1c E) Assay. This document describes a submission seeking FDA clearance for a modification to an existing device, specifically to extend the low end of the analytical measuring range of total hemoglobin (tHb).

However, the document does not contain the detailed study results, acceptance criteria tables with performance data, information on sample sizes for test and training sets, expert qualifications, or adjudication methods that would be typically found in a comprehensive study report proving a device meets acceptance criteria.

The 510(k) Summary states that "Performance data were needed to evaluate the change" and "The verification study of linearity was done in accordance with the CLSI standard recognized by the FDA. This study along with other verification activities demonstrate equivalent performance to the predicate and effective risk mitigations. The studies met pre-determined acceptance criteria." and "Testing verified all acceptance criteria were met."

While these statements confirm that studies were conducted and met acceptance criteria, the specific details requested in your prompt (e.g., the actual table of acceptance criteria vs. performance, sample sizes, expert involvement, etc.) are not present in this summary document.

Therefore, I cannot provide the requested information from this document. To answer your prompt, I would need a more detailed study report or clinical trial summary that includes the actual performance data and study design specifics.

Ask a specific question about this device

The Aina HbA1c Monitoring System 2 consists of the Aina 2 Automated HbA1c Device, Aina HbA1c Test Kits, mobile device, and the Aina Mobile Application. It is intended to be used for quantitative measurement of % HbA1c (DCCT/NGSP) and mmol/mol HbA1c (IFCC) in human anticoagulated venous whole blood. It is intended for in-vitro diagnostic use by healthcare professionals in a laboratory environment to monitor long term glycemic control of persons previously diagnosed with diabetes. This test is not in the diagnosis of or screening for diabetes or for use on neonates.

The system consists of the Aina 2 Automated HbA1c Device for sample processing that connects to a smartphone via Bluetooth, the Aina Device for optical test strip readout, Aina HbA1c Test Kits which contain all the reagents necessary for running each HbA1c test, and the Aina Mobile Application. The Aina Device is a reflectance-based colorimetric sensor device that connects to the mobile device through the audio jack. The smartphone runs the Aina Mobile Application, which is software that allows for user interaction and illustrates the step-by-step testing process on its touchscreen. The Aina Mobile Application software is responsible for analyzing the optical signals measured by and transferred to it by the Aina Device, including applying analysis algorithms to compute the HbA1c reading. In addition, the Aina Mobile Application controls the functioning of the Aina 2 Automated HbA1c Device by sending it commands via Bluetooth. Streck A1c-Cellular control solutions can be used for regular quality control checking of the system.

Here's an analysis of the acceptance criteria and study details for the Aina HbA1c Monitoring System 2, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state "acceptance criteria" in a separate section with pass/fail thresholds. However, it does present performance data from various studies. Based on the data provided, the implied acceptance criteria would be that the device demonstrates comparable performance to established methods and exhibits suitable analytical performance characteristics.

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

• Test Set (Clinical Accuracy): n=132 (for regression analysis) fresh prospective venous whole blood samples.
• Data Provenance: Samples collected from study participants at three (3) clinical sites. The country of origin is not explicitly stated, but the submission is to the U.S. FDA by a company based in Boston, MA, suggesting the clinical sites were likely in the United States. The study design was prospective (fresh samples).

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

• The ground truth for the clinical accuracy study was established using the Tosoh G8 reference method. This is an automated laboratory analyzer, considered a high-performance liquid chromatography (HPLC) system, which is a widely accepted reference method for HbA1c measurement.
• No human "experts" were used to establish the ground truth in terms of reading images or diagnosing. The ground truth was based on the measurement from a validated reference instrument.

4. Adjudication Method for the Test Set:

• This is not applicable as the ground truth was established by an automated reference method (Tosoh G8) rather than human experts requiring adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, 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 performed. This device is an in-vitro diagnostic (IVD) measurement system, not an AI-assisted diagnostic imaging or interpretation tool that involves human readers improving with AI.

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

• Yes, the performance studies described are for the "Aina HbA1c Monitoring System 2" acting as a standalone device. While healthcare professionals operate the device, the reported performance metrics (repeatability, linearity, clinical accuracy) are of the device as a measurement system. The "Aina Mobile Application" applies analysis algorithms to compute the HbA1c reading, which is the core of its "standalone" algorithmic performance.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.):

• The ground truth for the clinical accuracy study was established using a validated reference laboratory method: the Tosoh G8 for HbA1c measurement. This is considered a highly accurate and standardized method.

8. The Sample Size for the Training Set:

• The document does not provide information on the sample size used for the training set. This is a common omission in 510(k) summaries for IVD devices, as the focus is typically on the analytical and clinical validation of the final product, rather than the deep learning model's training specifics. It does mention the "Aina Mobile Application software is responsible for analyzing the optical signals measured by and transferred to it by the Aina Device, including applying analysis algorithms to compute the HbA1c reading," implying there are algorithms that would have been developed and potentially "trained," but no training data specifics are given.

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

• Since no information about a dedicated training set is provided, the method for establishing its ground truth is also not detailed. Assuming standard IVD development, any internal optimization or calibration (which might be analogous to "training") would typically use samples characterized by a reference method similar to, or the same as, the one used for the clinical validation (e.g., Tosoh G8 or other established HbA1c reference methods).

Ask a specific question about this device

The Tina-quant Hemoglobin A1cDx Gen.3 assay is intended for use as an aid in diagnosis of diabetes and as an aid in identifying patients who may be at risk for developing diabetes. It is an in vitro diagnostics reagent system intended for quantitative determination of mmol/mol hemoglobin A1c (IFCC) and % hemoglobin A1c (DCCT/NGSP) in hemolysate or venous whole blood on the cobas c 503 clinical chemistry analyzer. HbA1c determinations are useful for monitoring of long-term blood glucose control in individuals with diabetes mellitus.

Tina-quant Hemoglobin A1cDx Gen.3 assay is an in vitro diagnostics reagent system intended for quantitative determination of mmol/mol hemoglobin A1c (IFCC) and % hemoglobin A1c (DCCT/NGSP) in hemolysate or whole blood on the cobas c 503 clinical chemistry analyzer. The assay offers separate applications that are specific to the sample types whole blood and hemolysate. The Whole Blood Application differs from the Hemolysate Application in the hemolyzing step. For the Whole Blood Application, whole blood samples are placed on the analyzer and hemolysis occurs onboard the analyzer. For the Hemolysate Application, hemolyzed samples are placed on the analyzer and hemolysis occurs manually before placing the samples onboard the analyzer. The two applications yield the same results. Hemolyzing reagent is part of the test system and is either placed on board the analyzer for the Whole Blood Application or used manually for the Hemolysate Application. Anticoagulated whole blood is hemolyzed either manually or automatically prior to determination of HbAlc by a turbidimetric inhibition immunoassay. Liberated hemoglobin (Hb) in the hemolyzed sample is converted to a derivative having a characteristic absorption spectrum and measured bichromatically. The instrument calculates the % HbAlc from the HbAlc/Hb ratio according to a user selected protocol, either IFCC or NGSP protocols.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) summary for the Tina-quant Hemoglobin A1cDx Gen.3:

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

The document doesn't explicitly state "acceptance criteria" as a single, consolidated table with pass/fail thresholds. Instead, it presents various performance studies and their results. The implicit acceptance criteria are that the device's performance metrics are acceptable for its intended use and comparable to or better than the predicate device.

Here’s a table summarizing the reported device performance for key metrics:

• Reproducibility (total CV%): Most samples/controls show CV% between 1.0% and 1.9%.
• Repeatability (CV%): Most samples/controls show CV% between 0.4% and 0.6%.
  Whole Blood Application:
• Reproducibility (total CV%): Most samples/controls show CV% between 1.2% and 1.6%.
• Repeatability (CV%): Most samples/controls show CV% between 0.4% and 0.8%. |
  | Limit of Blank (LoB) | Detection limit sensitive enough for clinical application. | Hb LoB: 0.0530 mmol/L (0.085 g/dL)
  HbA1c LoB: 0.0220 mmol/L (0.035 g/dL)
  This corresponds to 15 mmol/mol (IFCC) and 3.5% HbA1c (DCCT/NGSP) at 13.2 g/dL Hb. |
  | Limit of Detection (LoD) | Detection limit sensitive enough for clinical application. | Hb LoD: 0.119 mmol/L (0.192 g/dL)
  HbA1c LoD: 0.0437 mmol/L (0.07 g/dL)
  This corresponds to 22 mmol/mol (IFCC) and 4.2% HbA1c (DCCT/NGSP) at 13.2 g/dL Hb. |
  | Linearity/Reportable Range | Linear response across the claimed measuring range. | Hemoglobin (Hb): 4 – 40 g/dL (2.48 – 24.8 mmol/L)
  HbA1c: 0.3 – 2.6 g/dL (0.186 – 1.61 mmol/L)
  This corresponds to a measuring range of 23-196 mmol/mol HbA1c (IFCC) and 4.2-20.1% HbA1c (DCCT/NGSP).
  Empirical First Order Regression: Pearson's r for Hb = 0.9999, HbA1c = 0.9990. |
  | Endogenous Interferences | No significant interference from common endogenous substances at specified concentrations. | Demonstrated claimed maximum concentrations without interference for: Bilirubin (60 mg/dL), Ditaurobilirubin (60 mg/dL), Lipemia (400 mg/dL), Rheumatoid Factors (750 IU/mL), Total Protein (21 g/dL), Albumin (60 g/L), Immunoglobulin (IgG) (60 g/L), Glucose (1000 mg/dL), Triglycerides (1584 mg/dL). A percent deviation criteria was used (not explicitly stated but implied to be within acceptable limits). |
  | Cross-Reactivity | No significant cross-reactivity with specified hemoglobin fractions and glycated albumin. | Max Whole Blood Cross-Reactant Concentration with no Interference: HbA0 (120 g/dL), HbA1(a+b) (0.96 g/dL for Level 1, 1.6 g/dL for Level 2), Carbamylated Hb (2.0 g/dL), Acetylated Hb (2.0 g/dL), Glycated Albumin (10 g/dL), Labile HbA1c (1000 mg/dL).
  Note: Specimens with >7% HbF may yield lower than expected HbA1c values. |
  | Hemoglobin Variants | Accurate results for common hemoglobin variants (HbS, HbC, HbE, HbD, HbA2) within acceptable bias. | Relative % Bias from Reference Method at Low (around 6.5%) and High (around 9%) HbA1c:
• HbS: -2.5% (Low), -4.0% (High)
• HbC: -3.9% (Low), -6.0% (High)
• HbE: -0.1% (Low), -1.2% (High)
• HbD: -1.8% (Low), -2.6% (High)
• HbA2: -1.0% (Low), 0.4% (High)
  Note: Specimens with >7% HbF may yield lower than expected HbA1c values. |
  | Exogenous Interferences (Drugs) | No significant interference from a list of commonly used drugs at specified concentrations. | No significant interference reported for 18 listed drugs (N-Acetylcysteine, Acetylsalicylic acid, Ampicillin-Na, Ascorbic acid, Cefoxitin, Heparin, Levodopa, Methyldopa + 1.5, Metronidazole, Doxycyclin, Rifampicin, Gammagard, Cyclosporine, Phenylbutazone, Acetaminophen, Ibuprofen, Theophylline, Tolbutamide) at tested concentrations. |
  | Sample Matrix Comparison | Acceptable agreement across different anticoagulants and fill levels. | Mean Difference for K2-EDTA, K3-EDTA, Na Heparin, Li Heparin, NaF/Potassium oxalate, EDTA/Fluoride at full and half-full tubes indicate close agreement (e.g., -0.026 to 0.019). Upper and Lower 95% CIs are provided (e.g., -0.181 to 0.172). |
  | Method Comparison | Good agreement with the NGSP reference method (Tosoh Automated Glycohemoglobin Analyzer HLC-723G8). | Whole Blood Application: Mean bias vs. NGSP TOSOH = -0.046%.
  Hemolysate Application: Mean bias vs. NGSP TOSOH = 0.046%.
  Bias at concentrations: (e.g., 5% HbA1c: WB -2.4%, Hemolysate 0.6%; 12% HbA1c: WB 0.7%, Hemolysate 1.2%). |
  | Total Error (TE) | Total Error within clinical requirements, considering both bias and precision. | Hemolysate Application: TE ranging from 3.0% to 4.4% across HbA1c levels.
  Whole Blood Application: TE ranging from 3.1% to 5.2% across HbA1c levels. |

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

• Precision (Repeatability and Intermediate Precision):

  • Sample Size: 10 samples (2 controls, 8 human samples) for each application (Hemolysate and Whole Blood). Measured for 21 days.
  • Data Provenance: Human samples and controls mentioned. No specific country of origin is stated, but implied to be laboratory-based testing. Prospective study design.

• Analytical Sensitivity (LoB, LoD):

  • Sample Size:
    • LoB: One analyte-free sample. 60 measurements per lot across 3 lots.
    • LoD: Five unique human samples with low-analyte concentrations. 60 measurements per lot across 3 lots.
  • Data Provenance: Human samples mentioned. Laboratory-based testing. Prospective study design.

• Linearity/Assay Reportable Range:

  • Sample Size: Separate dilution series (at least eleven levels) prepared from human hemolysate sample pools.
  • Data Provenance: Human hemolysate samples. Laboratory-based testing. Prospective study design.

• Endogenous Interferences:

  • Sample Size: Pooled whole blood samples at two HbA1c levels, spiked with 9 different interferents. 18 spiked samples + interferent-free pools. Each tested in ten-fold.
  • Data Provenance: Pooled whole blood samples. Laboratory-based testing. Prospective study design.

• Cross-Reactivity:

  • Sample Size: Not explicitly stated as a number of unique samples, but rather a "series of experiments" with specific cross-reactants. Ten replicates of each sample were analyzed for each dilution level.
  • Data Provenance: Laboratory-based testing using prepared samples to introduce cross-reactants. Prospective study design.

• Hemoglobin Variants:

  • Sample Size: 30 HbS, 30 HbC, 30 HbE, 29 HbD, 15 HbA2, 19 Elevated HbF. Total = 153 samples.
  • Data Provenance: Not specified, but implied to be characterized patient samples containing the variants. Laboratory-based testing. Prospective.

• Exogenous Interferences (Drugs):

  • Sample Size: Hemolysate samples at two HbA1c levels, spiked with 18 common drugs at two concentrations. Each drug/concentration combination tested in ten-fold.
  • Data Provenance: Hemolysate samples and spiked drugs. Laboratory-based testing. Prospective study design.

• Sample Matrix Comparison:

  • Sample Size: At least 40 samples of each anticoagulant type (e.g., K2-EDTA, K3-EDTA, Na Heparin, Li Heparin, NaF/Potassium oxalate, EDTA/Fluoride) at full and half-filled tubes. Samples from one donor for full/half-filled comparisons.
  • Data Provenance: Human donor samples. Laboratory-based testing. Prospective study design.

• Method Comparison:

  • Sample Size: 171 whole blood samples and 173 hemolysate samples.
  • Data Provenance: Samples from a "secondary NGSP reference laboratory." This suggests these are clinical samples that have been previously characterized by a gold standard (NGSP certified) method. The nature (retrospective/prospective clinical samples) is not explicitly stated but is consistent with a clinical validation using real patient samples.

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

The document does not describe the use of human experts to establish ground truth in the way one would for image-based diagnostic AI. This device is an in vitro diagnostic (IVD) reagent system for quantifying a biomarker (HbA1c).

• Ground truth for the performance studies (e.g., precision, linearity, interferences) is established through:
  • Reference materials (e.g., controls like PreciControl HbA1c norm/path).
  • Dilution series from characterized sample pools.
  • Spiking experiments with known concentrations of interferents or cross-reactants.
• For Hemoglobin Variants and Method Comparison:
  • The "ground truth" or reference method is the NGSP Tosoh HPLC system. This system undergoes certification by the National Glycohemoglobin Standardization Program (NGSP) and is considered a highly accurate laboratory assay method, not dependent on human expert interpretation of a result. No individual human expert counts or qualifications are reported for establishing these reference values.

4. Adjudication method for the test set

Not applicable. This is an IVD device, not an AI or imaging diagnostic device that typically requires expert adjudication for ground truth establishment. The performance is assessed by comparing results to established reference methods, spiked concentrations, or statistical analysis of replicates.

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

Not applicable. The Tina-quant Hemoglobin A1cDx Gen.3 assay is an in vitro diagnostic (IVD) device for quantitative determination of HbA1c. It does not involve human readers interpreting images or data with or without AI assistance. It provides a numerical result.

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

Yes, the studies described are all standalone (algorithm only) performance evaluations. The device autonomously measures HbA1c and Hb concentrations, calculates the ratio, and reports the final HbA1c result. There is no human intervention in the result generation process once the sample is loaded onto the analyzer.

7. The type of ground truth used

The ground truth used in various parts of the study consists of:

• Reference Methods: The NGSP Tosoh HPLC system for method comparison, which is a recognized standardized method for HbA1c determination.
• Certified Reference Materials/Controls: PreciControl HbA1c norm and path with assigned values.
• Known Concentrations: For linearity, LoB, LoD studies, the "truth" is derived from preparing samples with known concentrations or by statistical analysis of repeat measurements of low/negative samples.
• Spiked Samples: For interference and cross-reactivity studies, the "truth" is the un-spiked sample value, and the effect is measured by deviation after adding a known amount of interferent.
• Characterized Patient Samples: For hemoglobin variant testing, samples from patients known to carry specific hemoglobin variants were used.

8. The sample size for the training set

This document does not describe a "training set" in the context of machine learning or AI. The Tina-quant Hemoglobin A1cDx Gen.3 is a reagent system for a well-established immunoassay technique. Its development involved chemical and assay optimization, not machine learning model training.

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

Not applicable, as there is no mention or indication of a machine learning "training set" for this IVD device. The assay's analytical principles are based on turbidimetric inhibition immunoassay (TINIA) and bichromatic photometric determination, which are traditional chemical analysis methods, not AI-driven algorithms requiring training data.

Ask a specific question about this device

The PixoTest POCT System, consisting of PixoTest POCT Analyzer and PixoTest A1c Test Kit, is used for the quantitative measurement of glycated hemoglobin (%HbA1c) in fingerstick capillary and venous whole blood samples. It is an in-vitro diagnostic system intended to monitor long term glycemic control in individuals previously diagnosed with diabetes mellitus.

The PixoTest POCT System is intended for clinical laboratory and Point-of-Care Professional use. It is not intended for use in the diagnosis of or screening for diabetes and is not intended for use on neonates.

Not Found

This document is a 510(k) clearance letter from the FDA for the PixoTest POCT System for measuring glycated hemoglobin (HbA1c). However, it does not contain the specific acceptance criteria, detailed study results, or information about the sample size, ground truth establishment, expert qualifications, or adjudication methods for the performance studies.

The letter confirms the device's clearance and its intended use: "quantitative measurement of glycated hemoglobin (%HbA1c) in fingerstick capillary and venous whole blood samples... intended to monitor long term glycemic control in individuals previously diagnosed with diabetes mellitus."

To provide the requested information, you would need access to the full 510(k) premarket notification submission (K192369) itself, which typically includes detailed performance data from validation studies. This clearance letter only states that the device is "substantially equivalent" to legally marketed predicate devices, implying that its performance meets established standards, but does not explicitly list those standards or the specific data showing compliance.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them from the provided text. The document refers to the "enclosure" for the indications for use but does not include the detailed performance data that would answer your questions.

Ask a specific question about this device

The OneDraw™ A1C Test System, which consists of the OneDraw Blood Collection Device and the OneDraw A1C Test, is intended to collect capillary blood from the upper arm of individuals 18 years of age or older onto filter (matrix) paper within the collection device by a healthcare professional. Samples are delivered to the laboratory for the quantitative measurement of HbA1c for monitoring the long-term control of blood sugar (glucose) in people with diabetes. Testing performed on samples collected with this device should not be used to diagnose or screen for diabetes. The OneDraw A1C Test System should not be used with neonates.

The OneDraw™ A1C Test System includes the OneDraw Blood Collection Device and the OneDraw A 1C Test. The OneDraw Blood Collection Device is a single-use, sterile, capillary blood specimen collection device. The OneDraw Blood Collection Device includes a transport sleeve, accessories, and instructions (OneDraw Blood Collection Device Instructions for Use (IFU)) which are needed to collect, package, and mail the sample to the designated certified clinical laboratory for HbA1c testing, using the OneDraw A1C Test.

The OneDraw Blood Collection Device incorporates lancets to make incisions in the skin and a vacuum to draw blood at the surface of the skin through channels to deposit the blood onto collection and stabilization matrices (matrix strips). The matrix strips are contained within a cartridge which is removed from the device after the draw is complete. The cartridge is then inserted into the transport sleeve which encloses and protects the sample during shipping to the clinical laboratory.

Once the transport sleeve containing the sample is received by the clinical laboratory, one of the dry blood sample matrices is removed. The matrix is then eluted in Beckman Hemolyzing Reagent (BHR) in 2 mL tubes or 2.2 mL deepwell plates using an orbital shaker. Next, the sample is diluted in BHR to its final concentration and tested using FDA-cleared Beckman Coulter AU480 Chemistry Analyzer and A 1 c reagents, including calibrators, (K 120199) per the OneDraw A 1 C Test IFU.

The document describes the OneDraw™ A1C Test System, which includes the OneDraw Blood Collection Device and the OneDraw A1C Test. The device is intended to collect capillary blood from the upper arm for quantitative measurement of HbA1c in people with diabetes. The testing is not for diagnosis or screening of diabetes and should not be used with neonates. The following information outlines the acceptance criteria and the studies performed to demonstrate the device meets these criteria.

1. Table of Acceptance Criteria & Reported Device Performance

2. Sample Size for Test Set and Data Provenance

• Precision (Assay - Repeatability): 80 data points were collected. The source of the blood samples is not explicitly mentioned as a specific country of origin, but the testing was performed in the context of an FDA submission, implying a US-based or international study adhering to US regulatory standards. It is a prospective study as samples were specifically analyzed for the purpose of the study.
• Precision (Device - Lot-to-Lot Analysis): 23 participants. The study involved multiple collection sites, suggesting prospective data collection.
• Precision (Device - Operator-to-Operator): 25 participants. The study involved multiple collection sites, suggesting prospective data collection.
• Method Comparison: 107 participants. Blood collections were conducted at two different clinical sites. This implies prospective collection for the study.
• Linearity, Interference, Limits of Detection, Product Stability, Flex Studies: The sample sizes (e.g., number of replicates, levels tested, specific blood specimens) were described within each section (e.g., "at least 20 days, two runs per day" for assay precision, "two (2) HbA1c levels... six (6) blood volumes per level... 6 matrix strips per volume" for blood volume flex study). Data provenance is prospective testing conducted for the device's validation.

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

• The document does not mention the use of "experts" in the traditional sense (e.g., radiologists, pathologists) to establish ground truth for this in vitro diagnostic device.
• Instead, the ground truth for HbA1c measurements is established by comparison to a "standard venipuncture (tested using Beckman's NGSP-certified method on the Beckman Coulter AU480 Analyzer)" (for method comparison) and other established laboratory methods and guidelines (e.g., CLSI guidelines). The accuracy of these reference methods is implicitly accepted as the ground truth.
• The qualifications of the personnel operating the reference methods are not explicitly stated but are assumed to be trained laboratory professionals.

4. Adjudication Method for the Test Set

• Adjudication methods (like 2+1, 3+1) are typically used in image-based diagnostic studies where human interpretation of medical images can vary.
• For this in vitro diagnostic device, which provides quantitative measurements, there is no "adjudication" in the sense of reconciling differing expert opinions. The performance is assessed by comparing the device's quantitative results against established reference methods or accepted criteria through statistical analysis.

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

• No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted.
• MRMC studies are relevant for evaluating the impact of an AI system on human reader performance, typically in diagnostic imaging. This device is a blood collection and testing system for HbA1c, not an AI diagnostic imaging tool or a system designed to assist human readers in interpretation.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• Yes, the performance studies described are essentially standalone performance evaluations of the OneDraw™ A1C Test System.
• The device functions as a blood collection and testing system, and its output (HbA1c levels) is directly measured and compared to reference methods. There is no "human-in-the-loop" interpretative step by a medical professional whose diagnostic accuracy is being augmented or tested. The healthcare professional collects the sample, but the analysis is done by the device system and associated laboratory methods.

7. Type of Ground Truth Used

• The ground truth used is primarily based on reference laboratory results obtained from "standard venipuncture (tested using Beckman's NGSP-certified method on the Beckman Coulter AU480 Analyzer)" for HbA1c measurement.
• Other ground truth validations include established ranges for linearity, known concentrations for interference testing, and performance against recognized CLSI guidelines for precision, stability, and limits. This is essentially measurement against accepted reference methods and established statistical criteria.

8. Sample Size for the Training Set

• The document does not describe explicit "training sets" in the context of machine learning or AI models.
• This device is an in vitro diagnostic system for quantitative measurement, not a machine learning algorithm that requires a training set in the typical sense.
• The "development" or "internal validation" data—distinct from the performance data presented for regulatory submission—is not detailed in this summary.

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

• As concluded in point 8, the document does not describe a "training set" for a machine learning model for which ground truth would need to be established. Therefore, this question is not applicable based on the provided information.

Ask a specific question about this device

The PixoTest POCT System, consisting of PixoTest POCT Analyzer and PixoTest A1c Test Kit, is used for the quantitative measurement of glycated hemoglobin (%HbA1c) in venous whole blood samples. It is an in-vitro diagnostic system intended to monitor long term glycemic control in individuals previously diagnosed with diabetes mellitus.

The PixoTest POCT System is intended for clinical laboratory and Point-of-Care Professional use. It is not intended for use in the diagnosis of or screening for diabetes and is not intended for use on neonates.

PixoTest® POCT System consists of the following devices:

1. PixoTest® POCT Analyzer
   Include:

• PixoHealth POCT A1c App
• USB Charger
• USB Type C Charge Cable
• PixoTest POCT Calibration Card

2. PixoTest® POCT A1c Test Kit
   Include:

• A1c Test Strip
• Spoit with Latex-Tablet
• Buffer Solution Tube

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary:

Device: PixoTest® POCT System - PixoTest® POCT Analyzer and PixoTest® A1c Test Kit

Intended Use: Quantitative measurement of glycated hemoglobin (%HbA1c) in venous whole blood samples for monitoring long-term glycemic control in individuals previously diagnosed with diabetes mellitus. Intended for clinical laboratory and Point-of-Care Professional use.

1. Table of Acceptance Criteria and Reported Device Performance

The provided document doesn't explicitly list specific quantitative acceptance criteria values prior to the study for each performance metric, but it does state that the study results "demonstrate that the accuracy specifications... meet the acceptance criteria." The study focused on accuracy compared to a laboratory reference method.

Note: For a full regulatory submission, specific acceptance criteria for accuracy (e.g., bias, precision measured by CV%, correlation coefficient R^2, Bland-Altman agreement with reference method, allowable total error) would typically be defined and presented numerically. This summary only provides a high-level conclusion.

2. Sample Size and Data Provenance

• Test Set Sample Size: 120 subjects
• Data Provenance: The location of data collection is not explicitly stated as a country but it was collected at "3 point-of-care sites." It's reasonable to infer these are clinical sites that conducted the study. The study appears to be prospective as it involved collecting samples from subjects for the purpose of the study.

3. Number of Experts and Qualifications for Ground Truth

• This device is an in-vitro diagnostic (IVD) for measuring HbA1c, not a diagnostic imaging AI. Therefore, the concept of "experts" establishing ground truth in the traditional sense (e.g., radiologists for images) does not directly apply.
• Ground Truth Establishment: The ground truth for the test set was established by comparison with a laboratory reference instrument. In this case, it was the "TOSOH G7 Analyzer lab instrument." This is a standard approach for IVD device validation, where a known, highly accurate, and often predicate or gold-standard laboratory method serves as the reference. Qualified laboratory personnel, following validated procedures, operate such reference instruments.

4. Adjudication Method for the Test Set

• As this is an IVD device measuring an analyte (HbA1c) against a reference instrument, an "adjudication method" in the sense of multiple human readers resolving disagreements (e.g., 2+1, 3+1) is not applicable. The comparison is quantitative between the new device and the reference laboratory instrument.

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

• No, an MRMC comparative effectiveness study was not done. This type of study (comparing human readers with AI vs. without AI assistance) is relevant for AI-powered diagnostic imaging devices where human interpretation is part of the clinical workflow.
• The PixoTest POCT system is an automated in-vitro diagnostic device that provides a quantitative measurement. It does not involve human "reading" or a human-in-the-loop AI assistance model in the way an imaging AI would.

6. Standalone Performance Study

• Yes, a standalone performance study was done. The core of the clinical evaluation was to compare the performance of the PixoTest POCT Analyzer and PixoTest A1c Test Kit (the device itself) against a well-established laboratory reference method (TOSOH G7 Analyzer).
• The study "comparing venous whole blood A1c values on the PixoTest POCT Analyzer and PixoTest A1c Test Kit with values on TOSOH G7 Analyzer lab instrument" directly assesses the standalone analytical performance of the device.

7. Type of Ground Truth Used

• Reference Laboratory Instrument / Expert Consensus on Reference Method: The ground truth was established by values obtained from a TOSOH G7 Analyzer lab instrument. This represents a highly accurate and accepted reference method for HbA1c measurement in a clinical laboratory setting, effectively serving as the "gold standard" or expert consensus (via established, validated methodology). It's not pathology (histology), or direct outcomes data, but rather a robust, analytical measurement from a validated reference device.

8. Sample Size for the Training Set

• The document does not provide information regarding the sample size of a training set. This is typical for regulatory summaries of IVD devices where the underlying technology (reflectance photometry, immunoassay) relies on established principles of analytical chemistry and does not inherently involve complex data-driven "training" in the machine learning sense that would require a large, labeled training dataset of the same type as the test set. While there might be internal algorithm development and calibration data, it is not described as a "training set" in the context of a typical AI/ML submission, nor is its size reported here.

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

• Given that a "training set" (in the AI/ML context) is not explicitly discussed for this device, the method for establishing its ground truth is not provided.
• For IVD devices like this, calibration and validation during development typically involve using reference materials, calibrators, and control materials with known concentrations, traceable to international standards if applicable. These values are established through rigorous analytical methods by reference laboratories or manufacturers.

Ask a specific question about this device