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 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 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

The Quo-Test Alc System is intended for the in vitro quantitative determination of glycated hemoglobin (%HbA1c) levels in venous whole blood samples (using K2EDTA and lithium heparin anticoagulants). Measurement of percent glycated hemoglobin (%HbA1c) is effective for monitoring long-term glycemic control in individuals previously diagnosed with diabetes mellitus.

The Quo-Test A1c System is not intended for screening or diagnosis of diabetes or neonatal use. The device is intended for professional use in a clinical laboratory setting.

The Quo-Test Analyzer and A1c Test Kit (Quo-Test A1c System) are intended for the in-vitro quantitative determination of glycated hemoglobin in whole blood samples obtained from venous samples. The system contains a fluorimeter and two photometers to enable both fluorescent and photometric measurements to be made. The Quo-Test A1C Assay is calibrated by the manufacturer using European Reference Laboratory (ERL) calibrators. There are no user-serviceable parts in the analyzer. It has ports to support a printer and barcode scanner plus a USB port. It is powered by an AC/DC adapter plugged into a 100-240V AC outlet. The Quo-Test A1c Test Cartridge contains all the reagents, in a plastic cuvette, required to perform an HbA1c test on the Quo-Test Analyzer. The reagents consist of a lysing agent, buffer and a boronate fluorophore conjugate. A low level of sodium azide preservative is used to enhance the shelf life of the test cartridge. Each test cartridge is for single-use. The test cartridges are supplied in individual foil pouches and should be stored at 2 - 8°C.

This document describes the premarket notification (510(k)) for the Quo-Test A1c System, a device intended for the in vitro quantitative determination of glycated hemoglobin (%HbA1c) levels in venous whole blood samples for monitoring long-term glycemic control in individuals previously diagnosed with diabetes mellitus.

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

1. A Table of Acceptance Criteria and the Reported Device Performance

The acceptance criteria are generally implied by the performance characteristics demonstrated to be comparable (substantially equivalent) to the predicate device and compliant with relevant CLSI guidelines. While explicit "acceptance criteria" are not presented in a single table with pass/fail marks, the results provided in the analytical performance sections serve as the evidence that the criteria were met.

Here's a table summarizing the implicit acceptance criteria (based on common industry standards and the predicate device's performance, and supported by the study methodologies) and the reported performance:

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

• Precision Study (20-day precision):
  • Sample Size: Three venous blood samples (High, Medium, Low A1C) and two control solutions. Each was tested in duplicate at two separate occasions per day over twenty days.
  • Data Provenance: Internal evaluation by the manufacturer. Not specified if retrospective or prospective, but the design suggests a prospective, controlled laboratory study. Country of origin not explicitly stated for samples but manufacturer is Germany.
• Linearity Study:
  • Sample Size: 11 patient samples (mixed in incremental amounts to generate a series of 11 samples over a broad HbA1c concentration range). All samples were analyzed fivefold.
  • Data Provenance: Study carried out by Isala Ziekenhuis, Department of Clinical Chemistry, Zwolle, The Netherlands in August 2018. This was a prospective study using patient samples.
• Stability Study (Reconstituted Controls):
  • Sample Size: Three EKF A1c Control Kits, each with a Normal Control. 4 bottles of each level (Normal/Abnormal) from each lot were pooled after reconstitution.
  • Data Provenance: Internal testing (manufacturer or OEM). Prospective.
• Stability Study (Cartridges - Shelf Life):
  • Sample Size: Three blood samples (covering the relevant clinical range 5-11% A1C) and the normal and abnormal kit controls. Each of five samples measured n=3 times on each of three Quo-Test analysers at five interval time points over a 15-month period.
  • Data Provenance: Internal testing (manufacturer). Prospective, real-time study.
• Analytical Specificity (Interference):
  • Sample Size: Not explicitly stated for the number of blood samples or replicates, but the study design evaluated the effects of various interfering substances.
  • Data Provenance: Not specified, but likely internal laboratory testing.
• Analytical Specificity (Hemoglobin Variants):
  • Sample Size: Venous whole blood samples collected in K2 EDTA tubes spread across the analytical measurement range (4.6-11.6 % HbA1c) for each variant.
  • Data Provenance: Not specified, but likely internal laboratory testing.
• Method Comparison Studies:
  • Sample Size: Total of 424 subjects across three clinical sites. 423 K2EDTA venous samples and 149 heparin venous samples. 115 normal subjects (27.1%) and 308 diabetes subjects. 209 male and 215 female subjects, ranging from 21 to 89 years of age.
  • Data Provenance: Prospective study conducted at three clinical sites. IRB approval was obtained. Samples were sent to an NGSP-certified reference laboratory (Diabetes Diagnostic Laboratory, Columbia. MO). Country of origin for clinical sites/subjects is not specified, but the reference lab is in the US (Missouri).

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

The concept of "experts" as human readers/interpreters establishing ground truth, as typically seen in AI/imaging studies, does not directly apply here. This is an in vitro diagnostic (IVD) device measuring a biochemical analyte.

• Ground Truth for Analytical Performance: Established by quantitative laboratory methods and reference standards.
  • Precision/Linearity/Stability/Analytical Specificity: Ground truth is the quantitative value determined by the instrument/method under evaluation, compared against expected ranges or reference methods / defined mixtures. No human "experts" are adjudicating individual results in the sense of image interpretation.
  • Traceability: The ground truth for calibration and methods is tied to IFCC reference methods and NGSP certification, which involve a network of reference laboratories and expert committees, not individual human readers.
• Ground Truth for Method Comparison: Established by a NGSP-certified reference laboratory using the Tosoh 8 analyzer. The NGSP certification process ensures that laboratories meet stringent criteria for accuracy and precision in HbA1c measurement. This is the gold standard for HbA1c testing.

4. Adjudication Method for the Test Set

Not applicable in the conventional sense of image interpretation or clinical diagnosis by multiple readers. The "ground truth" for the quantitative HbA1c measurements (analyte levels) is established by the NGSP-certified reference method, which is a highly standardized and validated laboratory process, not a subjective human interpretation requiring adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and What Was the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

Not applicable. This is an in vitro diagnostic (IVD) device designed for direct quantitative measurement of HbA1c in blood, not an AI system assisting human readers in interpreting complex medical images or data. There are no "human readers" involved in interpreting the results of the Quo-Test A1c System in a manner that would necessitate an MRMC study.

6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, the studies presented are standalone performance evaluations of the Quo-Test A1c System itself. The device is designed to provide a quantitative HbA1c result directly from a blood sample. Its output is a numerical value (%HbA1c), which is then used by laboratory professionals or clinicians for patient management. There is no "human-in-the-loop" interaction for interpreting the device's output in the way an AI imaging algorithm might require a radiologist's review. The device performs its measurement and calculation independently.

7. The Type of Ground Truth Used

• Analytical Performance (Precision, Linearity, Stability, Analytical Specificity): The ground truth is effectively the expected value or the reference method/instrument's value for the specific analyte concentration in control materials, spiked samples, or serially diluted/mixed patient samples. For traceabilty, the ground truth is established by the IFCC reference method and NGSP-certified standards.
• Method Comparison: The ground truth for patient samples was established by an NGSP-certified reference laboratory using the Tosoh 8 analyzer, which serves as the gold standard/reference method for HbA1c measurement.

8. The Sample Size for the Training Set

Not applicable in the context of an AI/machine learning model where a "training set" is used to develop the algorithm. The Quo-Test A1c system is a biochemical assay, not an AI algorithm trained on data. Its "training" or calibration is based on manufacturer's procedures using reference calibrators traceable to international standards (NGSP/IFCC), as described in the "Calibration" section.

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

As explained above, there's no "training set" in the AI sense. For the calibration of the device and its cartridges:

• The Quo-Test A1C System is certified by the National Glycohemoglobin Standardization Program (NGSP) and International Federation of Clinical Chemistry and Laboratory Medicine (IFCC).
• The Quo-Test Analyzer and A1C Test Cartridges have been calibrated using samples provided by the European Reference Laboratory (ERL) via the NGSP network.
• Results obtained using the Quo-Test A1C System are traceable to the IFCC reference method.

This means the ground truth for the device's calibration (which would be analogous to "training" in an ML context) is established by highly standardized and internationally recognized reference methods and laboratories.

Ask a specific question about this device

The skyla Hi Hemoglobin A1c System, consisting of the skyla Hi Analyzer and skyla Hi Hemoglobin A1c Reagent Kit is an in-vitro diagnostic test for quantitative measurement of the percent concentration (%) of glycated hemoglobin (HbA Ic %) in venous and finger-stick capillary whole blood.

The measurement of % HbA1c is used to monitor long-term glycemic control in persons previously diagnosed with diabetes mellitus.

This system is intended for clinical laboratory and point-of-care use.

This test is not for screening or diagnosis of diabetes.

The skyla Hi Analyzer is a portable and compact system, and was designed with skyla Hi Hemoglobin A1c Reagent Kit for on-site quantitative measurement of the percent concentration (%) of glycated hemoglobin (HbA1c %) in human blood.

The provided document describes the FDA 510(k) clearance for the Skyla Hi Hemoglobin A1c System. This is an in-vitro diagnostic device that measures glycated hemoglobin (HbA1c %) in blood for monitoring long-term glycemic control in persons previously diagnosed with diabetes mellitus.

Therefore, the acceptance criteria and study detailed below relate to the analytical and clinical performance of this diagnostic device, not an AI/ML-based device. The concepts of "experts establish ground truth," "adjudication," "multi-reader multi-case," and "standalone algorithm performance" are not directly applicable in the context of an in-vitro diagnostic device clearance, as these are typically used for imaging or AI/ML-driven diagnostic aids.

However, I can extract and present the performance data and study design details relevant to this type of device based on the provided text.

Acceptance Criteria and Reported Device Performance

The acceptance criteria for an in-vitro diagnostic device typically involve precision (reproducibility and repeatability) and method comparison (accuracy against a reference method). The reported device performance is demonstrated through studies detailed in the "Discussion of Non-Clinical Tests Performed" and "Discussion of Clinical Tests Performed" sections.

Table of Acceptance Criteria (Implied) and Reported Device Performance:

• Patient 1 (Mean 5.04%): 0.095 SD (1.9% CV)
• Patient 2 (Mean 5.56%): 0.110 SD (2.0% CV)
• Patient 3 (Mean 6.54%): 0.135 SD (2.1% CV)
• Patient 4 (Mean 7.96%): 0.198 SD (2.5% CV)
• Patient 5 (Mean 12.10%): 0.292 SD (2.4% CV)
• Control 1 (Mean 5.20%): 0.130 SD (2.5% CV)
• Control 2 (Mean 9.69%): 0.260 SD (2.7% CV)
• Calibrator 1 (Mean 13.58%): 0.138 SD (1.0% CV) |
  | Linearity | Demonstrated linearity across the claimed measuring range. | Evaluated (mentioned as "Evaluations included linearity"), but specific results/range are not provided in the summary. |
  | Method Comparison (Accuracy/Correlation) | Demonstrated strong correlation and agreement with a legally marketed comparator device or a recognized reference method. (Typically assessed via regression analysis, bias analysis, or Bland-Altman plots with acceptable limits). | Against Bio-Rad VARIANT II Hemoglobin testing system:
• Venous Whole Blood: y = 0.9945x + 0.0779
• Finger-stick Capillary Blood: y = 0.9993x + 0.0589
  (Conclusion: "comparable to comparative device whole blood testing results.") |
  | Interference | Demonstrated that common interfering substances do not significantly impact results. | Evaluated (mentioned as "Evaluations included interference"), but specific results/substances are not provided in the summary. |
  | Sample Volume | Demonstrated consistent performance across acceptable sample volume ranges. | Evaluated (mentioned as "Evaluations included sample volume"), but specific results/ranges are not provided in the summary. |
  | Hematocrit | Demonstrated consistent performance across a range of hematocrit levels. | Evaluated (mentioned as "Evaluations included hematocrit"), but specific results/ranges are not provided in the summary. |

Study Details:

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

   • Precision Test Set:

     • Total samples: 8 different samples (5 patient samples, 2 control samples, 1 calibrator).
     • Total runs/measurements: For each sample, 80 measurements were performed at each of the 3 sites, totaling 240 measurements per sample type. This is broken down into within-run, between-run, and between-day components.
     • Provenance: Not explicitly stated, but typically these are controlled laboratory studies using patient samples, control materials, and calibrators. The presence of "Site 1, Site 2, Site 3" indicates a multi-site study. It is likely prospective collection for study purposes. Country of origin for data is not specified.

   • Method Comparison Test Set (POC User Performance Study):

     • Total samples: A total of 243 samples were analyzed.
     • Provenance: The study was performed in "POC sites by intended operators," suggesting a prospective clinical study environment. The samples included both venous whole blood and finger-stick capillary samples. Country of origin for data is not specified.

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

   • This is not applicable in the context of an in-vitro diagnostic device like an HbA1c assay. The "ground truth" for HbA1c measurements is established by a reference method, not by expert consensus or interpretations. In this case, the Bio-Rad VARIANT II Hemoglobin testing system served as the comparator/reference method for the method comparison study.

3. Adjudication method for the test set:

   • Not applicable. Adjudication methods (like 2+1, 3+1) are used in studies involving human interpretation of complex data (e.g., medical images) where there can be inter-reader variability. For an HbA1c assay, the output is a quantitative numerical value, and the comparison is direct to a reference method result.

4. 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. This is not an AI/ML-assisted diagnostic device, and there are no "human readers" interpreting images or similar data. The study is evaluating the analytical and clinical performance of a laboratory/point-of-care instrument.

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

   • Not applicable. While the device (Skyla Hi Hemoglobin A1c System) operates independently to produce a numerical result, the concept of "standalone algorithm performance" typically applies to AI/ML systems generating an output that would then be presented to a human for review/decision. Here, the device is the analytical system. Its performance is demonstrated directly by the precision and method comparison studies.

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

   • The "ground truth" for the method comparison study was the results obtained from a legally marketed predicate device/reference method, specifically the Bio-Rad VARIANT II Hemoglobin testing system. The performance is assessed by correlating the results of the new device with this established method. For precision studies, there isn't a "ground truth" in the same sense; rather, the "true value" is approximated by the mean of many measurements, and variability around that mean is assessed.

7. The sample size for the training set:

   • This refers to the development of the device itself (e.g., calibration, reagent formulation, software algorithms). The document does not specify a "training set" size in the way it would for an AI/ML model. The device's internal algorithms and calibration are developed through internal R&D processes and validated with various studies (e.g., linearity, calibrator assignments), which are generally proprietary and not detailed in a 510(k) summary beyond their successful completion.

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

   • Not explicitly mentioned in the context of "training data" for an AI/ML model. For an in-vitro diagnostic device, the "training" (development and calibration) would involve using reference materials, calibrators traceable to international standards (if applicable for HbA1c, e.g., IFCC), and characterized patient samples, with their values established by highly accurate methods or external reference laboratories.

Ask a specific question about this device

ACE Hemoglobin A lc (HbA lc) Reagent is intended for the quantitative determination of percent hemoglobin A lc in venous whole blood collected in K2-EDTA tubes using the ACE Axcel® Clinical Chemistry Systems. This test is intended for use in clinical laboratories and physician office laboratories to monitor long term blood glucose control in individuals with diabetes mellitus. For in vitro diagnostic use only.

The ACE Hemoglobin A1c (HbA1c) Reagent assay requires a pretreatment step of denaturation of the whole blood samples, which is performed off-line. The red blood cells in the sample are lysed by the Hemoglobin Denaturant and the hemoglobin chains are hydrolyzed. For determination of HbA1c, a latex agglutination inhibition assay is used. In the absence of HbA1c in the sample, the synthetic polymer containing the immunoreactive portion of HbA 1c Agglutinator Reagent will agglutinate with the antibody-coated microparticles in the HbA1c Antibody Reagent. The presence of HbA1c in the blood sample competes for the antibody binding sites and inhibits agglutination. The increase in absorbance, monochromatically at 692 mm, is inversely proportional to the HbA1c present in the sample. For the determination of total hemoglobin, all hemoglobin derivatives in the sample are converted to alkaline hematin. The reaction produces a green colored solution. which is measured bichromatically at 573 nm/692 nm. The intensity of color produced is directly proportional to the total hemoglobin concentration in the sample. The concentrations of both HbA 1 c and total hemoglobin are measured, the ratio is calculated, and the result reported as percent HbA1c.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for the ACE Hemoglobin A1c (HbA1c) Reagent device are implicitly established by demonstrating comparable performance to the predicate device, the DCA 2000+ System for Hemoglobin A1c (K951361), across a range of analytical performance characteristics. While explicit numerical acceptance criteria are not always stated, the study aims to show that the new device's performance aligns with acceptable standards for HbA1c measurement in clinical diagnostics.

Here's a table summarizing the reported device performance:

Study Details:

2. Sample Size and Data Provenance for Test Set:

• Linearity: 11 samples were used for both HbA1c and Total Hemoglobin linearity studies, run in 4 replicates each, for both the ACE Alera and ACE Axcel systems.
• Precision (In-house): 4 samples (A, B, C, D) were tested, but the number of runs/replicates to calculate SD and %CV is not explicitly stated in the table. Typically, precision studies involve multiple replicates over several days.
• Precision (Physician Office Labs - POLs): 4 samples were tested across 3 POLs for each instrument (ACE Alera and ACE Axcel). Similar to in-house, the specific number of runs/replicates per POL for SD and %CV calculation is not detailed.
• Comparative Analysis (In-house): 101 samples for ACE Alera and 102 samples for ACE Axcel were compared against the predicate device (DCA 2000+).
• Comparative Analysis (POLs): 50 samples per POL for a total of 150 samples for ACE Alera, and 52 samples for one POL and 50 samples for the other two POLs (total 152 samples) for ACE Axcel were compared against the predicate device (DCA 2000+).
• Analytical Specificity/Cross-Reactivity: The number of samples for these studies is not explicitly stated, but typically involves spiking known concentrations of interferents into samples and measuring the effect.
• Data Provenance: The studies were conducted in-house by Alfa Wassermann Diagnostic Technologies, LLC, and in external Physician Office Laboratories (POLs). Given the nature of performance validation for a diagnostic device, these studies are prospective, as samples are analyzed using the new device and compared against a reference method or predicate. The "country of origin of the data" is implicitly the United States, where the manufacturer and the POLs are located.

3. Number of Experts and their Qualifications for Ground Truth:

The document does not mention the use of "experts" in the traditional sense (e.g., radiologists, pathologists) to establish ground truth for the test set. For an in vitro diagnostic device measuring a quantitative analyte like HbA1c, the ground truth is typically established by:

• Reference Methods: Highly accurate and precise analytical methods, often traceable to international standards (e.g., NGSP, IFCC), which are considered the "gold standard" for measuring the analyte.
• Predicate Devices: Comparison to a legally marketed device that has already established its safety and effectiveness.

In this case, the ground truth for the comparative studies was derived from the predicate device (DCA 2000+ System for Hemoglobin A1c), which is itself NGSP Certified and traceable to IFCC reference materials.

4. Adjudication Method for the Test Set:

Not applicable. Adjudication methods (like 2+1, 3+1) are typically used in clinical studies involving interpretation of medical images or complex diagnostic assessments by human readers, where discrepancies between readers need to be resolved. For a quantitative in vitro diagnostic device, the ground truth is established analytically through reference methods or predicate comparison, not through expert consensus requiring adjudication.

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

Not applicable. MRMC studies are generally performed for image-based diagnostic aids or other devices where human interpretation plays a significant role in the diagnostic outcome. This document describes the analytical performance validation of an in vitro diagnostic reagent, which is a quantitative measurement, not an interpretative task for human readers in the context of an MRMC study. Therefore, no effect size of human readers improving with AI vs. without AI assistance is relevant or reported.

6. Standalone (Algorithm Only) Performance Study:

Yes, this entire submission focuses on the standalone performance of the ACE Hemoglobin A1c (HbA1c) Reagent when used with the ACE Alera® and ACE Axcel® Clinical Chemistry Systems. The studies presented (linearity, precision, comparative analysis, specificity, cross-reactivity) all evaluate the direct analytical performance of the device itself, without human intervention for interpretation beyond standard laboratory procedures for operating the instrument and processing samples.

7. Type of Ground Truth Used:

The ground truth used for the comparative analysis studies was the predicate device, the DCA 2000+ System for Hemoglobin A1c. The document explicitly states that the DCA Hemoglobin A1c test method is National Glycohemoglobin Standardization Program (NGSP) Certified and is traceable to International Federation of Clinical Chemistry (IFCC) reference materials and test methods. This indicates that the predicate device serves as a highly standardized and accepted reference for HbA1c measurement.

8. Sample Size for the Training Set:

The document does not explicitly mention a "training set" in the context of machine learning or AI models. This device is a diagnostic reagent kit for a clinical chemistry system, not a software algorithm that requires a separate training phase with a distinct dataset. The performance data presented are for the validation of the finalized device.

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

As there is no "training set" in the context of this device being a reagent for a clinical chemistry system, this question is not applicable. The device's design and formulation would have been developed through internal R&D, likely using internal validation and optimization experiments, but these are not typically referred to as a "training set" with established ground truth in the same way as for AI/ML models. The ground truth for the validation of the device's performance (as described above) was established by comparison to the NGSP/IFCC-traceable predicate device.

Ask a specific question about this device