Search Results

Amydi-med Disposable Non-invasive EEG Sensor is applied directly to an adults/pediatrics patient's skin to record physiological signals (e.g., the electroencephalogram, EEG) in the healthcare facility / hospital.

Amydi-med Disposable Non-invasive EEG Sensor is a low impedance, single patient use, disposable, non-sterile provided sensor that is designed for application to the sites including forehead, temporal, above eyebrow, and mastoid process. It is designed to provide ease of use and accurate electrode placement.

The main components of this sensor are the flexible PCB with electrodes, polyethylene base pad with medical grade pressure sensitive adhesive on its double sides, nylon plastic tine disks, polyurethane foam disks, aqueous gel ( , and cable connector. Each sensor has three (3) to six (6) electrodes on the flexible PCB for different application sites.

The provided text describes the 510(k) summary for the Amydi-med Disposable Non-invasive EEG Sensor (K240668), focusing on its substantial equivalence to a predicate device (K220448). The document highlights performance data for safety and electrical characteristics.

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

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify the sample size used for the test sets in the biocompatibility, electrical, adhesive, or shelf-life testing. It also does not provide information on the country of origin of the data or whether the studies were retrospective or prospective.

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

This section is not applicable as the device is a medical sensor (hardware) undergoing performance and safety testing, not an AI/software device requiring expert consensus for ground truth establishment.

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

This section is not applicable for the type of device and testing described. Adjudication methods are typically relevant for studies involving human interpretation or assessments where discrepancies need resolution.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is relevant for AI-powered diagnostic or interpretive tools, not for a disposable non-invasive EEG sensor.

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

A standalone performance evaluation (algorithm only) was not done. This refers to AI algorithm performance without human intervention, which is not applicable to a physical medical device like an EEG sensor.

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

The concept of "ground truth" as typically applied to AI/diagnostic studies is not directly applicable here. For hardware testing:

• Biocompatibility: Ground truth is established by the specified standards (e.g., cell viability for cytotoxicity, skin reaction for irritation) and determined by laboratory tests.
• Electrical Performance: Ground truth is defined by the parameters and limits specified in the ANSI/AAMI EC12 standard.
• Adhesive Performance: Ground truth is defined by the parameters and limits specified in the IEC 60601-2-2 standard.
• Shelf Life: Ground truth is determined by the device's ability to meet its performance specifications over time following accelerated aging and real-time stability testing.

8. The sample size for the training set

The document does not mention a training set. This is a physical medical device, not an AI/machine learning model that typically undergoes training.

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

This question is not applicable as there is no mention of a training set for this device.

Ask a specific question about this device

The Amylase2 assay is used for the quantitation of amylase in human serum, plasma, or urine on the ARCHITECT c System. The Amylase2 assay is to be used primarily as an aid in the diagnosis and treatment of pancreation of the pancreas).

The Amylase2 assay is an automated clinical chemistry assay. The Amylase2 assay is a two-part reaction. Ethylidene-4-NP-G7 (EPS) is hydrolyzed by a-amylase to form 4,6ethylidene-α-(1,4)-D-glucopyranosyl-Gx and 4-nitrophenyl-α-(1,4)-glucopyranosyl-G(7-x). The 4-nitrophenyl-a-(1,4)-glucopyranosyl-G(7-x) is then hydrolyzed into glucose monomers and the assay chromophore (4-nitrophenol) by a-glucosidase. The resulting change in absorbance at 404 nm is proportional to the a-amylase concentration in the sample. Methodology: Enzymatic/Colorimetric. The device is a reagent kit.

Here's a breakdown of the acceptance criteria and the study details for the Amylase2 device, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA 510(k) summary does not explicitly list "acceptance criteria" in a singular table, but rather presents the results of various performance studies. I've extracted the performance metrics and their corresponding observed results to form this table, interpreting the reported successful values as meeting implicit acceptance criteria for substantial equivalence.

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

The document provides details on various studies, each with its own sample size and design:

• Precision (Serum/Plasma & Urine - Within-Laboratory):
  • Sample Size: For each of the controls (2 levels) and panels (3 for serum/plasma, 5 for urine), N=80 data points were collected. This involved testing samples in duplicate, twice per day for 20 days.
  • Provenance: Human serum/plasma and human urine panels were used. No specific country of origin is mentioned, but the context implies an in-vitro diagnostic study conducted under CLSI guidelines, likely in a controlled laboratory setting. It is a prospective study as samples were tested according to a pre-defined protocol.
• System Reproducibility (Serum/Plasma & Urine):
  • Sample Size: For each of the controls (5 for serum/plasma, 4 for urine), N=90 data points were collected. This involved testing samples in a minimum of 3 replicates at 2 separate times per day on 5 different days across 3 instruments and 3 technicians.
  • Provenance: The study used controls, implying commercially prepared materials or pooled biological samples. It is a prospective study.
• Accuracy:
  • Sample Size: Not explicitly stated but implies a set of calibrator materials and potentially patient samples based on "material standardized to the Certified Reference Material IRMM/IFCC-456."
  • Provenance: Relies on certified reference materials and likely patient samples.
• Lower Limits of Measurement (LoB, LoD, LoQ):
  • Sample Size: n ≥ 60 replicates of zero-analyte and low-analyte level samples for each determination (LoB, LoD, LoQ).
  • Provenance: Control materials or spiked biological samples designed to have specific low analyte levels. Prospective.
• Linearity:
  • Sample Size: Not explicitly stated, but typically involves a series of diluted/spiked samples to cover the analytical range.
  • Provenance: Spiked or diluted biological samples. Prospective.
• Potentially Interfering Substances (Serum/Plasma & Urine):
  • Sample Size: Not explicitly stated, but each substance was tested at 2 levels of the analyte (approximately 50 U/L and 200 U/L for serum/plasma; 450 U/L and 1400 U/L for urine). This implies numerous replicates for each interferent and analyte level.
  • Provenance: Biological samples (serum/plasma/urine) spiked with various endogenous and exogenous substances. Prospective.
• Method Comparison:
  • Sample Size: 124 serum samples and 103 urine samples.
  • Provenance: Human serum and urine samples. The description doesn't explicitly state if prospective or retrospective, but typically such studies involve prospectively collected samples from a diverse patient population. No country of origin specified.
• Tube Type:
  • Sample Size: Samples collected from a minimum of 40 donors.
  • Provenance: Human blood samples collected into different tube types. Prospective.
• Dilution Verification:
  • Sample Size: 5 human serum samples and 5 urine samples, each tested in replicates of 5 after automated and manual dilution.
  • Provenance: Human serum and urine samples spiked with α-amylase from porcine pancreas. Prospective.

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

This information is not provided in the document. For an in-vitro diagnostic device, "ground truth" often refers to the true concentration of the analyte, which is usually established by highly precise reference methods, certified reference materials, or by comparison with a well-established predicate device, rather than expert consensus on images or clinical diagnoses. The document indicates standardization against IRMM/IFCC-456, which is a reference material for amylase, and comparison to a predicate device (AMY, K981653). These serve as the "ground truth" or reference for the device's performance.

4. Adjudication Method for the Test Set

This section is not applicable as this is an in-vitro diagnostic (IVD) device for quantitative measurement of amylase. Adjudication methods like "2+1" or "3+1" are typically used in clinical studies involving interpretation of medical images or subjective evaluations, where multiple experts independently assess data and discrepancies are resolved. For an IVD, the "ground truth" is measured quantitatively against a reference standard or predicate.

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

This information is not provided and is not applicable to this device. An Amylase2 assay is an automated clinical chemistry assay, not an AI-powered diagnostic imaging device that requires human "readers" or involves AI assistance in interpretation. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to this product.

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

The Amylase2 assay is an automated clinical chemistry assay, meaning its performance is inherently "standalone" in the sense that it provides a quantitative result without direct human intervention in the measurement process itself, beyond sample loading and general instrument operation. The studies described (precision, accuracy, linearity, interference, method comparison) are all evaluating the algorithm/reagent system's performance independently.

7. The Type of Ground Truth Used

The ground truth for the Amylase2 device's performance studies relies on:

• Reference Materials: For accuracy, the device was compared against "material standardized to the Certified Reference Material IRMM/IFCC-456."
• Predicate Device: For method comparison, the Amylase2 assay was compared to the predicate device, Amylase assay (List Number 7D58), which serves as the established reference standard in this context.
• Spiked Samples: For linearity, lower limits of measurement, interference, and dilution verification, samples were often "spiked" with known concentrations of α-amylase or interfering substances to create samples with a known "true" value.
• Commercial Controls: For precision and reproducibility studies, commercially available controls with known target ranges were used.

8. The Sample Size for the Training Set

The document describes studies for validation and verification purposes (test sets). For an IVD like Amylase2, the "training set" would refer to the data used by the manufacturer during the assay development phase to optimize reagents, calibrate the instrument response, and refine the measurement algorithms. This specific information about the development/training data size is not provided in the 510(k) summary, as the summary focuses on the performance of the final device.

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

Similar to point 8, the specific details on how ground truth was established for any internal "training set" used during development are not provided. Typically, for such IVDs, this would involve a rigorous process of using purified analytes, gravimetric/volumetric standards, certified reference materials, and comparison to established reference methods to assign "true" values to a large panel of samples during the assay's development and optimization.

Ask a specific question about this device

The AMYPOWER ALLTRACK power wheelchair's intended use is to provide mobility to persons limited to a seating position, that have the capability of operating a powered wheelchair. The AMYPOWER ALL TRACK power wheelchair empowers physically challenged individuals by providing a means of mobility.

The AMYPOWER ALLTRACK power wheelchair is a battery powered, motor driven device. It is a rigid or "non-folding" type power wheelchair design that offers functionality to be used as a mid wheel drive or a rear wheel drive base. The design offers a modular approach and can be configured in multiple versions to suit different client needs. The ALLTRACK series power wheelchair is designed to offer the ultimate in safety, stability, performance and comfort for the user. It features an active six wheel suspension as well as a seat suspension, and front and rear anti-tip casters which allow for surface contact of all six wheels at all times and prevents pitching on slopped terrain. The ALLTRACK power wheelchair utilizes components typically found on most wheelchairs, including but not limited to a rigid steel frame, a seat, armrests, front riggings, two main drive wheels, two electric drive motors, front & rear castors, two batteries, a charger, a positioning belt and a controller.

The provided text describes the submission for a power wheelchair, which is a medical device. Based on the information provided, this is not a device that relies on algorithms, AI, or specific performance metrics that would require an "acceptance criteria" table in the traditional sense of AI/ML-driven devices.

Instead, the acceptance criteria for this type of device are met through adherence to established industry standards and regulations for safety and functionality. The study that proves the device meets these criteria is the non-clinical testing described in the document.

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

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

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

• Sample Size: Not explicitly stated as a number of individual units. The testing involved "the AMYPOWER ALLTRACK series power wheelchair," implying potentially one or a representative sample of units undergoing the specified non-clinical tests.
• Data Provenance: The testing was conducted in accordance with international and North American standards (ISO & ANSI/RESNA). The manufacturer, Amylior Inc., is based in Quebec, Canada, suggesting the testing likely occurred to satisfy Canadian and US regulatory requirements for market clearance. The data is based on non-clinical testing, which is a prospective assessment of the device's physical performance characteristics against defined standards.

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

• This information is not applicable as the "ground truth" for this device is established by objective engineering and safety standards (ISO, ANSI/RESNA), not by expert consensus on clinical data interpretation. The evaluation is against measurable physical properties and functional requirements.

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

• Not applicable. Adjudication methods like "2+1" typically apply to cases where multiple human readers are interpreting complex data (e.g., medical images) and their disagreements need to be resolved by a third party. For a power wheelchair's non-clinical safety and performance testing, the results are objectively measured against established criteria; there is no subjective interpretation requiring adjudication.

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. This device is a mechanical power wheelchair, not an AI/ML-driven diagnostic or assistive device that would involve human readers or comparative effectiveness studies with AI assistance.

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

• Not applicable. This device is a mechanical power wheelchair and does not contain artificial intelligence algorithms. Its performance is inherent in its design and construction, and validated through physical testing against standards.

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

• The ground truth is based on established international and national engineering, safety, and performance standards (ISO EMC Standard 7176-14 and ANSI/RESNA WC vol. 1 & vol. 2, Section 21:1998 amendments). Compliance with these objective standards serves as the "ground truth" for device acceptability.

8. The sample size for the training set

• Not applicable. This device is a mechanical power wheelchair; it does not involve machine learning or a "training set" in the context of AI/ML models.

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

• Not applicable. As stated above, there is no training set for this type of device.

Ask a specific question about this device

The Amylase EPS Reagent is used for the quantitative determination of a-Amylase (1,4-α-D-glucan glucanohydrolase EC3.2.1.1) in human serum, plasma or urine on Beckman Coulter SYNCHRON CX ®/ LX ® Systems. a-Amylase is most frequently measured in the diagnosis of acute pancreatitis, when serum levels may be grossly elevated.

Amylase EPS Reagent

The provided text is a 510(k) premarket notification letter from the FDA to Thermo Fisher Scientific regarding the "Amylase EPS Reagent." This document confirms the substantial equivalence of the device to a legally marketed predicate device.

However, the document does not contain any information about acceptance criteria or a study proving the device meets those criteria. It is a regulatory approval letter, not a scientific study report.

Therefore, I cannot provide the requested information. The document focuses on regulatory approval and mentions the intended use of the reagent (quantitative determination of α-Amylase in human serum, plasma, or urine for diagnosis of acute pancreatitis), but it does not detail any performance metrics, study designs, sample sizes, or ground truth methodologies.

Ask a specific question about this device

For the quantitative determination of Amylase in human serum and urine. Amylase measurements are used primarily for the diagnostics and treatment of pancreatitis.

Not Found

This document is a 510(k) clearance letter from the FDA for a medical device called "Amylase Liquid Reagent" by TECO Diagnostics. It is a regulatory approval document and does not contain information about acceptance criteria or a study proving the device meets those criteria, nor any of the other requested details about a study.

Therefore, I cannot fulfill your request for the specific information regarding acceptance criteria and study details based on the provided text. The letter primarily states that the device is substantially equivalent to a legally marketed predicate device.

Ask a specific question about this device

This product is to be used in a diagnostic laboratory setting, by qualified laboratory technologists, for the quantitative determination of amylase in human serum. It is intended for in vitro diagnostic use only. The determination of amylase in serum is most commonly performed for the diagnosis and treatment of diseases of the pancreas.

Not Found

The document provided is a premarket notification (510(k)) letter from the FDA to Pointe Scientific, Inc. regarding their Amylase EPS-G7 (Liquid) Reagent Set. This type of document declares "substantial equivalence" to a predicate device, which allows the product to be marketed, but does not typically include detailed studies proving performance against acceptance criteria in the way a clinical trial for a novel AI device would.

Therefore, many of the specific details requested in the prompt, such as sample sizes for test and training sets, expert qualifications for ground truth, adjudication methods, or MRMC studies, are not applicable to this 510(k) submission for an in vitro diagnostic reagent kit.

However, I can extract the relevant information about the device and its intended use, and explain why other sections are not present:

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

This document (a 510(k) clearance letter) does not typically contain a table of detailed performance characteristics and acceptance criteria in the way a clinical study report for an AI device might. For in-vitro diagnostic products like this, the demonstration of "substantial equivalence" to a legally marketed predicate device is the primary regulatory hurdle. This means the device is shown to perform as well as, or comparably to, an existing device on the market.

While the letter doesn't explicitly state "acceptance criteria," the intended performance of the device is for the "quantitative determination of amylase in human serum" for the "diagnosis and treatment of diseases of the pancreas." Substantial equivalence implies that its performance (e.g., sensitivity, specificity, accuracy, precision, linearity, interfering substances) is comparable to, and not worse than, the predicate device.

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

This information is not provided in the 510(k) clearance letter. For in vitro diagnostic reagents, performance studies are conducted, but their detailed results (including sample sizes, study design, and data provenance) are typically submitted to the FDA in a separate dossier and summarized or referenced in the 510(k) submission, rather than being fully reproduced in the publicly available clearance letter.

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

This information is not applicable/provided in this context. For a reagent test determining a quantitative analyte (amylase), the "ground truth" is typically established by reference methods, standard assays, or certified reference materials, not by expert consensus in the way a diagnostic imaging interpretation would be.

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

This information is not applicable/provided. Adjudication methods are relevant for subjective interpretations (like radiology reads) where multiple experts might disagree. For quantitative assays, the "ground truth" is determined by objective laboratory measurements, not expert consensus requiring adjudication.

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

This is not applicable. This device is a reagent set for laboratory testing, not an AI-assisted diagnostic tool that aids human readers. Therefore, an MRMC study comparing human performance with and without AI assistance is irrelevant.

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

This is not applicable. This is a laboratory reagent kit, not an algorithm. Its performance is inherent to the chemical reaction and analytical equipment, not an AI algorithm.

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

For an amylase reagent test, the "ground truth" would typically be established through:

• Reference methods: Highly accurate and validated analytical methods.
• Standardized calibrators: Materials with known, certified concentrations of amylase.
• Interlaboratory comparisons: Performance against other established and trusted assays.

The specific type of ground truth used is not detailed in this 510(k) clearance letter.

8. The sample size for the training set

This information is not applicable/provided. This device is a chemical reagent, not a machine learning model, so there is no "training set" in the AI sense. Performance validation involves testing the reagent's characteristics (e.g., linearity, precision, accuracy, reproducibility) across a range of samples and conditions, but this is distinct from training an AI model.

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

This information is not applicable/provided for the reasons stated in point 8.

Ask a specific question about this device

Ask a specific question about this device

The intended use of the device is to provide posterior tilting for positioning and pressure relief in a powered wheelchair.

AmySystems PTS50CG Weight Shift Power Tilt System

The provided text is a 510(k) clearance letter from the FDA for a medical device called "AmySystems PTS50CG-50° Power Tilt System." This document grants market clearance based on substantial equivalence to a predicate device.

However, the letter does not contain any information regarding acceptance criteria, device performance studies, sample sizes, ground truth establishment, expert qualifications, or any of the other specific details requested in your prompt.

The 510(k) clearance process primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than requiring extensive de novo clinical studies with detailed performance metrics and statistical analyses as might be found in a PMA (Premarket Approval) application.

Therefore, I cannot populate the table or answer the specific questions based on the information provided in the input text. The document confirms the device's clearance for marketing and its intended use but does not delve into the technical study details you are asking for.

Ask a specific question about this device

The intended use of the device is to provide posterior tilting for positioning and pressure relief in a powered wheelchair.

Not Found

I am sorry, but the provided text is a letter from the FDA regarding a 510(k) premarket notification for a power tilt system for wheelchairs. It confirms the device's substantial equivalence to a predicate device and its classification.

The document does not contain any information about:

• Acceptance criteria or reported device performance for a study.
• Sample sizes, data provenance, number of experts, adjudication methods, MRMC studies, standalone studies, or ground truth details for any testing.
• Training set information.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets the acceptance criteria based on the provided input.

Ask a specific question about this device

The Amylase assay is used for the quantitation of amylase in serum, plasma, or urine on the AEROSET System. Amylase measurements are used primarily for the diagnosis and treatment of pancreatitis (inflammation of the pancreas).

Amylase is an in vitro diagnostic assay for the quantitative determination of amylase in serum, plasma, or urine. The Amylase assay is a clinical chemistry assay. The amylase in the sample hydrolyzes the 2-chloro-4-nitrophenyl-alpha-D-maltotrioside (CNPG3) to release 2-chloro-4-nitrophenol (CPNP) and form 2-chloro-4-nitrophenyl-alpha-D-maltoside (CNPG2), maltotriose (G3), and glucose (G). The rate of formation of the 2-chloro-4-nitrophenol is measured as an increase in the absorbance at 405 nm and is directly proportional to the activity of amylase present in the sample.

The Abbott Laboratories "Amylase" assay (Amy) is used for the quantitative determination of amylase in serum, plasma, or urine on the AEROSET System, primarily for the diagnosis and treatment of pancreatitis.

Here's a breakdown of its acceptance criteria and the study that proves its performance:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document describes "acceptable correlation" as the acceptance criterion for the comparison studies. The specific numerical thresholds for correlation coefficient, slope, and intercept were not explicitly defined as acceptance criteria but are presented as the results that demonstrated "acceptable correlation" compared to the predicate device. Similarly, for precision, linearity, and sensitivity, specific acceptance criteria in terms of numerical ranges were not provided in the summary, but the reported performance values are presented as meeting the implied standard of "substantially equivalent" to the predicate.

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

The document does not explicitly state the sample size used for the test set for the comparative performance studies or the precision studies.

The data provenance is not specified in terms of country of origin or whether it was retrospective or prospective. It states that "comparative performance studies were conducted" and "precision studies were conducted," implying these were experimental studies.

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

Not applicable. This device is an in vitro diagnostic assay that quantifies amylase levels. The "ground truth" for the test set in this context would be the results obtained from the predicate device (Boehringer Mannheim α-Amylase/EPS assay on the Hitachi 717 Analyzer) against which the new device was compared. This is a comparison between two quantitative assays, not an expert-based diagnostic ground truth.

4. Adjudication Method for the Test Set

Not applicable, as the evaluation involves comparing quantitative results from two analytical devices, not adjudication by human experts.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and If So, 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 assay, not an imaging device requiring human reader interpretation or an AI-assisted diagnostic tool.

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

Yes, this is effectively a standalone performance evaluation. The "Amy" assay on the AEROSET System is an automated analytical system that quantitatively measures amylase. Its performance characteristics (correlation, precision, linearity, sensitivity) were evaluated directly, without human interpretation as part of the primary diagnostic output.

7. The Type of Ground Truth Used

The "ground truth" for the comparative effectiveness study (which establishes substantial equivalence) was the measurements obtained from the legally marketed predicate device: the Boehringer Mannheim α-Amylase/EPS assay (K882225) on the Hitachi 717 Analyzer.

8. The Sample Size for the Training Set

Not applicable. This is a classic in vitro diagnostic device, not a machine learning or AI-based algorithm that requires a "training set" in the computational sense. The device's calibration and method development would involve internal studies, but these are distinct from a "training set" for AI.

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

Not applicable, for the same reason as point 8.

Ask a specific question about this device