Search Results

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 Atellica® CH Amylase_2 (AMY_2) assay is for in vitro diagnostic use in the quantitative determination of amylase activity in human serum, plasma (lithium heparin), and urine using the Atellica® CH Analyzer. Such measurements are used primarily in the diagnosis and monitoring of acute pancreatitis (inflammation of the pancreas).

The Atellica® CH Amylase_2 (AMY_2) assay is based on the procedure of Jensen and Wydeveld. The Atellica CH AMY 2 assay uses ethylidene blocked p-nitrophenylmaltoheptaoside as substrate. The indicator enzyme a-glucosidase, used to release pnitrophenol (PNP), is also employed in the assay. The terminal glucose of the substrate is chemically blocked, preventing cleavage by the indicator enzymes. The released pnitrophenol is measured at 410/694 nm.

The Siemens Healthcare Diagnostics Inc. Atellica® CH Amylase_2 (AMY_2) assay is an in vitro diagnostic device for the quantitative determination of amylase activity in human serum, plasma (lithium heparin), and urine. These measurements are used primarily in the diagnosis and monitoring of acute pancreatitis.

Here's an analysis of its acceptance criteria and the supporting study data:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" with pass/fail thresholds for each performance characteristic. Instead, it presents performance results which are implicitly considered acceptable for substantial equivalence to the predicate device. Based on the provided data, the table below summarizes the reported device performance for key analytical characteristics.

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

Detection Limit (LoB/LoD):

• Sample Size: LoB: 4 samples with no analyte tested (N=20 repetitions) for 3 days, using 3 reagent lots. LoD: 4 low analyte samples tested (N=20 repetitions) for 3 days, using 3 reagent lots. This totals to 240 replicates for LoB and 240 replicates for LoD.
• Data Provenance: Not explicitly stated, but implies laboratory-prepared control samples or de-identified human samples with near-zero or low analyte levels. Likely internal data from Siemens Healthcare Diagnostics Inc. R&D organization.

Limit of Quantitation (LoQ):

• Sample Size: 4 low samples processed for 3 reagent lots for 3 days, on one instrument. This totals 120 measurements per lot.
• Data Provenance: Not explicitly stated, but likely internal data from Siemens Healthcare Diagnostics Inc. R&D organization, using prepared low-concentration samples.

Linearity:

• Sample Size: 9 samples spanning the assay measuring interval for serum specimens and 9 samples for urine specimens. Each sample was measured in 5 replicates.
• Data Provenance: Samples were prepared by mixing high and low concentration samples, and by spiking native serum or urine pools with amylase. Low pools were created by diluting with CH diluent. Origin of native serum/urine pools not specified, but likely internal or commercially sourced.

Precision:

• Sample Size: n=2 replicates, two times per day for at least 20 days, for a total of 80 replicates per sample. This was done for controls, serum, plasma, and urine pools.
• Data Provenance: Laboratory controls, serum, plasma, and urine pools were used. Likely internal data from Siemens Healthcare Diagnostics Inc. R&D organization.

Interferences:

• Sample Size: Not explicitly given for the number of distinct samples, but tests were conducted using "fresh sample pools" (low and high measurand levels in serum and urine) spiked with interferents.
• Data Provenance: Fresh sample pools implies human serum and urine, likely obtained or prepared internally.

Method Comparison:

• Sample Size: Serum: N=118 samples. Urine: N=114 samples.
• Data Provenance: Remnant de-identified samples were tested. The study included native and spiked samples. The studies were conducted internally by Siemens Healthcare Diagnostics Inc. R&D personnel and externally by a contracted laboratory. The country of origin for these remnant samples is not specified, but typically would be from US clinical labs if the filing is for the US market.

Matrix Equivalency:

• Sample Size: N=66 matched serum and lithium heparin plasma sets.
• Data Provenance: Matched serum and lithium heparin plasma sets. Some samples were spiked with amylase. Likely internal data, origin of native samples unspecified.

Expected Values (Reference Intervals):

• Sample Size: Not explicitly stated for the verification study, but reference intervals were "verified". CLSI EP28-A3 suggests a minimum of 20 samples for verification.
• Data Provenance: Verified on the Atellica® CH Analyzer. Reference "Data on file at Siemens Healthcare Diagnostics".

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

This device is an in vitro diagnostic assay that measures amylase activity, not an imaging or a subjective diagnostic device requiring expert interpretation of results for ground truth. Therefore, no external experts were used to establish a "ground truth" for the test set in the way one might for diagnostic imaging or pathology. The ground truth (or 'true value') for quantitative assays is established through meticulous analytical methods, calibration using traceable reference materials (IRMM/IFCC-456 for this device), and comparison to a legally marketed predicate device.

The personnel conducting the method comparison study were "laboratory technicians with training similar to personnel who would conduct the tests in a hospital laboratory setting."

4. Adjudication method for the test set

Not applicable. As a quantitative assay, the results are numerical and objectively measured, not subject to individual interpretation and thus do not require an adjudication method among experts.

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 is an in vitro diagnostic assay performed by an automated analyzer, not an AI-assisted diagnostic device that would involve human readers (e.g., radiologists, pathologists) interpreting images or clinical data.

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

Yes, the performance data presented (Detection Limit, LoQ, Linearity, Precision, Interferences, Method Comparison, Matrix Equivalency) are all standalone performance data of the Atellica® CH Amylase_2 analyzer and its reagents, without human-in-the-loop performance influencing the assay results directly. The device automatically performs the quantitative determination of amylase activity.

7. The type of ground truth used

The "ground truth" for this quantitative assay is established via:

• Calibration Traceability: Traceable to IRMM/IFCC-456 Pancreatic Alpha-Amylase Reference Material and commutable to the IFCC Alpha-Amylase Primary Reference Procedure.
• Comparison to Predicate: Performance is demonstrated as substantially equivalent to a legally marketed predicate device (Roche Cobas Amylase Reagent), implying that the predicate's established accuracy serves as a benchmark.
• Analytical Standards and Controls: Use of internal and external quality control materials with known target values.
• Spiked Samples: For linearity, method comparison, and matrix equivalency, samples were spiked with known concentrations of amylase to cover the measuring range.

8. The sample size for the training set

Not applicable. This is a traditional in vitro diagnostic assay based on enzymatic colorimetric reactions, not an AI/ML-based algorithm that would require a "training set" in the context of machine learning. The "training" for such a device involves chemical formulation, instrument design, and analytical validation.

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

Not applicable, as there is no "training set" in the context of AI/ML for this device.

Ask a specific question about this device

alpha-AMYLASE DIRECT: Reagent for the measurement of alpha-amylase concentration in human serum, plasma or urine. The obtained values are useful as an aid in the diagnosis of acute and chronic pancreatitis. This reagent institus of in the BioSystems BA analyzers. Only for in vitro use in the clinical laboratory.

alpha-AMYLASE EPS: Reagent for the measurement of alpha-amylase concentration in human serum, plasma or urine. The obtained values are useful as an aid in the diagnosis of acute and chronic pancreatitis. This reagent is for use in the BioSystems BA analyzers. Only for in vitro use in the clinical laboratory.

alpha-AMYLASE PANCREATIC: Reagent for the measurement of pancreatic c-amylase concentration in human serum, plasma or urine. The obtained values are useful as an aid in the diagnosis of acute and chronin pancreatitis. This reagentis for use in the BioSystems BA analyzers. Only for in vitro use in the clinical laboratory.

BILIRUBIN DIRECT: Reagent for the measurement of direct bilirubin concentration in human serum or plasma. Measurements of the levels of bilirubin are used in the diagnosis and treatment of liver, hematological and metabolic disorders, including hepatitis and gall bladder block. This reagent is for use in the BioSystems Blockers. Only for in vitro use in the clinical laboratory.

BILIRUBIN TOTAL: Reagent for the measurement of total bilirubin concentration in human serum or plasma. Measurements of the levels of bilirubin are used in the diagnosis and treatment of liver, herrytological and metabolic disorders, including hepatitis and gall bladder block. This reagent is for nuse in the BioSystems Blockers. Only for in vitro use in the clinical laboratory.

Not Found

This 510(k) summary provides information about the substantial equivalence of several Biosystems S.A. reagents (alpha-AMYLASE DIRECT, alpha-AMYLASE EPS, alpha-AMYLASE PANCREATIC, BILIRUBIN DIRECT, BILIRUBIN TOTAL) to legally marketed predicate devices. It states that the devices are intended for in vitro diagnostic use in the clinical laboratory for measuring specific analyte concentrations in human serum, plasma, or urine, which are useful as aids in the diagnosis and treatment of certain medical conditions. However, the document does not contain any data, studies, or information regarding acceptance criteria or device performance statistics. It is a regulatory clearance letter, not a performance study report.

Therefore, I cannot extract the requested information regarding acceptance criteria, reported device performance, sample sizes, data provenance, expert qualifications, adjudication methods, MRMC studies, standalone performance, or ground truth establishment.

To answer your request, I would need a different document, such as a summary of safety and effectiveness (SSE) or a clinical study report that details the validation and performance characteristics of these reagent systems.

Ask a specific question about this device

The S TEST Reagent Cartridge Lactate Dehydrogenase (LD) is intended for the quantitative determination of LD in serum and plasma using the HITACHI Clinical Analyzer E40. The S TEST Reagent Cartridge Lactate Dehydrogenase (LD) is intended for use in clinical laboratories or physician office laboratories. For in vitro diagnostic use only. Measurements of LD are used in the diagnosis and treatment of liver and cardiac diseases.

The S TEST Reagent Cartridge Amylase (AMY) is intended for the quantitative determination of AMY in serum and plasma using the HITACHI Clinical Analyzer E40. The S TEST Reagent Cartridge Amylase (AMY) is intended for use in clinical laboratories or physician office laboratories. For in vitro diagnostic use only. Measurements of AMY are mainly used in the diagnosis and treatment of pancreatic diseases.

The Hitachi Clinical Analyzer is an automatic, bench-top, wet chemistry system intended for use in clinical laboratories or physician office laboratories. The instrument consists of a desktop analyzer unit, an operations screen that prompts the user for operation input and displays data, a printer, and a unit cover. The analyzer unit includes a single probe, an incubation rotor, carousels for sample cups and reagent cartridges, and a multi-wavelength photometer. The single-use reagent cartridges may be placed in any configuration on the carousel, allowing the user to develop any test panel where the reagent cartridges are available.

The S TEST reagent cartridges are made of plastic and include two small reservoirs capable of holding two separate reagents (R1 and R2), separated by a reaction cell/photometric cuvette. The cartridges also include a dot code label that contains all chemistry parameters, calibration factors, and other production-related information, e.g., expiration dating. The dimensions of the reagent cartridges are: 13.5 mm (W) × 28 mm (D) × 20.2 mm (H).

System operation: After the sample cup is placed into the carousel, the analyzer pipettes the sample, pipettes the reagent, and mixes (stirs) the sample and reagent together. After the sample and reagent react in the incubator bath, the analyzer measures the absorbance of the sample, and based on the absorbance of the reactions, it calculates the concentration of analyte in the sample. The test system can measure analytes in serum or plasma and results are available in approximately 15 minutes per test. This submission is for Reagent Cartridge ALP.

Chemistry reactions: (LD) Lactate dehydrogenase in samples catalyzes the reaction of converting lactic acid to pyruvic acid. During this reaction, NAD is converted into NADH with an increase in absorbance at 340 nm. The LD activity can be determined by measuring the production rate of the resulting NADH.

(AMY) Amylase in blood samples reacts with the substrate alfa-2-chloro-4-nitropheny]galactopyranosylmaltoside (Gal-G2-CNP), and the substrate is cleaved into 4galactopyranosylmaltose (Gal-G2) and 2-chloro-4-nitrophenol (CNP). Amylase activity is determined by measuring the production rate of CNP (yellow).

Here's a breakdown of the acceptance criteria and the study details for the Hitachi Chemical Diagnostics S TEST Reagent Cartridges for Lactate Dehydrogenase (LD) and Amylase (AMY):

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for this device are implied by the reported performance and comparison to predicate devices, rather than explicitly stated as discrete pass/fail thresholds in a formal table from the provided text. However, we can infer the expected performance based on the studies conducted.

S TEST Reagent Cartridge Lactate Dehydrogenase (LD)

S TEST Reagent Cartridge Amylase (AMY)

2. Sample Size and Data Provenance for the Test Set

• 10-day In-house Precision (LD, AMY):
  • Sample Size: Three levels of samples were tested. Each level was tested in two runs, twice a day, for 20 days. This implies a significant number of replicates (e.g., 3 levels * 2 runs/day * 2 times/day * 20 days = 240 measurements per analyte, though typically results are grouped for analysis). The text explicitly states 30 replicates per sample per site for the external precision studies.
  • Data Provenance: Not explicitly stated, but "in-house" implies from the manufacturer's laboratory. "Clinical specimens" for method comparison suggest human samples.
• Method Comparison (LD):
  • Sample Size (Test Set): 106 clinical specimens.
  • Data Provenance: Not explicitly stated, but "clinical specimens" implies human samples, presumably retrospective or prospectively collected for the study. No country of origin is mentioned.
• Method Comparison (AMY):
  • Sample Size (Test Set): 105 clinical specimens.
  • Data Provenance: Not explicitly stated, but "clinical specimens" implies human samples, presumably retrospective or prospectively collected for the study. No country of origin is mentioned.
• Matrices Comparisons (LD):
  • Sample Size (Test Set): 39 matched serum/plasma samples.
  • Data Provenance: Not explicitly stated; "clinical samples" implies human.
• Matrices Comparisons (AMY):
  • Sample Size (Test Set): Approximately 43 matched serum/plasma samples.
  • Data Provenance: Not explicitly stated; "clinical samples" implies human.
• External Site Precision (LD, AMY):
  • Sample Size (Test Set): Three blinded serum samples (low, middle, high concentrations for each analyte). Each sample was assayed six times per day for five days, yielding 30 replicates per sample per site. This was done at three external sites.
  • Data Provenance: "three external POL-type sites" (Physician Office Laboratory-type sites). Implies human serum samples.
• External Site Method Comparison (LD):
  • Sample Size (Test Set): Approximately 70-80 serum specimens (specifically, 87 for Site 1, 78 for Site 2, 86 for Site 3).
  • Data Provenance: "three external POL-type sites" using "serum specimens with LD values". Implies human serum samples.
• External Site Method Comparison (AMY):
  • Sample Size (Test Set): Approximately 70-80 serum specimens (specifically, 76 for Site 1, 69 for Site 2, 71 for Site 3).
  • Data Provenance: "three external POL-type sites" using "serum specimens with AMY values". Implies human serum samples.

3. Number of Experts and Qualifications for Ground Truth

This device is a quantitative diagnostic test for measuring enzyme levels (LD and AMY) in blood samples, typically analyzed by laboratory equipment. The "ground truth" for such devices is established by validated reference methods or predicate devices, not typically by expert review of images or clinical assessments in the same way an AI diagnostic imaging device would use radiologists.

• For Method Comparison studies, the "ground truth" or reference method was "a standard laboratory system" (in-house studies) or "a comparative method as the reference method" (external POL studies). These are assumed to be legally marketed and validated laboratory instruments. No human experts are described as establishing "ground truth" in this context.

4. Adjudication Method for the Test Set

Not applicable for this type of quantitative diagnostic device. Adjudication methods like 2+1 or 3+1 are used in interpretation tasks (e.g., radiology for AI devices) where human judgment is pooled to establish a consensus ground truth. Here, the "ground truth" is determined by the output of a reference laboratory instrument or method.

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

No. An MRMC study is not relevant for this type of device, which is an automated quantitative assay. This device does not involve human readers interpreting images or clinical data with or without AI assistance. The studies performed compare the device's quantitative output to established reference methods or predicate devices.

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

Yes, the studies described are standalone performance assessments of the device (Hitachi E40 Clinical Analyzer with S TEST Reagent Cartridges). The performance characteristics (analytical sensitivity, linearity, precision, interference, method comparison, matrices comparison) evaluate the instrument and reagent system's ability to accurately and precisely measure the target analytes entirely autonomously. There is no human interaction in producing the raw quantitative result from the device.

7. Type of Ground Truth Used

The ground truth used for performance evaluation was:

• Validated Reference Methods / Predicate Devices: For linearity, analytical sensitivity, and method comparison studies, the Hitachi E40 system results were compared against established reference methods or legally marketed predicate devices (Roche cobas c systems LDHI2 and AMYL2). The specific details of these reference methods are not provided but are generally understood to be highly accurate and precise laboratory assays.
• Known Concentrations: For precision studies, samples with "low, middle, and high concentrations" were used, implying that the approximate target concentrations were known or characterized.
• Spiked Samples: For interference studies, substances were added to samples at known concentrations to assess their impact on the assay (e.g., "50 mg/dL bilirubin").

8. Sample Size for the Training Set

This information is not provided in the summary. For a medical device like this (a reagent cartridge and analyzer), there isn't typically a "training set" in the sense of machine learning. The device's operational parameters, algorithms (for calculation), and calibration are established during its design and development, likely using extensive internal testing and optimization. Manufacturers establish operating procedures and calibration protocols based on R&D, not a discrete "training set" in the AI sense.

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

Given that this is a traditional in-vitro diagnostic device and not a machine learning algorithm, the concept of a "training set" and establishing "ground truth" for it, as typically understood in AI/ML, does not directly apply. The "ground truth" for developing the device itself would stem from fundamental principles of analytical chemistry, enzyme kinetics, and rigorous laboratory validation processes using primary calibrators and reference materials. The device's calibration curves and internal calculations are based on well-established scientific principles and extensive validation during its development phase.

Ask a specific question about this device

ELITech Clinical Systems AMYLASE SL is intended for the quantitative in vitro determination of amylase in human serum and plasma on ELITech Clinical Systems Selectra analyzers. It is not intended for use in Point of Care settings. Measurements of amylase are used primarily for the diagnosis and treatment of pancreatitis (inflammation of the pancreas).

ELITech Clinical Systems ELICAL 2 is a multi-parametric calibrator for in vitro diagnostic use in the calibration of quantitative ELITech Clinical Systems methods on ELITech Clinical Systems Selectra analyzers.

ELITech Clinical Systems ELITROL I and ELITROL II are multi-parametric control sera for in vitro diagnostic use in accuracy control of quantitative ELITech Clinical Systems methods on ELITech Clinical Systems Selectra analyzers.

ELITech Clinical Systems AMYLASE SL is available as kit only. It consists of one reagent R whose the composition is: MES buffer (pH 6.15), sodium chloride, calcium chloride, potassium thiocyanate, CNP-G3 (2-chloro-4-nitrophenyl-α-maltotrioside), sodium azide.

ELITech Clinical Systems ELICAL2 is a lyophilized calibrator based on human serum containing constituents to ensure optimal calibration. ELICAL 2 is prepared exclusively from the blood of donors tested individually and found to be negative for HbsAg and to the antibodies to HCV and HIV according to FDA-approved methods.

ELITech Clinical Systems ELITROL I and ELITROL II are two level quality control products consisting of a lyophilized human serum containing constituents at desired levels. ELITROL I and ELITROL II are prepared exclusively from the blood of donors tested individually and found to be negative for HbsAg and to antibodies to HCV and HIV according to FDA-approved methods.

1. Acceptance Criteria and Reported Device Performance

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

• Precision Test Set: 80 measurements for each of 3 levels (total of 240 measurements) were taken.
• Linearity Test Set: The number of samples for the linearity study is not specified, but the study was conducted according to CLSI protocol EP6-A.
• Detection Limit (LoD & LoQ) Test Set: 15 measurements for each of 4 samples with low concentration of analyte (total 60 measurements)
• Interference Test Set: The number of unique samples is not specified, but various substances were tested at specified concentrations.
• Method Comparison Test Set: 100 serum patient samples.
• Plasma Comparison Test Set: 48 paired plasma (in lithium heparin) samples.
• Data Provenance: The document does not explicitly state the country of origin. The studies appear to be prospective analytical performance studies conducted by the device manufacturer.

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

• For in vitro diagnostic devices like the ELITech Clinical Systems AMYLASE SL, "ground truth" for analytical performance studies is typically established by comparing results to well-defined reference methods, predicate devices, or by preparing samples with known concentrations. The document does not mention the involvement of "experts" in the context of establishing ground truth in the way it might apply to image-based diagnostic AI. Instead, it relies on established laboratory procedures and reference standards.
• The "IFCC method" is mentioned as the traceability standard for the calibrator, which implies a highly standardized and internationally recognized reference for amylase measurement. The reference range also cites a publication by G. Schumann et al. on IFCC Primary Reference Procedures.

4. Adjudication Method for the Test Set

• Adjudication methods (like 2+1, 3+1) are typically used for qualitative or semi-quantitative diagnostic tests where human interpretation is involved. For this quantitative in vitro diagnostic device, such an adjudication method is not relevant or mentioned. The performance is assessed by comparing quantitative results to reference methods, predicate devices, or known values, which is inherently objective and does not require adjudication in the human interpretative sense.

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

• No, an MRMC comparative effectiveness study was not done. This type of study is specifically designed for image-based diagnostics or other tests heavily reliant on human interpretation, often to quantify the improvement in human reader performance with AI assistance. This device is a quantitative clinical chemistry assay, not an AI-assisted diagnostic.

6. Standalone Performance Study

• Yes, the performance characteristics (precision, linearity, detection limits, interference, method comparison) described are all standalone (algorithm only) performance studies of the device (AMYLASE SL reagent on the Selectra ProM analyzer). The device itself is an automated assay, and its performance is evaluated independent of human interpretation or intervention beyond standard laboratory procedures.

7. Type of Ground Truth Used

• Precision: Internal controls and samples with known or characterized concentrations.
• Linearity: Samples prepared with varying, known concentrations.
• Traceability: Traceable to the IFCC method.
• Stability: Measured over time using internal controls and reference materials.
• Detection Limit (LoD) & Quantification Limit (LoQ): Calculated based on repeated measurements of low-concentration samples.
• Interference: Samples spiked with known interferents at specified concentrations.
• Method Comparison: Comparison against a legally marketed predicate device (Roche Diagnostics AMYL2 on cobas c111 analyzer) using patient samples. This serves as a comparative ground truth.
• Plasma Comparison: Comparison between serum and lithium heparin plasma samples from the same patients.

8. Sample Size for the Training Set

• This device is a reagent for a clinical chemistry assay, not an AI/ML algorithm that requires a "training set" in the conventional sense. The development of such assays involves extensive R&D and optimization, but not typically a labeled "training set" of data for algorithm learning.

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

• As stated above, the concept of a "training set" and associated "ground truth" establishment for algorithm learning does not apply to this type of in vitro diagnostic device. The development and validation process relies on established analytical chemistry principles and performance testing against recognized standards and methods.

Ask a specific question about this device

AMY7 reagent, in conjunction with SYNCHRON® System(s) and UniCel® DxC System(s), is intended for the quantitative determination of total Amylase activity in human serum, plasma or urine.

Amylase measurements are used primarily in the diagnosis and treatment of pancreatitis.

AMY7 reagent is used to measure the amylase activity by an enzymatic rate method. The system monitors the change in absorbance at 410 nanometers. This change in absorbance is directly proportional to the activity of AMY7 in the sample and is used by the System to calculate and express the total AMY7 activity.

The SYNCHRON G7 Amylase (AMY7) Reagent is designed for optimal performance on the SYNCHRON LX®, UniCel® DxC 600/800, and SYNCHRON CX® PRO Clinical Systems. The reagent kit contains two 200-test cartridges.

Acceptance Criteria and Device Performance for SYNCHRON® Systems G7 Amylase (AMY7) Reagent

This document describes the acceptance criteria and study proving the SYNCHRON® Systems G7 Amylase (AMY7) Reagent meets these criteria, based on the provided FDA 510(k) submission (K091846).

1. Table of Acceptance Criteria and Reported Device Performance

The provided document doesn't explicitly state "acceptance criteria" with numerical thresholds. Instead, it demonstrates substantial equivalence to a predicate device through various performance studies. The implicit acceptance criterion is that the candidate device's performance should be comparable to or better than the predicate device across critical metrics.

Based on the summary of performance data, the following table outlines the reported device performance for different studies. The "Acceptance Criteria" column reflects the implicit expectation for a new device to perform comparably to or better than the predicate.

The study details that "Equivalence is demonstrated through method comparison, stability, linearity, and imprecision experiments." The provided results for method comparison and precision support this claim by showing strong correlation coefficients and low coefficients of variation, indicating the device performs comparably to the predicate.

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

The document refers to "test sets" in the context of method comparison and precision studies.

• Method Comparison Studies (Test Set Sample Sizes):
  • Serum: N=87 (on CX7 PRO), N=83 (on DxC 600)
  • Urine: N=78 (on CX7 PRO), N=78 (on DxC 600)
• Precision Studies (Test Set and Measurement Sample Sizes):
  • Each of the 12 precision measurements (e.g., Within-Run Serum/Plasma Level 1 on CX7 PRO) was based on N=80 measurements. This means 80 individual readings or replicates were taken for each specific sample level/type/imprecision category on each platform.
• Data Provenance: The document does not specify the country of origin of the data or whether the data was retrospective or prospective.

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

This section is not applicable to this type of device. The SYNCHRON® Systems G7 Amylase (AMY7) Reagent is an in-vitro diagnostic assay for quantitative determination of amylase activity. The "ground truth" for such devices is typically established by comparing its measurements against a legally marketed predicate device (as done here) or against a recognized reference method, rather than through expert consensus on qualitative interpretation (like in imaging diagnostics). Therefore, no human experts were involved in establishing the ground truth for the test set in the way described.

4. Adjudication Method for the Test Set

This section is not applicable for the same reasons as point 3. No human adjudication was involved as the ground truth is based on quantitative measurements and comparison to a predicate device.

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 section is not applicable. This device is an automated in-vitro diagnostic reagent and does not involve "human readers" or "AI assistance" in the context of interpretation or a MRMC study.

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

This describes the nature of the device: it is a standalone automated assay. The performance data presented (method comparison, precision) reflects the algorithm's (reagent's) performance without human intervention in the measurement process after sample loading. The results are generated directly by the SYNCHRON® System(s) and UniCel® DxC System(s).

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The ground truth for this device is established by comparison to a legally marketed predicate device (Thermo Fisher Scientific, Inc. Amylase EPS Reagent, K070064) using method comparison studies. This type of comparison demonstrates that the new device provides results that are substantially equivalent to a device already cleared by the FDA, implying that its measurements are generally accepted as accurate and reliable for the intended use. In addition, the device's inherent precision (reproducibility of results) is also assessed and forms part of its validated performance.

8. The Sample Size for the Training Set

The document does not provide details about a "training set" in the context of machine learning or AI models. For an IVD reagent, development and validation typically involve:

1. Reagent formulation and optimization: This involves experiments to define the optimal concentrations of components, reaction times, etc., using various samples, analogous to a training phase by trial and error in product development.
2. Verification studies (linearity, interference, etc.): These use various prepared samples to ensure the assay performs as expected.
3. Validation studies (method comparison, precision, stability): These studies, as detailed in the document, use human biological samples to demonstrate performance against established methods.

The document directly presents validation study results. It does not separate data into distinct "training" and "test" sets in the machine learning sense, as the device is a chemical reagent, not an AI model.

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

As noted in section 8, the concept of a "training set" with an associated ground truth in the AI context is not directly applicable here. The development and optimization of the reagent formulation implicitly involves establishing what constitutes an accurate amylase measurement (i.e., "ground truth") often through comparison to known standards, reference methods, or existing predicate devices during the development phase. However, the document does not detail this initial development process. The "ground truth" for the validation specified in this document is the performance of the predicate device.

Ask a specific question about this device

The EasyRA amylase Reagent (AMY) is for the measurement of a-Amylase in serum using the "EasyRA chemistry analyzer". Amylase measurements are used for the diagnosis and treatment of pancreatitis (inflammation of the pancreas) and other pancreatic disorders. For in vitro diagnostic use only.

The EasyRA Blood Urea Nitrogen (BUN) Reagent is for the measurement of urea in serum using the "EasyRA chemistry analyzer". Urea measurements in serum are used for the diagnosis and treatment of certain renal and metabolic diseases. For in vitro diagnostic use only.

The EasyRA Glucose hexokinase (GLU-H) Reagent is for the measurement of glucose in serum using the "EasyRA chemistry analyzer". Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and pancreatic islet cell carcinoma. . For in vitro diagnostic use only.

The EasyRA Triglyceride (TRIG) Reagent is for the measurement of triglycerides in serum using the "EasyRA chemistry analyzer". Triglyceride measurements are used in the diagnosis and treatment of diabetes mellitus, nephrosis, liver obstruction, and other diseases involving lipid metabolism or various endocrine disorders. For in vitro diagnostic use only.

The EasyRA Uric Acid (URIC) Reagent is for the measurement of uric acid in serum using the "EasyRA chemistry analyzer". Uric Acid measurements are used in the diagnosis and treatment of renal and metabolic disorders, including renal failure, gout, leukemia, psoriasis, starvation or other wasting conditions, and of patients receiving cytotoxic drugs. For in vitro diagnostic use only.

Not Found

The provided text is a 510(k) premarket notification approval letter for several EasyRA reagents used with the EasyRA chemistry analyzer. It does not contain information about acceptance criteria, the study design, sample sizes, ground truth establishment, or expert qualifications for demonstrating device performance.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets those criteria based solely on the provided text. The document confirms that the devices are substantially equivalent to legally marketed predicate devices, but it does not detail the specific performance studies that led to this determination.

To answer your questions, I would need access to the actual 510(k) submission document (K080823) which would contain the performance summary.

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

Amylase reagent, with associated calibrators and controls, are intended for use on ABX PENTRA 400 Clinical Chemistry Analyzer to measure amylase analyte.

ABX PENTRA Amylase CP reagent with associated calibrators and controls are for quantitative in vitro diagnostic determination of the activity of the enzyme amylase in human serum and plasma based on an enzymatic photometric assay. Amylase measurements are used primarily for the diagnosis and treatment of pancreatitis (inflammation of the pancreas).

The ABX PENTRA Multical is a calibrator for use in the calibration of quantitative Horiba ABX methods on Horiba ABX clinical chemistry analyzers.

The ABX PENTRA N Control is for use in quality control by monitoring accuracy and precision.

The ABX PENTRA P Control is for use in quality control by monitoring accuracy and precision.

All the reagents, controls and calibrators included in this submission are for use on the ABX PENTRA 400 (K052007), which is a discrete photometric benchtop clinical chemistry analyzer.

The ABX PENTRA Amylase CP is an in vitro diagnostic assay for the quantitative determination of alpha-amylase in human serum and plasma based on an enzymatic photometric test. The assay is composed of a bi-reagent cassette, with 26 ml and 6,5 ml compartments. Reagents are chemical solutions with additives.

The ABX PENTRA Multical is a lyophilized human serum calibrator with chemical additives and materials of biological origin.

The ABX PENTRA N Control and ABX PENTRA P Control are quality control products consisting of lyophilized human serum with chemical additives and materials of biological origin added as required to obtain given component levels.

The ABX PENTRA Clean-Chem CP and ABX PENTRA Clean-Chem 99 CP are ready-to-use chemical cleaning solutions for use on the ABX Pentra 400 system.

Here's a breakdown of the acceptance criteria and study information for the ABX PENTRA Amylase CP and its associated calibrators and controls, based on the provided 510(k) summary:

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

Ask a specific question about this device

The Sentinel Pancreatic Amylase is used for the quantitation of pancreatic amylase levels in human serum or plasma. Amylase measurements are used primarily for the diagnosis and treatment of pancreatitis (inflammation of the pancreas). For In Vitro use only.

The Sentinel Pancreatic Amylase is an in vitro diagnostic assay for the quantitative determination of pancreatic amylase in serum or plasma. The Sentinel Pancreatic Amylase is a two-reagent format that is carried out in two successive steps. In the first incubation step, the activity of the human salivary alpha-amylase is inhibited using two different monoclonal antibodies with no effect on the pancreatic alpha-amylase. In the second reaction step, the pancreatic alpha-amylase catalyses the hydrolysis of the EPS substrate (Ethylidene Protected Substrate) p-nitrophenyl-maltoheptaoside 4,6ethylidene-blocked (Ethylidene-G7PNP) forming 2 ethylidene-G4 + 2 G3PNP + ethylidene-G3 + G4PNP. The a-glycosidase hydrolyses all fragments of G2PNP. G3PNP, and G4PNP into p-nitro phenol (PNP) and glucose (G). The increase of absorbance, due to PNP formation, is proportional to the activity of pancreatic alphaamylase in the examined sample.

The Sentinel Pancreatic Amylase is an in vitro diagnostic assay for the quantitative determination of pancreatic amylase in serum or plasma. The study conducted aimed to demonstrate substantial equivalence to the Roche Pancreatic Amylase assay (K895880) on the Roche analyzer.

Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

• Correlation Coefficient: 0.9994
• Slope: 0.965
• Y-intercept: 3.843
  ARCHITECT c8000 vs. Sentinel Pancreatic Amylase (AEROSET):
• Correlation Coefficient: 0.9998
• Slope: 1.011
• Y-intercept: -0.796 |
  | Precision | Acceptable within-run, between-run, and between-day variability. (Specific %CV targets likely defined internally, comparable to the predicate device) | AEROSET Analyzer:
• Total %CV for Level 1: 3.99%
• Total %CV for Level 2: 1.64%
• Total %CV for Level 3: 1.11%
  ARCHITECT c8000 Analyzer:
• Total %CV for Level 1: 1.50%
• Total %CV for Level 2: 0.60% |
  | Linearity | Linear range comparable to or exceeding the predicate device. | Up to 2200 U/L |
  | Limit of Detection (Sensitivity) | Limit of detection comparable to or better than the predicate device. | 1 U/L |

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

• Method Comparison (AEROSET vs. Roche): Samples ranged from 5 to 2428 U/L. The exact number of individual samples is not explicitly stated, but the range indicates a broad spectrum of pancreatic amylase levels were tested.
• Method Comparison (ARCHITECT c8000 vs. AEROSET): Samples ranged from 4 to 2290 U/L. The exact number of individual samples is not explicitly stated.
• Precision Studies: Three levels of control material for the AEROSET and two levels of control material for the ARCHITECT c8000. For each level, within-run, between-run, and between-day studies were performed, implying multiple replicates were run over several days. The exact number of replicates is not specified.
• Data Provenance: The document does not explicitly state the country of origin of the data or whether the studies were retrospective or prospective. Given it's an in vitro diagnostic assay, the samples would typically be human serum or plasma originating from patients, and the study would be conducted prospectively (collecting samples and running tests according to a defined protocol).

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

This section is not applicable to this type of in vitro diagnostic assay. For quantitive chemical assays like the Pancreatic Amylase test, "ground truth" is established by the highly accurate and precise measurements from a reference method (the predicate device in this case, and potentially higher-order reference methods for calibration), not by expert consensus or interpretation of images.

4. Adjudication method for the test set

This is not applicable for a quantitative chemical assay. Adjudication methods like "2+1" or "3+1" are typically used in clinical imaging or pathology studies where there's subjectivity in interpretation by multiple experts. For this device, the comparison is directly between numerical results from two different assays.

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. An MRMC study is relevant for diagnostic imaging or pathology, specifically to assess the impact of a device (often AI-powered) on the performance of human readers. The Sentinel Pancreatic Amylase is a fully automated in vitro diagnostic assay that provides a quantitative numerical result; it does not involve human "readers" in the diagnostic interpretation process that an AI might assist.

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

Yes, the studies described are standalone performance studies (algorithm only). The Sentinel Pancreatic Amylase is an automated instrument-based assay, and its performance characteristics (precision, linearity, limit of detection, and method comparison) are evaluated based on the analytical measurements produced by the device itself, without human intervention in the diagnostic interpretation. The comparison is made against another standalone diagnostic assay (the predicate).

7. The type of ground truth used

The "ground truth" for the test set was essentially the measurements obtained from the legally marketed predicate device, the Roche Pancreatic Amylase assay (K895880) on the Roche analyzer (and Hitachi 911 Analyzer). For precision, linearity, and limit of detection, the ground truth is established by the inherent analytical capabilities of the assay and potentially by preparing reference materials with known concentrations. The goal of the study was to show substantial equivalence to this established method.

8. The sample size for the training set

This is not applicable in the context of this 510(k) summary for an in vitro diagnostic reagent kit. "Training set" refers to data used to develop and optimize a model or algorithm, typically for AI/machine learning applications. For a chemical assay like this, there isn't an "algorithm" in the same sense that requires a training set. The assay's performance is based on its chemical reactions and instrument calibration, which are developed through R&D and analytical validation, not by training on a data set.

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

As noted above, the concept of a "training set" and its associated ground truth is not applicable to this type of device submission. The chemical and enzymatic reactions, as well as the measurement principles, are based on established scientific principles and analytical chemistry, not on machine learning from a training data set.

Ask a specific question about this device