Search Results
Found 14 results
510(k) Data Aggregation
(30 days)
In vitro test for the quantitative determination of total bilirubin in human serum and plasma on the cobas c 111 system.
Measurements of the levels of bilirubin and organic compound formed during normal and abnormal destruction of red cells, is used in the diagnosis of liver, hemolytic hematological and metabolic disorders, including hepatitis and gall bladder block.
The Total Bilirubin Special reagent is intended for use on the cobas c 111 analyzer for the quantitative determination of total or direct bilirubin in serum and plasma.
The cobas c 111 analyzer is a partially automated, in-vitro diagnostic analyzer capable of performing clinical chemistry, specific protein and electrolyte tests. Analytes are measured photometrically or turbidimetrically; the analyzer also has an optional ISE module for measuring sodium, potassium and chloride.
The cobas c 111 instrument is a random access analyzer designed to be operated on a bench top in the professional environment using a combination of a photometric analysis unit and an optional ion selective electrodes (ISE).
Here's a breakdown of the acceptance criteria and study information for the Total Bilirubin Special reagent application to the cobas c 111 analyzer, based on the provided text:
Context: This submission is a Special 510(k) for a modification to an existing device. The modification involves applying the already cleared Total Bilirubin Special reagent to a new analyzer, the cobas c 111, which is itself a modification of the COBAS INTEGRA 400 plus. Therefore, the primary focus of the performance data is to demonstrate equivalence of the reagent's performance on the new analyzer compared to its performance on the predicate analyzer.
Acceptance Criteria and Reported Device Performance
The acceptance criteria are implicitly defined by demonstrating equivalence to the predicate device. The performance characteristics of the modified device (on cobas c 111) are compared to the predicate device (on COBAS INTEGRA Total Bilirubin Special, K063543).
| Acceptance Criteria (Implicit: Equivalence to Predicate) | Reported Device Performance (Modified Device: Total Bilirubin Special on cobas c 111) | Predicate Device Performance (COBAS INTEGRA Total Bilirubin Special) |
|---|---|---|
| Precision (Within-run) | 1.79% @ 21.7 µmol/L | 2.44% @ 15.80 µmol/L |
| 0.64% @ 64.2 µmol/L | 1.39% @ 54.00 µmol/L | |
| 2.94% @ 15.2 µmol/L | (Not explicitly within-run for this level) | |
| 0.77% @ 60.0 µmol/L | (Not explicitly within-run for this level) | |
| Precision (Total) | 2.32% @ 21.6 µmol/L | (Not explicitly "Total") |
| 0.71% @ 67.4 µmol/L | (Not explicitly "Total") | |
| 3.10% @ 16.2 µmol/L | (Not explicitly "Total") | |
| 0.79% @ 83.0 µmol/L | (Not explicitly "Total") | |
| Precision (Between day) | (Not explicitly stated for modified device) | 4.13% @ 14.7 µmol/L |
| (Not explicitly stated for modified device) | 2.15% @ 47.20 µmol/L | |
| Measuring Range | 0.1-25.2 mg/dL | 0-25 mg/dL |
| Measuring Range (with postdilution) | 0.1-101 mg/dL | 0-250 mg/dL |
| Lower Detection Limit | 0.1 mg/dL | 0.063 mg/dL |
| Endogenous interferences | Same (as predicate) | Hemolysis: No significant interference up to 1000 mg/dL, Lipemia: No significant interference up to 1400 mg/dL as Intralipid |
| Exogenous interferences | Same (as predicate) | Ascorbic acid at 30 mg/dL causes artificially decreased total bilirubin values |
Note on Acceptance Criteria: For a Special 510(k) like this, the implicit acceptance criterion is that the performance of the modified device is substantially equivalent to the predicate device, meaning it performs as well or better for the critical parameters. The table demonstrates this comparable performance.
Study Information
-
Sample sizes used for the test set and the data provenance:
- Test Set Sample Size: The document does not explicitly state the sample size used for the performance evaluation (precision, measuring range, detection limit, interference studies).
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). This is a manufacturer's internal validation, likely conducted in a controlled lab environment.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This being an in-vitro diagnostic (IVD) chemistry analyzer, the "ground truth" for the test set is established by the reference method for total bilirubin (Doumas reference method, as mentioned in the traceability section) and highly controlled laboratory samples (e.g., control materials, spiked samples). There's no mention of human experts interpreting results in the way a radiologist interprets an image.
-
Adjudication method for the test set:
- Not applicable in the context of an IVD chemistry analyzer. Results are quantitative outputs from the instrument.
-
If a multi-reader multi-case (MRMC) comparative effectiveness study was done:
- No. This is a quantitative in-vitro diagnostic device, not an imaging device that requires human interpretation.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, this is an algorithm-only (analyzer-only) performance study. The analyzer performs the test and provides a quantitative result. There is no human interpretation component in the direct measurement of bilirubin by this device.
-
The type of ground truth used:
- Reference Method: The device is standardized against the Doumas reference method for total bilirubin. This is the primary established ground truth for bilirubin measurement.
- Control Materials: Performance is likely evaluated using assayed control materials (e.g., Precinorm U, Precipath U mentioned as quality controls) with known concentration values.
-
The sample size for the training set:
- Not applicable as this is not a machine learning/AI algorithm that requires a "training set" in the conventional sense. This is an analytical chemistry device where the "training" would be the initial development and calibration of the reagent and instrument platform.
-
How the ground truth for the training set was established:
- Not applicable. The "ground truth" for the development of such an IVD device is based on established clinical chemistry principles and standardization against internationally recognized reference methods (like Doumas). Calibrators are used to establish the measurement curve, and these calibrators are themselves traceable to a reference method.
Ask a specific question about this device
(64 days)
The Osmetech OPTI LION Electrolyte Analyzer is intended to be used for the measurement of pH, sodium, potassium, ionized calcium, and chloride in samples of whole blood, serum, plasma and aqueous controls in either a traditional clinical laboratory setting or point-of-care locations by personnel minimally qualified to perform and report these results.
The OPTI LION Electrolyte Analyzer is a small [4.7 x 14.2 x 9.1 inches, 10 pounds}, microprocessor-based instrument using optical fluorescence for the measurement of pH, sodium, potassium, ionized calcium, and chloride and utilizes a graphical touch screen user interface.
The disposable, single use cassette contains five optical fluorescent sensors placed in a polycarbonate substrate, which is packaged with an insert-able sample probe into a sealed foil pouch which bears a bar-code label with calibration, lot identification, and expiration dating information.
The Osmetech OPTI LION Electrolyte Analyzer is a medical device intended for the measurement of pH, sodium, potassium, ionized calcium, and chloride in whole blood, serum, plasma, and aqueous controls. The following information details the acceptance criteria and the study that proves the device meets these criteria.
1. Table of Acceptance Criteria and Reported Device Performance
The provided document does not explicitly state pre-defined acceptance criteria values for each analyte. Instead, it refers to the "medically allowable errors as defined in CLIA'88 performance standards" as the benchmark for comparison. The study's conclusion is that the device's performance is acceptable against these standards.
Without specific numerical acceptance criteria from the document, we can infer the performance metrics reported as evidence of meeting an unspecified acceptable level based on CLIA'88 standards.
| Analyte | Acceptance Criteria (Implied by CLIA'88 Standards) | Reported Device Performance (Systematic Differences and 95% CIs) |
|---|---|---|
| pH | Systematic differences and 95% CIs |
Ask a specific question about this device
(62 days)
The Preciset DAT Plus II calibrators are designed for the calibration of the Roche assays for drugs of abuse in human urine on automated clinical chemistry analyzers. The Cfas DAT Qualitative Plus calibrator is designed for the qualitative calibration of the Roche assays for drugs of abuse in human urine on automated clinical chemistry analyzers.
Roche Preciset DAT Plus II calibrators contain a mixture of 2 different drugs, prepared by the quantitative addition of drug or drug metabolite to drug-free human urine. Drugs included are benzodiazepines and opiates. The calibrator set contains up to six levels for each drug contained in bottles 1-6. Bottle 1 is negative (drug free) human urine, followed by bottles 2-6 containing increasing amounts of each drug in a multi-analyte mixture. Drug or drug metabolite and their respective levels included are as follows: Benzodiazepines: 0, 50, 100, 200, 400 ng/ml (no 6th level) Opiates: 0, 150, 300, 600, 1000, 2000 ng/ml. Roche Cfas DAT Qualitative Plus calibrator contains a mixture of 7 different drugs, prepared by the quantitative addition of drug or drug metabolite to drug-free human urine. Drugs included are barbiturates, benzodiazepines, cocaine, methadone, opiates, phencyclidine, and propoxyphene. The calibrator set contains a single level for each drug mixture. Drugs or drug metabolites and their respective levels included are as follows: Barbiturates: 200 ng/ml Benzodiazepines: 300 ng/ml Cocaine: 150 ng/ml Methadone: 300 ng/ml Opiates: 2000 ng/ml Phencyclidine: 25 ng/ml Propoxyphene: 300 ng/ml
The provided text describes a 510(k) summary for Roche Preciset DAT Plus II and Cfas DAT Qualitative Plus Calibrators, which are devices used for calibrating drug of abuse assays in human urine on automated clinical chemistry analyzers. As such, the information does not contain acceptance criteria or study results in the typical sense of measuring device performance against a predefined clinical or technical threshold.
Instead, this document focuses on demonstrating substantial equivalence to a predicate device. This regulatory pathway does not require new efficacy studies if the new device is sufficiently similar to a previously cleared one.
Therefore, many of the requested elements for describing acceptance criteria and study results are not applicable to this type of regulatory submission and the provided documentation.
Here's an assessment based on the available information:
1. Table of acceptance criteria and the reported device performance:
- Not applicable. The document does not describe specific acceptance criteria (e.g., sensitivity, specificity, accuracy targets) for its own performance. Instead, it aims to show substantial equivalence to a 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):
- Not applicable. This document does not describe a performance study with a test set in the way you might expect for a diagnostic device measuring patient outcomes. The "data" here refers to the quantitative addition of drug or drug metabolite to drug-free human urine for calibrator preparation.
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):
- Not applicable. Ground truth in this context would relate to the precise concentration of drugs in the calibrators, which is established by the manufacturer through quantitative addition, not by expert interpretation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not applicable. No adjudication method is described as this is not a study assessing diagnostic performance against a clinical ground truth.
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:
- Definitely Not applicable. This device is a calibrator for laboratory assays, not an AI-powered diagnostic tool involving human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable. This is not an algorithm, but a physical calibrator product.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The "ground truth" for the calibrators is the known, quantitatively added concentration of drug or drug metabolite in drug-free human urine. This is an engineered "truth" rather than a discovery-based one (like pathology).
8. The sample size for the training set:
- Not applicable. There is no "training set" in the context of this device. The calibrators are manufactured to precise specifications.
9. How the ground truth for the training set was established:
- Not applicable. As above, no training set for this product. The "ground truth" for the calibrators themselves is established by the quantitative addition process during manufacturing.
Summary of what the document DOES provide regarding comparison:
The core of the submission is to establish substantial equivalence to the predicate device: "Abuscreen OnLine Preciset DAT I Calibrators" (K951595).
The comparison focuses on:
- Intended Use: Both the new device and the predicate are designed for the calibration of Roche assays for drugs of abuse in human urine on automated clinical chemistry analyzers.
- Device Description (Composition):
- Preciset DAT Plus II: Contains Benzodiazepines (0, 50, 100, 200, 400 ng/ml) and Opiates (0, 150, 300, 600, 1000, 2000 ng/ml). Up to six levels.
- Cfas DAT Qualitative Plus: Contains Barbiturates (200 ng/ml), Benzodiazepines (300 ng/ml), Cocaine (150 ng/ml), Methadone (300 ng/ml), Opiates (2000 ng/ml), Phencyclidine (25 ng/ml), Propoxyphene (300 ng/ml). Single level.
- Predicate Device (Abuscreen OnLine Preciset DAT I): Contains a mixture of 9 different drugs (amphetamines, barbiturates, benzodiazepines, cocaine, methadone, methaqualone, opiates, phencyclidine, and propoxyphene). Four levels for each drug.
- All calibrators are prepared by the quantitative addition of drug or drug metabolite to drug-free human urine.
The primary argument for substantial equivalence rests on the similar intended use and the fact that both the new and predicate devices are calibrators for drug of abuse assays, even though the specific drug mixtures and number of levels differ. The regulatory approval letter confirms that the FDA determined the device to be substantially equivalent to legally marketed predicate devices.
Ask a specific question about this device
(20 days)
The cassette COBAS Integra Albumin Gen.2 (ALB2) contains an in vitro diagnostic reagent system intended for use on COBAS Integra systems for the quantitative determination of the albumin concentration in human serum and plasma. Albumin measurements are used in the diagnosis and treatment of numerous diseases involving primarily the liver or kidneys.
The COBAS Integra Albumin Gen.2 is a colorimetric assay for the determination of albumin concentration in serum or plasma. At a pH value of 4.1, albumin displays a sufficiently cationic character to be able to bind with bromcresol green (BCG) to form a blue-green complex. The color intensity is directly proportional to the albumin concentration and can be determined photometrically.
The provided text is a 510(k) Summary for the COBAS Integra Albumin Gen.2. It describes the device, its intended use, and claims substantial equivalence to a predicate device. However, it does not contain any information about acceptance criteria, device performance studies, sample sizes, expert ground truth, adjudication methods, or comparative effectiveness studies. The document primarily focuses on regulatory approval and equivalence to a previously marketed device.
Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets the acceptance criteria, as this information is not present in the provided text.
Ask a specific question about this device
(28 days)
Ammonia/Ethanol/CO2 Calibrator is for use in the calibration of quantitative Roche methods on Roche clinical chemistry analyzers as specified in the enclosed value sheet.
Ammonia/Ethanol/CO2 Control is for use in quality control by monitoring accuracy and precision for the quantitative methods as specified in the enclosed value sheet.
The Ammonia/Ethanol/CO2 Calibrator is a liquid ready-for-use calibrator based on a buffered aqueous solution. The concentration of the calibrator The Ammonia/Ethanol/CO2 Controls are liquid ready-for-use controls based on a buffered aqueous solution. The adjusted concentrations of the control components are in the normal range for the Normal control and the pathological range for the Abnormal control.
This document is a 510(k) summary for a medical device (Ammonia/Ethanol/CO2 Calibrator and Controls) and does not contain information typically found in a study proving a device meets acceptance criteria for an AI or software-based medical device.
The provided text describes a calibrator and controls for in vitro diagnostic devices, which are reagents used to ensure the accuracy and precision of laboratory tests on clinical chemistry analyzers. These are physical products, not software/AI, and therefore the concepts of "acceptance criteria," "device performance," "sample size for test/training sets," "ground truth," "MRMC studies," or "standalone performance" as typically applied to AI/software devices are not directly applicable in the same way.
The document focuses on establishing substantial equivalence to existing legally marketed predicate devices, which is the regulatory pathway for this type of product. Substantial equivalence means the new device is as safe and effective as a legally marketed device that is not subject to PMA (Premarket Approval).
Here's a breakdown of the information in relation to your request, highlighting what's missing due to the nature of the device:
1. Table of Acceptance Criteria and Reported Device Performance:
This type of table is not present in the document because this is not a performance study of an AI/software device. For a calibrator/control, "performance" relates to its ability to accurately and precisely calibrate and control the analytical process of a clinical chemistry analyzer. The document states:
- Intended Use of Calibrator: "for use in the calibration of quantitative Roche methods on Roche clinical chemistry analyzers as specified in the enclosed value sheet."
- Intended Use of Control: "for use in quality control by monitoring accuracy and precision for the quantitative methods as specified in the enclosed value sheet."
The "acceptance criteria" here would generally be related to the stability, homogeneity, and assigned values of the calibrator/control, and their ability to ensure the accuracy of the assay. These details are not within this summary. Substantial equivalence usually means that the new device performs similarly to the predicate in these aspects.
| Acceptance Criteria (Implied for Calibrator/Control) | Reported Device Performance (Implied from substantial equivalence claim) |
|---|---|
| Ability to accurately calibrate quantitative Roche methods | Substantially equivalent to predicate device (K952282) |
| Ability to monitor accuracy and precision for quantitative methods | Substantially equivalent to predicate device (K951595) |
| Performance characteristics (e.g., analyte concentrations, stability) | Equivalent to predicate devices (K952282 and K951595) |
Regarding items 2-9, these are generally not applicable to this type of device and submission:
2. Sample size used for the test set and the data provenance: Not applicable. There's no "test set" in the context of an AI/software algorithm. The device itself is a physical calibrator/control.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for an AI/software device is not relevant here. The ground truth for the calibrator/control would be the analytically determined true values of the analytes within the product, established through reference methods or highly accurate assays, not expert consensus on images or similar data.
4. Adjudication method for the test set: Not applicable.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not applicable. This type of study is for evaluating human performance with and without AI assistance for tasks like diagnosis or detection.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable. This is not an algorithm.
7. The type of ground truth used: For a calibrator/control, the "ground truth" refers to the assigned values or the true concentrations of the analytes (Ammonia, Ethanol, CO2) within the calibrator and control materials. This is typically established through a rigorous analytical process using reference methods and highly accurate instrumentation, not expert consensus, pathology, or outcomes data in the way these terms are used for AI/software devices.
8. The sample size for the training set: Not applicable. No training set for an AI/software algorithm.
9. How the ground truth for the training set was established: Not applicable.
Summary of what's provided for this type of device and submission:
- Device Name: Ammonia/Ethanol/CO2 Calibrator and Controls
- Intended Use: Calibration and quality control for quantitative Roche methods on Roche clinical chemistry analyzers.
- Predicate Device:
- Regulatory Conclusion: Substantial Equivalence to the predicate devices. This means the FDA has determined the new device is as safe and effective as the existing marketed devices. The "study that proves the device meets the acceptance criteria" in this context is the evidence presented by the manufacturer to the FDA demonstrating this substantial equivalence, which would include data on the formulation, stability, and characterization of the calibrator and controls, demonstrating they perform comparably to the predicate. These detailed data points are not typically included in the 510(k) Summary, but rather in the full 510(k) submission.
Ask a specific question about this device
(50 days)
The cassette COBAS INTEGRA LDL Direct (LDL-D) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA 700 for the quantitative determination of LDL-cholesterol direct concentration in serum and plasma. Low density lipoprotein cholesterol measurement, in conjunction with other lipid determinations, has been shown to be useful in assessing the risk of coronary heart disease.
The Roche Calibrator LDL Direct is intended for use as calibrator in quantitative Low Density Lipoprotein cholesterol assays. It is recommended for use with LDL Direct reagents on COBAS® chemistry systems. A calibrator is a device intended for medical purposes for use in a test system to establish points of reference that are used in the determination of values in the measurement of substances in human specimens.
The COBAS INTEGRA test applications contained in this submission are intended for use with the COBAS INTEGRA Analyzer, which is also known as the COBAS INTEGRA 700. The COBAS INTEGRA Analyzer and COBAS INTEGRA Reagent cassettes together provide an integrated system for in vitro diagnostic testing. The COBAS INTEGRA Analyzer utilizes three measuring principles, i.e., absorbance, fluorescence polarization and ion-selective electrodes. The analyzer has a throughput of up to 600 tests per hour with STAT samples prioritized and tested immediately. Random sample access, robotics and a user interface optimize time management and streamline workflow. The COBAS INTEGRA can store up to 68 COBAS INTEGRA Reagent Cassettes on board, 24 hours a day at 2-8°C. The COBAS INTEGRA Reagent Cassettes are compact and preparation-free with the added convenience of long term on-board stability. Barcode readers are used to identify newly loaded reagent cassettes, samples for patient identification, and rack inserts and to read calibration and control data from the cassette label. COBAS INTEGRA tests include chemistry, drugs of abuse, immunology, ion selective electrodes, therapeutic drug monitoring, and hematology reagents.
The cassette COBAS INTEGRA LDL Direct (LDL-D) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA 700 for the quantitative determination of LDL-cholesterol direct concentration in serum and plasma.
The Roche Calibrator LDL Direct is intended for use as calibrator in quantitative Low Density Lipoprotein cholesterol assays. It is recommended for use with LDL Direct reagents on COBAS® chemistry systems.
Here's a breakdown of the acceptance criteria and study information for the Roche COBAS® INTEGRA LDL Direct and Roche Calibrator LDL Direct, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't explicitly state "acceptance criteria" as a separate, pre-defined set of thresholds. Instead, it presents performance characteristics of the new device and compares them to those of predicate devices to demonstrate substantial equivalence. The implication is that if the new device's performance aligns with or is comparable to the predicate devices, it meets the "acceptance criteria" for substantial equivalence.
| Performance Characteristic | Acceptance Criteria (Implied by Predicate Performance) | Reported Device Performance (COBAS INTEGRA LDL Direct) |
|---|---|---|
| Intended Use (Reagent) | Quantitative determination of LDL-cholesterol direct concentration in serum or plasma, useful in assessing coronary heart disease risk. | Quantitative determination of LDL-cholesterol direct concentration in serum and plasma, useful in assessing coronary heart disease risk. |
| Intended Use (Calibrator) | Calibrator for quantitative Low Density Lipoprotein cholesterol assays. | Calibrator for quantitative Low Density Lipoprotein cholesterol assays on COBAS chemistry systems. |
| Matrix (Calibrator) | Human serum | Human serum |
| Approx. Value (Calibrator) | 51.4 mg/dL | 2.85 mmol/L (110 mg/dL) |
| Precision (Level 1 Mean) | Not explicitly stated (predicate data not available for direct comparison) | 2.72 mmol/L (105 mg/dL) |
| Precision (Level 1 Within Run CV) | Not explicitly stated | 1.4 |
| Precision (Level 1 Total CV) | Not explicitly stated | 1.9 |
| Precision (Level 2 Mean) | Not explicitly stated | 5.12 mmol/L (198 mg/dL) |
| Precision (Level 2 Within Run CV) | Not explicitly stated | 1.8 |
| Precision (Level 2 Total CV) | Not explicitly stated | 2.1 |
| Linearity | 500 mg/dL | 14.0 mmol/L (540 mg/dL) |
| Accuracy (Correlation Coefficient vs. COBAS MIRA) | Not explicitly stated (predicate comparison is to Beta-quantification or Friedewald) | 0.964 |
| Accuracy (Linear Regression vs. COBAS MIRA) | Not explicitly stated | y = 0.85x + 0.7 mmol/L |
Note: For accuracy, the new device is compared to COBAS MIRA, Beta-quantification, and Friedewald formula. The predicate device's accuracy is provided against Beta-quantification. The document implies that a strong correlation (e.g., r > 0.95) and a linear regression close to y=x would be acceptable for accuracy.
2. Sample Size Used for the Test Set and Data Provenance
The document refers to "clinical and nonclinical studies."
-
Test Set Sample Size for Accuracy:
- Against COBAS MIRA: n = 276
- Against Beta-quantification: n = 150
- Against Friedewald formula: n = 276
-
Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts
This type of information is not provided in the document. For an in vitro diagnostic device like this, ground truth is typically established through reference methods or established laboratory procedures, not by human experts in the way it would be for an imaging AI.
4. Adjudication Method for the Test Set
This information is not applicable and therefore not provided. Adjudication methods (like 2+1, 3+1) are common in clinical trials involving subjective interpretations (e.g., imaging reads) to resolve discrepancies. For a quantitative diagnostic test like LDL-cholesterol, discrepancies would typically be resolved by retesting, using a definitive reference method, or investigating pre-analytical/analytical errors.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of Human Readers Improvement with AI vs. Without AI Assistance
This information is not applicable and therefore not provided. MRMC studies are relevant for imaging devices or AI tools where human readers are interpreting data, and the AI's role is to assist or augment their performance. The Roche COBAS INTEGRA LDL Direct is a laboratory diagnostic assay, not one that involves human interpretation of "cases" in an MRMC context.
6. If a Standalone Study (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, this is essentially a standalone study. The document describes the performance of the COBAS INTEGRA LDL Direct system itself (the reagent cassette + analyzer) in measuring LDL-cholesterol directly. There isn't a human-in-the-loop component described for the function of this diagnostic device.
7. The Type of Ground Truth Used
The ground truth for the accuracy studies was established by comparing the COBAS INTEGRA LDL Direct results against:
- COBAS MIRA: Another automated chemistry analyzer, likely acting as a comparative reference method.
- Beta-quantification: A established reference method for lipoprotein analysis, considered highly accurate for LDL-cholesterol.
- Friedewald formula: A calculated estimate of LDL-cholesterol based on other lipid measurements (total cholesterol, HDL-cholesterol, triglycerides).
8. The Sample Size for the Training Set
The document does not mention a "training set". This is an in vitro diagnostic device, not an AI/machine learning algorithm in the typical sense that would require a distinct training set for model development. The development process for an IVD involves formulation, optimization, and verification, rather than "training" with a dataset for an algorithm.
9. How the Ground Truth for the Training Set Was Established
Since there is no "training set" mentioned or implied for this type of device, this information is not applicable.
Ask a specific question about this device
(82 days)
The cassette COBAS INTEGRA x-1-Antitrypsin (AAT) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA 700 for the quantitative immunological determination of human x-1-antitrypsin in serum and plasma. The measurements aid in the diagnosis of several conditions including juvenile and adult cirrhosis of the liver. In addition, a-1-antitrypsin deficiency has been associated with pulmonary emphysema.
The cassette COBAS INTEGRA Immunoglobulin A (IGA/IGAP) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA 700 for the quantitative immunological determination of human immunoglobulin A in serum and plasma. addition to the standard application (IGA), the sensitive application (IGAP) is designed for the quantitative determination of low IgA concentrations in e.g. pediatric samples. Measurement of this immunoglobulin aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
The cassette COBAS INTEGRA Immunoglobulin M (IGM/IGMP) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA 700 for the quantitative immunological determination of human immunoglobulin M in serum and plasma. In addition to the standard application (IGM), the sensitive application (IGMP) is designed for the quantitative determination of low IgM concentrations in e.g. pediatric samples. Measurement of this immunoglobulin aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
The cassette COBAS INTEGRA Immunoglobulin G (Turbidimetric) (IGGT/IGGTC) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA 700 for the quantitative immunological determination of human immunoglobulin G in serum, plasma (IGGT) and cerebrospinal fluid (IGGTC). Measurement of this immunoglobulin aids in the diagnosis of abnormal protein metabolism and the body's lack of ability to resist infectious agents.
The COBAS INTEGRA test applications contained in this submission are intended for use with the COBAS INTEGRA Analyzer, which is also known as the COBAS INTEGRA 700. The COBAS INTEGRA Analyzer and COBAS INTEGRA Reagent cassettes together provide an integrated system for in vitro diagnostic testing. The COBAS INTEGRA Analyzer utilizes three measuring principles, i.e., absorbance, fluorescence polarization and ion-selective electrodes. The analyzer has a throughput of up to 600 tests per hour with STAT samples prioritized and tested immediately. Random sample access, robotics and a user interface optimize time management and streamline workflow. The COBAS INTEGRA can store up to 68 COBAS INTEGRA Reagent Cassettes on board, 24 hours a day at 2-8°C. The COBAS INTEGRA Reagent Cassettes are compact and preparation-free with the added convenience of long term on-board stability. Barcode readers are used to identify newly loaded reagent cassettes, samples for patient identification, and rack inserts and to read calibration and control data from the cassette label. COBAS INTEGRA tests include chemistry, drugs of abuse, immunology, ion selective electrodes, therapeutic drug monitoring, and hematology reagents.
Here's a breakdown of the acceptance criteria and study information for the Roche COBAS® INTEGRA Reagent Cassettes for α-1-Antitrypsin (AAT), Immunoglobulin A (IGA/IGAP), and Immunoglobulin M (IGM/IGMP), based on the provided text:
Important Note: The provided document is a 510(k) Summary. This type of summary focuses on demonstrating substantial equivalence to a legally marketed predicate device, rather than proving the device meets specific pre-defined acceptance criteria in the same way a novel device might. The "acceptance criteria" here are inferred from the performance characteristics presented to show equivalence. The studies are primarily comparative studies against predicate devices.
1. Table of Acceptance Criteria and Reported Device Performance
Device: Roche COBAS® INTEGRA Reagent Cassettes (AAT, IGA/IGAP, IGM/IGMP)
| Performance Characteristic | Acceptance Criteria (inferred from predicate/previous version) | Reported Device Performance (Modified COBAS INTEGRA) | Predicate Device Performance (where available) |
|---|---|---|---|
| α-1-Antitrypsin (AAT) | |||
| Accuracy (Corr. Coeff. (r)) | Must be comparable to predicate (e.g., K972640: 0.967 / K954992: 0.930) | 0.995 (vs. BM) | Predicate K972640: 0.967; Cleared K954992: 0.930 |
| Linear Regression | Must be comparable to predicate | 1.30x - 0.31 g/L | Predicate K972640: 0.993x + 9.9 mg/dL; Cleared K954992: 0.90x + 0.06 g/L |
| Immunoglobulin A (IGA/IGAP) | |||
| Precision (IGA) | |||
| Level 1 (Mean ~2.0-2.3 g/L) | Within-run CV comparable to predicate/cleared (e.g., BM: 0.9%, Cleared: 1.4%) | 2.0% | Predicate BM: 0.9%; Cleared K954457: 1.4% |
| Level 2 (Mean ~3.5-6.2 g/L) | Within-run CV comparable to predicate/cleared (e.g., BM: 0.8%, Cleared: 0.81%) | 0.97% | Predicate BM: 0.8%; Cleared K954457: 0.81% |
| Total CV Level 1 | Total CV comparable to predicate/cleared (e.g., BM: 2.2%, Cleared: 2.8%) | 2.3% | Predicate BM: 2.2%; Cleared K954457: 2.8% |
| Total CV Level 2 | Total CV comparable to predicate/cleared (e.g., BM: 1.8%, Cleared: 1.8%) | 1.2% | Predicate BM: 1.8%; Cleared K954457: 1.8% |
| Accuracy (Corr. Coeff. (r)) | Must be comparable to predicate (e.g., BM: 0.99 / Cleared: 0.989) | 0.994 (vs. BM/Hitachi) | Predicate BM: 0.99; Cleared K954457: 0.989 |
| Linear Regression | Must be comparable to predicate | 1.023x - 0.214 g/L | Predicate BM: 0.83x + 20.6 mg/dL; Cleared K954457: 0.97x - 0.05 g/L |
| Assay Range | Must be comparable or improved | 0.45 - 7.3 g/L (std); 0.15 - 98.6 g/L (rerun) | Cleared K954457: 0.79 - 12.6 g/L (std); 0.27 - 30.2 g/L (rerun) |
| Sensitivity | Must be comparable or improved | 0.45 g/L | Cleared K954457: 0.79 g/L |
| Immunoglobulin M (IGM/IGMP) | |||
| Precision (IGM) | |||
| Level 1 (Mean ~0.55-0.6 g/L) | Within-run CV comparable to predicate/cleared (e.g., BM: 0.79%, Cleared: 2.6%) | 2.4% | Predicate BM: 0.79%; Cleared K954457: 2.6% |
| Level 2 (Mean ~1.9-2.0 g/L) | Within-run CV comparable to predicate/cleared (e.g., BM: 0.8%, Cleared: 2.0%) | 1.6% | Predicate BM: 0.8%; Cleared K954457: 2.0% |
| Total CV Level 1 | Total CV comparable to predicate/cleared (e.g., BM: 3.7%, Cleared: 3.1%) | 3.2% | Predicate BM: 3.7%; Cleared K954457: 3.1% |
| Total CV Level 2 | Total CV comparable to predicate/cleared (e.g., BM: 2.4%, Cleared: 2.2%) | 1.9% | Predicate BM: 2.4%; Cleared K954457: 2.2% |
| Accuracy (Corr. Coeff. (r)) | Must be comparable to predicate (e.g., BM: 0.979 / Cleared: 0.994) | 0.994 (vs. BM/Hitachi) | Predicate BM: 0.979; Cleared K954457: 0.994 |
| Linear Regression | Must be comparable to predicate | 1.293x + 0.341 g/L | Predicate BM: 0.81x + 5.9 mg/dL; Cleared K954457: 1.12x - 0.06 g/L |
| Assay Range | Must be comparable or improved | 0.16 - 5.18 g/L (std); 0.05 - 24.35 g/L (rerun) | Cleared K954457: 0.31 - 5.0 g/L (std); 0.11 - 12.1 g/L (rerun) |
| Sensitivity | Must be comparable or improved | 0.16 g/L | Cleared K954457: 0.31 g/L |
2. Sample Sizes Used for the Test Set and Data Provenance
- α-1-Antitrypsin (AAT):
- Sample Size: 288
- Data Provenance: Not explicitly stated but implied to be clinical samples (serum/plasma). Origin (e.g., country) and retrospective/prospective nature are not specified.
- Immunoglobulin A (IGA/IGAP):
- Sample Size: 584
- Data Provenance: Not explicitly stated but implied to be clinical samples (serum/plasma). Origin (e.g., country) and retrospective/prospective nature are not specified.
- Immunoglobulin M (IGM/IGMP):
- Sample Size: 556
- Data Provenance: Not explicitly stated but implied to be clinical samples (serum/plasma). Origin (e.g., country) and retrospective/prospective nature are not specified.
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 reagent, and the 'ground truth' is established by comparative measurements against predicate devices using laboratory methods, not human expert interpretation of images or clinical cases. The comparison is against established laboratory testing methods.
4. Adjudication Method for the Test Set
Not applicable. The 'test set' here consists of biological samples measured by the device and compared to results from predicate devices/methods. There is no human adjudication process described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No. MRMC studies are typically for imaging devices or AI tools that assist human readers in interpretation. This is an IVD reagent, and the effectiveness is evaluated through analytical performance characteristics like accuracy, precision, and linearity when compared to established methods.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, in a sense. The studies summarized are standalone performance evaluations of the reagent cassette on the COBAS INTEGRA Analyzer. The results are generated by the automated system, without "human-in-the-loop" needing to interpret the primary measurement, although human operators load samples and review results. The comparison is between the modified reagent's performance and that of other established laboratory methods (predicate devices).
7. The Type of Ground Truth Used
The ground truth used for these studies is comparative measurement data from legally marketed predicate devices and established laboratory methods. Specifically:
- AAT: Comparison against Boehringer Mannheim α-1-Antitrypsin Reagent (K972640) and Cleared COBAS INTEGRA α-1-Antitrypsin (K954992). The "vs. BM" implies using the Boehringer Mannheim method as a reference.
- IGA/IGAP: Comparison against Boehringer Mannheim Immunoglobulin A Reagent (K955907) and Cleared COBAS INTEGRA Immunoglobulin A (K954457). The "vs. BM/Hitachi" indicates comparison with these laboratory systems.
- IGM/IGMP: Comparison against Boehringer Mannheim Immunoglobulin M Reagent (K955908) and Cleared COBAS INTEGRA Immunoglobulin M (K954457). The "vs. BM/Hitachi" indicates comparison with these laboratory systems.
8. The Sample Size for the Training Set
Not applicable. These are reagent cassettes used with an existing analyzer. There is no mention of machine learning or AI models with "training sets" in the context of this 510(k) submission. The development and optimization of the reagent formulations and assay parameters would be part of a different internal R&D process, not typically described as a "training set" in this context.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no "training set" in the context of this device and submission. The "ground truth" for evaluating the performance of these reagents is established through established analytical chemistry and immunology principles, validated against reference materials, and benchmarked against predicate diagnostic assays.
Ask a specific question about this device
(86 days)
The cassette COBAS INTEGRA Alkaline Phosphatase IFCC liquid (ALPL2 and ALPL6) contain an in vitro diagnostic reagent system intended for use on COBAS INTEGRA for the quantitative determination of the catalytic activity of alkaline phosphatase in serum and plasma. Measurements of alkaline phosphatase or its isoenzymes are used in the diagnosis and treatment of liver, bone, parathyroid, and intestinal diseases.
The cassette COBAS INTEGRA a-Amylase EPS Pancreatic (AMY-P / AMYUP) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA for the quantitative determination of the catalytic activity of pancreatic or-amylase in serum, plasma, and urine. Amylase measurements are used primarily for the diagnosis and treatment of pancreatitis (inflammation of the pancreas).
The cassette COBAS INTEGRA C-reactive Protein (Latex), (CRPLX) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA for the quantitative immunological determination of human C-reactive protein in serum and plasma. Measurements of C-reactive protein aids in evaluation of the amount of injury to tissue.
The COBAS INTEGRA test applications contained in this submission are intended for use with the COBAS INTEGRA Analyzer, which is also known as the COBAS INTEGRA 700. The COBAS INTEGRA Analyzer and COBAS INTEGRA Reagent cassettes together provide an integrated system for in vitro diagnostic testing. The COBAS INTEGRA Analyzer utilizes three measuring principles, i.e., absorbance, fluorescence polarization and ion-selective electrodes. The analyzer has a throughput of up to 600 tests per hour with STAT samples prioritized and tested immediately. Random sample access, robotics and a user interface optimize time management and streamline workflow. The COBAS INTEGRA can store up to 68 COBAS INTEGRA Reagent Cassettes on board, 24 hours a day at 2-8°C. The COBAS INTEGRA Reagent Cassettes are compact and preparation-free with the added convenience of long term on-board stability. Barcode readers are used to identify newly loaded reagent cassettes, samples for patient identification, and rack inserts and to read calibration and control data from the cassette label. COBAS INTEGRA tests include chemistry, drugs of abuse, immunology, ion selective electrodes, therapeutic drug monitoring, and hematology reagents. Through this submission, it is the intention of Roche to gain clearance for three additional COBAS Reagent Cassettes. These are the COBAS INTEGRA Alkaline Phosphatase IFCC liquid (ALPL2 and ALPL6), the COBAS INTEGRA a-Amylase EPS Pancreatic (AMY-P / AMYUP), and the COBAS INTEGRA C-Reactive Protein (Latex), (CRPLX).
The provided text is a 510(k) Summary for Roche COBAS® INTEGRA Reagent Cassettes, detailing the characteristics and performance of three new reagent cassettes (Alkaline Phosphatase IFCC liquid, α-Amylase EPS Pancreatic, and C-Reactive Protein (Latex)) compared to their legally marketed predicate devices.
Here's an analysis of the acceptance criteria and study information:
1. Table of Acceptance Criteria and Reported Device Performance
The documents do not explicitly state "acceptance criteria" as a set of predefined thresholds that the device must meet in the same way modern AI/ML device submissions would. Instead, the "Performance Characteristics" section for each proposed device is presented alongside the performance of its predicate device, implying that equivalence in these characteristics is the underlying acceptance criterion for substantial equivalence.
Since specific acceptance criteria are not called out, I will present the reported performance characteristics for the new devices. The implicit acceptance criterion is "comparable performance to the predicate device."
| Performance Characteristic | COBAS INTEGRA Alkaline Phosphatase IFCC liquid (ALPL2 & ALPL6) (Proposed) | COBAS INTEGRA α-Amylase EPS Pancreatic (AMY-P / AMYUP) (Proposed) | COBAS INTEGRA C-Reactive Protein (Latex) (CRPLX) (Proposed) | Implicit Acceptance Criteria (Comparable to Predicate) |
|---|---|---|---|---|
| Intended Use | Quantitative determination of catalytic activity of alkaline phosphatase in serum and plasma | Quantitative determination of catalytic activity of pancreatic α-amylase in serum, plasma, and urine | Quantitative immunological determination of human C-reactive protein in serum and plasma | Must align with predicate device's intended use |
| Methodology | Enzymatic colorimetric using 4-Nitrophenylphosphate (IFCC) | Enzymatic colorimetric using substrate 4,6-ethylidene-p-nitrophenyl-α-D-malto-heptaoside | Particle enhanced immunoturbidimetric | Must be similar to or provide equivalent results to predicate device's methodology |
| Sample Type | Serum and Plasma | Serum, plasma, and urine | Serum and Plasma | Must be identical to predicate |
| Calibrator | Roche Calibrator (human) (K942706) | Roche Calibrator (human) (K942706) | CRP T Standard (K951595) | Must be compatible and provide comparable calibration to predicate |
| Controls | Roche Control Serum N and P (human) (K972214) | Roche Control Serum N and P (human) (K972214) | CRP T Control (K954992), CRP T N Control (Exempt) | Must be compatible and provide comparable control performance to predicate |
| Reagents | AMP in vial B (liquid); 4-Nitrophenylphosphate in vial C (liquid) | -enzyme, two monoclonal antibodies (mouse) in vial A (liquid); -substrate in vial C (liquid) | R1 BSA and immunoglobulins (mouse), vials A & B; R2 Latex particles coated with anti-CRP (mouse), vial C (liquid) | Must be chemically and functionally similar to predicate's reagents |
| Assay Range | 0-1500 U/L | Serum/Plasma and Urine: 0 - 1500 U/L | 0 - 160 mg/L | Similar or improved range compared to predicate |
| Sensitivity | 3.7 x 10^-4 ΔA/min per U/L of ALP | Serum/Plasma and Urine: 2.8 x 10^-4 ΔA/min per U/L of pancreatic α-amylase | 0.25 mg/L | Similar or improved sensitivity compared to predicate |
| Precision (Within-run %CV) | Level 1: 2.3; Level 2: 0.55 | Serum Level 1: 1.2; Serum Level 2: 0.91; Urine Level 1: 1.094; Urine Level 2: 0.8796 | Level 1: 1.8; Level 2: 1.5 | |
| (Second Set) Level 1: 2.0; Level 2: 2.4 | %CV values should be within acceptable clinical laboratory limits and comparable to predicate | |||
| Precision (Total %CV) | Level 1: 2.7; Level 2: 1.3 | Serum Level 1: 1.7; Serum Level 2: 1.6; Urine Level 1: 1.2; Urine Level 2: 1.1 | Level 1: 2.9; Level 2: 2.7 | |
| (Second Set) Level 1: 2.5; Level 2: 2.4 | %CV values should be within acceptable clinical laboratory limits and comparable to predicate | |||
| Accuracy (Corr. Coeff. (r)) | 0.999 | Serum: 0.999; Urine: 0.999 | 0.993 | Correlation coefficient should be high (close to 1), indicating strong agreement with predicate or reference method |
| Accuracy (Linear Regression) | 1.00x + 0.15 U/L | Serum: 1.03x + 0.3 U/L; Urine: 1.00x + 1.4 U/L | 1.07x - 6.2 mg/L | Slope should be close to 1 and y-intercept close to 0, indicating minimal bias relative to predicate or reference method |
2. Sample Size Used for the Test Set and Data Provenance
The "test set" in this context refers to the clinical samples used to evaluate the performance characteristics (precision and accuracy) of the new reagent cassettes.
-
COBAS INTEGRA Alkaline Phosphatase IFCC liquid (ALPL2 and ALPL6):
- Accuracy Sample Size (n): 252
- Data Provenance: Not specified, but generally for in vitro diagnostic (IVD) devices, these studies use patient samples collected in a clinical laboratory setting. The origin (country) and retrospective/prospective nature are not detailed in this summary.
-
COBAS INTEGRA α-Amylase EPS Pancreatic (AMY-P / AMYUP):
- Accuracy Sample Size (n):
- Serum: 246
- Urine: 106
- Data Provenance: Not specified, same general assumptions as above.
- Accuracy Sample Size (n):
-
COBAS INTEGRA C-Reactive Protein (Latex) (CRPLX):
- Accuracy Sample Size (n): 244
- Data Provenance: Not specified, same general assumptions as above.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
This information is not provided in the document. For IVD devices like these, "ground truth" for method comparisons is typically established by running the same samples on a legally marketed predicate device or a highly accurate reference method. It does not involve human expert consensus in the way image-based diagnostics might.
4. Adjudication Method for the Test Set
This is not applicable and therefore not provided. Adjudication methods like 2+1 or 3+1 are used in studies where human readers interpret data, and their disagreements need to be resolved. For quantitative chemical assays, the measurement itself is the "reader," and comparison is made to another assay.
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 is not applicable as the device is an in-vitro diagnostic reagent cassette for automated analyzers, not an AI or imaging device involving human readers.
6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was done
Yes, the performance data presented (assay range, sensitivity, precision, accuracy) represent the standalone performance of the reagent cassettes on the COBAS INTEGRA Analyzer. There is no human-in-the-loop component being evaluated for the measurement itself, only for the instrument's operation and result interpretation by laboratory personnel.
7. The Type of Ground Truth Used
For these types of in vitro diagnostic assays, the "ground truth" for the accuracy studies is implicitly established by comparing the results from the new device to those obtained from the legally marketed predicate device (or a recognized reference method). The correlation coefficients and linear regression data are direct comparisons to the predicate. For example, the accuracy section "Corr. Coefficient (r)" and "Linear regression" are direct comparisons between the proposed device and the cleared predicate device.
8. The Sample Size for the Training Set
This information is not provided and is likely not applicable in the same way it would be for an AI/ML device. For chemical reagents, "training" typically refers to the R&D and optimization phase to develop the reagent formulation and instrument application. It's not a discrete "training set" of patient data used to optimize an algorithm parameters that are then locked.
9. How the Ground Truth for the Training Set was Established
Similar to point 8, this is not provided and likely not applicable in the context of an AI/ML device. The "ground truth" during reagent development would involve analytical methods to confirm the chemical properties and performance of the reagents.
Ask a specific question about this device
(27 days)
The cassette COBAS INTEGRA Serum Barbiturates contains an in vitro diagnostic reagent system intended for use on the COBAS INTEGRA analyzer for the detection of barbiturates and their metabolites in human serum or heparinized plasma. This reagent system is intended for use in toxicological screenings where the analytical result is used in the management of barbiturate use or overdose.
The Abuscreen ONLINE Serum Barbiturates Calibrators are designed for calibration of the cassette COBAS INTEGRA Serum Barbiturates on the COBAS INTEGRA chemistry systems. The calibrators are used in the determination of values in the measurement of barbiturates in human specimens.
The cassette COBAS INTEGRA Serum Benzodiazepines contains an in vitro diagnostic reagent system intended for use on the COBAS INTEGRA analyzer for the detection of benzodiazepines and their metabolites in human serum or heparinized plasma. This reagent system is intended for use in toxicological screenings where the analytical result is used in the management of benzodiazepine use or overdose.
The Abuscreen ONLINE Serum Benzodiazepines Calibrators are designed for calibration of the cassette COBAS INTEGRA Serum Benzodiazepines on the COBAS INTEGRA chemistry systems. The calibrators are used in the determination of values in the measurement of benzodiazepines in human specimens.
The COBAS INTEGRA test applications contained in this submission are intended for use with the COBAS INTEGRA Analyzer, which is also known as the COBAS INTEGRA 700. The COBAS INTEGRA Analyzer and COBAS INTEGRA Reagent cassettes together provide an integrated system for in vitro diagnostic testing. The COBAS INTEGRA Analyzer utilizes three measuring principles, i.e., absorbance, fluorescence polarization and ion-selective electrodes. The analyzer has a throughput of up to 600 tests per hour with STAT samples prioritized and tested immediately. Random sample access, robotics and a user interface optimize time management and streamline workflow. The COBAS INTEGRA can store up to 68 COBAS INTEGRA Reagent Cassettes on board, 24 hours a day at 2-8°C. The COBAS INTEGRA Reagent Cassettes are compact and preparation-free with the added convenience of long term on-board stability. Barcode readers are used to identify newly loaded reagent cassettes, samples for patient identification, and rack inserts and to read calibration and control data from the cassette label. COBAS INTEGRA tests include chemistry, drugs of abuse, immunology, ion selective electrodes, therapeutic drug monitoring, and hematology reagents. Through this submission, it is the intention of Roche to gain clearance for two additional COBAS Reagent Cassettes and their associated calibrator sets. These are: the COBAS INTEGRA Serum Barbiturates (SBARB) Reagent Cassette, the Abuscreen ONLINE Serum Barbiturates Calibrators, the COBAS INTEGRA Serum Benzodiazepines (SBENZ) Reagent Cassette, and the Abuscreen ONLINE Serum Benzodiazepines Calibrators.
Here's an analysis of the acceptance criteria and study information for the Roche COBAS® INTEGRA Reagent Cassettes and Calibrators, based on the provided text:
Important Note: The provided document is a 510(k) Summary for a medical device cleared in 1998. It focuses on demonstrating substantial equivalence to predicate devices rather than establishing novel safety and effectiveness through a standalone, comprehensive clinical trial with pre-defined acceptance criteria in the way a new, high-risk device might today. The "acceptance criteria" detailed below are derived from the performance characteristics presented for comparison with the predicate device. The study is primarily a comparative effectiveness study against the predicate, alongside internal analytical validation.
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't explicitly state "acceptance criteria" in a pass/fail format with specific targets that the device must meet in a prospective study. Instead, it presents performance characteristics of the new device alongside those of its predicate for comparison, implying that the new device's performance should be comparable or substantially equivalent to the predicate. The "reported device performance" refers to the values presented for the COBAS INTEGRA system.
A. COBAS INTEGRA Serum Barbiturates (SBARB)
| Characteristic | Acceptance Criteria (Implied from Predicate) | Reported Device Performance (COBAS INTEGRA SBARB) |
|---|---|---|
| Intended Use | Detection of barbiturates/metabolites in human serum/plasma for toxicological screening, diagnosis, and treatment of use/overdose. | Detection of barbiturates/metabolites in human serum/heparinized plasma for toxicological screening, management of use/overdose. |
| Methodology | Fluorescence polarization | Fluorescence polarization |
| Sample Type | Serum and Plasma | Serum and Plasma |
| Assay Range | 0.70 - 40 µg/mL | 0.03 - 4 µg/mL (0.03 - 80 µg/mL with postdilution) |
| Cutoff Conc. | 2.0 µg/mL | 0.5 µg/mL |
| Sensitivity | 0.07 µg/mL | 0.03 µg/mL |
| Precision (Within-run % CV) | Level 1: 3.18%, Level 2: 3.47%, Level 3: 4.38% | Level 1: 4.1%, Level 2: 4.1%, Level 3: 2.3% |
| Precision (Total % CV) | Level 1: 4.00%, Level 2: 3.92%, Level 3: 4.73% | Level 1: 5.0%, Level 2: 4.2%, Level 3: 2.9% |
| Accuracy (Agreement vs GC/MS) | 79 positive, 14 negative (total 93 cases) | 37 positive, 10 negative (total 47 cases) |
| Reproducibility (Agreement vs Predicate ADX) | 69 positive, 123 negative | 35 positive, 12 negative |
B. COBAS INTEGRA Serum Benzodiazepines (SBENZ)
| Characteristic | Acceptance Criteria (Implied from Predicate) | Reported Device Performance (COBAS INTEGRA SBENZ) |
|---|---|---|
| Intended Use | Detection of benzodiazepines/metabolites in human serum/plasma for toxicological screening, diagnosis, and treatment of use/overdose. | Detection of benzodiazepines/metabolites in human serum/heparinized plasma for toxicological screening, management of use/overdose. |
| Methodology | Fluorescence polarization | Fluorescence polarization |
| Sample Type | Serum and Plasma | Serum and Plasma |
| Assay Range | 12 - 1000 ng/mL | 3 - 200 ng/mL (3 - 2000 ng/mL with postdilution) |
| Cutoff Conc. | 12.0 ng/mL | 3 ng/mL |
| Sensitivity | 12.0 ng/mL | 3 ng/mL |
| Precision (Within-run % CV) | Level 1: 3.19%, Level 2: 1.86%, Level 3: 3.41% | Level 1: 5.5%, Level 2: 1.9%, Level 3: 1.1% |
| Precision (Total % CV) | Level 1: 4.98%, Level 2: 3.73%, Level 3: 5.98% | Level 1: 5.4%, Level 2: 2.7%, Level 3: 2.0% |
| Accuracy (Agreement vs GC/MS) | 76 positive, 38 negative (total 114 cases) | 46 positive, 28 negative (total 74 cases) |
| Reproducibility (Agreement vs Predicate TDX) | 76 positive, 83 negative | 46 positive, 20 negative |
2. Sample Size Used for the Test Set and the Data Provenance
-
COBAS INTEGRA Serum Barbiturates (SBARB):
- Accuracy (compared to GC/MS): 47 samples (37 positive, 10 negative)
- Accuracy (compared to Predicate ADX): 47 samples (35 positive, 12 negative)
- Precision: Not explicitly stated, but typically involves multiple replicates across several runs for each level tested. Given the three levels and %CV calculation, a common practice would be 20 replicates for 2-3 levels over 2-3 days, resulting in at least 40-60 measurements per level. The exact number of individual patient samples used to derive these mean and CV values is not specified, but these are typically control or spiked samples.
- Data Provenance: Not explicitly stated (e.g., country of origin). The studies appear to be retrospective analytical performance evaluations conducted by the manufacturer as part of the submission to demonstrate equivalence.
-
COBAS INTEGRA Serum Benzodiazepines (SBENZ):
- Accuracy (compared to GC/MS): 74 samples (46 positive, 28 negative)
- Accuracy (compared to Predicate TDX): 66 samples (46 positive, 20 negative)
- Precision: Similar to SBARB, not explicitly stated, but common practice would imply multiple replicates for each of the three levels tested.
- Data Provenance: Not explicitly stated. Likely retrospective analytical performance evaluation.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts
- For both assays (Barbiturates and Benzodiazepines), the ground truth for accuracy was established using GC/MS (Gas Chromatography/Mass Spectrometry). GC/MS is considered a "gold standard" analytical method for drug confirmation and quantification in toxicology.
- The document does not specify the number of human experts involved in interpreting the GC/MS results or their qualifications. The interpretation of GC/MS data is typically performed by trained laboratory personnel (e.g., analytical chemists, toxicologists) within a certified laboratory environment.
4. Adjudication Method for the Test Set
- For the accuracy studies using GC/MS as the ground truth, there is no mention of an adjudication method in the traditional sense (e.g., 2+1 physician review). The GC/MS result itself serves as the definitive determination. Discrepancies between the device and GC/MS would be investigated analytically rather than through expert consensus on the clinical classification.
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
- No, an MRMC comparative effectiveness study was not done. This submission concerns in vitro diagnostic (IVD) reagent assays, which are standalone laboratory tests, not imaging devices or AI-assisted diagnostic tools that involve human readers. Therefore, the concept of "human readers improving with AI assistance" is not applicable here.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
- Yes, this entire submission effectively represents a standalone performance evaluation. The COBAS INTEGRA system, with these reagent cassettes, performs automated analysis. Its performance characteristics (precision, accuracy, sensitivity, assay range, cutoff) are measured directly based on the analytical results produced by the instrument and reagents, without immediate human intervention in the result generation itself. Human interaction would occur in sample loading, result review, and clinical interpretation.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
- The primary ground truth for the accuracy claims was:
- GC/MS (Gas Chromatography/Mass Spectrometry): This is a highly specific and sensitive analytical method for confirming and quantifying drugs, serving as the gold standard in toxicology for this type of test.
8. The Sample Size for the Training Set
- The document does not specify the sample size for a training set. For IVD assays based on established chemical principles (like fluorescence polarization immunoassay), there isn't a "training set" in the same way there would be for a machine learning or AI algorithm. The assay's parameters (e.g., antibody concentrations, reaction times, calibration curves) are developed and optimized by the manufacturer using internal R&D processes, but these are not explicitly detailed as a "training set" in the context of this 510(k) summary. The performance data presented are for the final, developed product.
9. How the Ground Truth for the Training Set Was Established
- As a "training set" is not explicitly mentioned or applicable in the AI/machine learning sense for this device, the question of how its ground truth was established is not directly answerable from the provided text. The development and optimization of such assays rely on well-characterized samples (e.g., spiked samples, confirmed positive/negative clinical samples, reference materials) to establish robust analytical performance, but these are part of the R&D process rather than a formalized "training set" with ground truth in the context of this regulatory submission.
Ask a specific question about this device
(80 days)
The cassette Roche COBAS INTEGRA Carbon Dioxide (CO2-S) contains an in vitro diagnostic reagent system intended for use on COBAS INTEGRA for the quantitative determination of the carbon dioxide concentration in serum and plasma. Determination of carbon dioxide concentration in blood is most commonly performed as an initial test in the cvaluation of the body's ability to control blood pH by appropriate removal of metabolism byproducts via the lung and kidneys.
The cassette Roche COBAS INTEGRA Glucose HK Liquid contains an in vitro diagnostic reagent system intended for use on the COBAS INTEGRA for the quantitative determination of the glucose concentration in serum, plasma, urine and cerebrospinal fluid (CSF). In addition, an optional glucose "fast application" for serum and plasma is available. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus and idiopathic hypoglycemia.
The COBAS INTEGRA test applications contained in this submission are intended for use with the COBAS INTEGRA Analyzer. The COBAS INTEGRA Analyzer and COBAS INTEGRA Reagent cassettes together provide an integrated system for in vitro diagnostic testing. The COBAS INTEGRA Analyzer utilizes three measuring principles, i.e., absorbance, fluorescence polarization and ion-selective electrodes. The analyzer has a throughput of up to 600 tests per hour with STAT samples prioritized and tested immediately. Random sample access, robotics and a user interface optimize time management and streamline workflow. The COBAS INTEGRA can store up to 68 COBAS INTEGRA Reagent Cassettes on board, 24 hours a day at 2-8℃. The COBAS INTEGRA Reagent Cassettes are compact and preparation-free with the added convenience of long term on-board stability. Barcode readers are used to identify newly loaded reagent cassettes, samples for patient identification, and rack inserts and to read calibration and control data from the cassette label. COBAS INTEGRA tests include chemistry, drugs of abuse, immunology, ion selective electrodes, therapeutic drug monitoring, and hematology reagents.
The provided text describes two devices, COBAS INTEGRA Carbon Dioxide (CO2-S) and COBAS INTEGRA Glucose HK Liquid (GLULF), in a 510(k) submission. Here's an analysis of the acceptance criteria and supporting studies for each:
Device 1: COBAS INTEGRA Carbon Dioxide (CO2-S)
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state "acceptance criteria." However, substantial equivalence is determined by comparing the performance characteristics of the proposed device against a legally marketed predicate device. The values presented for the proposed device imply the performance achieved for each characteristic, and the aim is to demonstrate that these are equivalent to or better than the predicate.
| Performance Characteristic | Acceptance Criteria (Predicate) | Reported Device Performance (CO2-S) |
|---|---|---|
| Assay Range | 0 - 40 mmol/L | 0 - 50 mmol/L |
| Sensitivity | $5.2 \times 10^{-2} \Delta A$ per mmol/L | $1.5 \times 10^{-2} \Delta A$ per mmol/L |
| Precision: | ||
| Level 1 Mean (mmol/L) | 18.9 | 19.5 |
| Level 2 Mean (mmol/L) | 33.0 | 33.8 |
| % CV (within-run) | Level 1: 1.2; Level 2: 1.1 | Level 1: 1.1; Level 2: 1.2 |
| % CV (total) | Level 1: 2.5; Level 2: 1.9 | Level 1: 3.1; Level 2: 2.5 |
| Accuracy: | ||
| Sample size (n) | 200 | 220 |
| Corr. Coefficient (r) | 0.997 | 0.999 |
| Linear Regression | 1.04x + 0.4 mmol/L | 1.01x - 0.8 mmol/L |
Note: The reported sensitivity for the proposed device (1.5 x 10^-2 ΔA per mmol/L) is lower than the predicate (5.2 x 10^-2 ΔA per mmol/L). In immunoassay terms, a lower ΔA indicates lower sensitivity, which could be a point of divergence. However, the FDA's clearance implies that the overall performance was deemed substantially equivalent, often considering the clinical impact and other strong performance metrics like accuracy and precision. The assay range of the proposed device is wider, which is generally an improvement. The precision and accuracy metrics are comparable or slightly better in some aspects for the proposed device.
2. Sample size used for the test set and the data provenance
- Sample size for accuracy test set (n): 220
- Data provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective). The document uses generic terms like "clinical and nonclinical studies." Given the context of a 510(k) submission to the US FDA, it's highly probable the data was collected under controlled conditions to support regulatory approval, likely in a prospective manner, but this is not explicitly confirmed.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. This is an in vitro diagnostic device measuring a quantitative analyte. The "ground truth" (or reference values) for comparison are established by a reference method or legally marketed predicate device, not by expert interpretation of images or other qualitative data. Therefore, no experts were used in this manner.
4. Adjudication method for the test set
Not applicable for this type of in vitro diagnostic device. Adjudication methods like 2+1 or 3+1 are typically used for qualitative assessments, often in imaging studies where multiple readers interpret results and discrepancies need resolution. For quantitative measurements, comparisons are made against established reference methods or predicate devices.
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 not an AI/imaging device. It is an in vitro diagnostic reagent system for quantitative determination of a chemical analyte.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
Yes, the performance characteristics provided (assay range, sensitivity, precision, accuracy) represent the standalone performance of the COBAS INTEGRA Carbon Dioxide (CO2-S) reagent on the COBAS INTEGRA Analyzer. This is typical for in vitro diagnostic devices where the analytical performance of the assay itself is validated.
7. The type of ground truth used
The ground truth for the analytical accuracy (correlation and linear regression) is based on comparison against a reference method or a predicate device. The linearity and correlation coefficients indicate how well the proposed device's measurements align with these established methods. The predicate device "COBAS INTEGRA Carbon Dioxide (CO2)" (K954992) serves as the primary comparator.
8. The sample size for the training set
Not provided. For in vitro diagnostic devices like this, there isn't typically a "training set" in the machine learning sense. Method development and optimization (which might be analogous to training) would involve various samples, but the specific number is not disclosed in the 510(k) summary, which focuses on validation/test data.
9. How the ground truth for the training set was established
Not applicable as there is no explicitly defined "training set" with ground truth in the traditional sense for this type of device in the provided document. Method development and optimization would use samples with known CO2 concentrations, but the specific process for establishing these values for internal development is not detailed.
Device 2: COBAS INTEGRA Glucose HK Liquid (GLULF) (fast application)
1. Table of Acceptance Criteria and Reported Device Performance
Similar to CO2-S, the document presents performance characteristics for the proposed GLULF "fast application" in comparison to its predicate (standard application).
| Performance Characteristic | Acceptance Criteria (Predicate) | Reported Device Performance (GLULF - fast application) |
|---|---|---|
| Assay Range | 0 - 40 mmol/L | 0 - 30 mmol/L |
| Sensitivity | $5.4 \times 10^2 \Delta A$ per mmol/L | $5.4 \times 10^2 \Delta A$ per mmol/L |
| Precision: | ||
| Level 1 Mean (mmol/L) | 5.3 | 4.7 |
| Level 2 Mean (mmol/L) | 33.2 | 27.7 |
| % CV (within-run) | Level 1: 1.7; Level 2: 0.72 | Level 1: 1.4; Level 2: 0.5 |
| % CV (total) | Level 1: 2.6; Level 2: 1.5 | Level 1: 2.4; Level 2: 1.2 |
| Accuracy: | ||
| Sample size (n) | 220 | 216 |
| Corr. Coefficient (r) | 0.999 | 0.999 |
| Linear Regression | 1.05x - 0.2 mmol/L | 0.99x + 0.01 mmol/L |
Note: The reported assay range for the "fast application" is narrower (0-30 mmol/L) compared to the standard application (0-40 mmol/L). However, precision for the fast application appears slightly better (lower %CVs), and the sensitivity is identical. The accuracy metrics (correlation coefficient and linear regression) are highly comparable, indicating substantial equivalence in performance for the intended use and specified range.
2. Sample size used for the test set and the data provenance
- Sample size for accuracy test set (n): 216
- Data provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective). Similar to CO2-S, the data would likely be from controlled studies, presumably prospective, but this is not explicitly confirmed.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. This is an in vitro diagnostic device measuring a quantitative analyte. The "ground truth" for comparison is established by a reference method or legally marketed predicate device.
4. Adjudication method for the test set
Not applicable for this type of in vitro diagnostic 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
Not applicable. This is not an AI/imaging device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, the performance characteristics provided represent the standalone analytical performance of the COBAS INTEGRA Glucose HK Liquid (GLULF) fast application reagent on the COBAS INTEGRA Analyzer.
7. The type of ground truth used
The ground truth for the analytical accuracy is based on comparison against a reference method (enzymatic reference method with hexokinase) or a predicate device (COBAS INTEGRA Glucose HK Liquid - standard application, K972250).
8. The sample size for the training set
Not provided. Similar to CO2-S, "training set" in the machine learning sense is not applicable or detailed in the document.
9. How the ground truth for the training set was established
Not applicable as there is no explicitly defined "training set" with ground truth in the traditional sense for this type of device in the provided document. Method development and optimization would use samples with known glucose concentrations, but the specific process for establishing these values for internal development is not detailed.
Ask a specific question about this device
Page 1 of 2