Search Results

The ABX MICROS 60 Hematology Analyzer is a fully automated (microprocessor controlled) hematology analyzer used for the in vitro diagnostic testing of whole blood specimens or blood cell concentrates. It operates in complete blood count (CBC) mode.

The ABX MICROS 60 device is a benchtop, clinical laboratory instruments that analyze in-vitro samples of whole blood specimens. The device operates in a complete blood count (CBC) and 3 part DIFF (LMG). As either a closed tube / closed system (CT/CS) or open tube/open system (OT/OS). The ABX MICROS 60 can evaluate 5,8, 16 or 18 hematology parameters depending on its internal configuration.

Here's a summary of the acceptance criteria and study information for the ABX MICROS 60 Hematology Analyzer based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document primarily discusses that the device met acceptance criteria, but specific quantitative criteria for each parameter are not explicitly detailed in a separate table. Instead, general statements about meeting guidelines and correlations are provided.

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

• Sample Size for Test Set: Not explicitly stated. The document mentions "clinical data provided in this submission" and "clinical studies," but no specific sample size (number of patients or specimens) is given for the test set used to evaluate linearity and accuracy.
• Data Provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective).

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

• Number and Qualifications of Experts: Not mentioned. For a hematology analyzer, ground truth typically refers to reference methods performed by trained laboratory personnel or comparison to a predicate device. The document states "Accuracy (Inter-procedural Correlation) demonstrated no evidence of significant bias between the MICROS 60 and the Abbott CD 4000," implying the Abbott CD 4000 served as the reference/ground truth for accuracy assessment.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable or not described. This type of adjudication is more common in studies involving subjective interpretation (e.g., medical imaging reads). For an automated hematology analyzer, performance is typically assessed by comparing its quantitative results against a reference method.

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

• MRMC Study: No, an MRMC study was not done. This type of study would involve human readers interpreting cases with and without AI assistance, which is not relevant for an automated hematology analyzer like the ABX MICROS 60. The device performs automated analysis without human interpretation in the loop.

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

• Standalone Performance: Yes, the entire performance evaluation described is for the device in standalone mode. The ABX MICROS 60 is an "automated cell counter and automated differential cell counter" and a "fully automated (microprocessor controlled) multi-parameter hematology analyzer." The performance data presented (precision, linearity, accuracy) are for the device operating independently.

7. The Type of Ground Truth Used:

• Ground Truth Type:
  • For precision and linearity, the ground truth would typically be established by repeated measurements on stable samples and statistical analysis to ensure reproducibility and accurate measurement across concentration ranges.
  • For accuracy (inter-procedural correlation), the ground truth was established by comparison to a legally marketed predicate device, the ABBOTT CD 4000 (K961439).

8. The Sample Size for the Training Set:

• Training Set Sample Size: Not applicable or not stated. Hematology analyzers like the ABX MICROS 60 typically rely on established physical principles (e.g., impedance, optical scattering) and calibrated reagents rather than machine learning algorithms trained on a dataset. Therefore, the concept of a "training set" in the context of AI/ML is not directly relevant here. The device is "based on the same fundamental technology" as predicate devices.

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

• Training Set Ground Truth Establishment: Not applicable, as there isn't a "training set" in the AI/ML sense. The device's operation is based on established scientific principles rather than being trained on a dataset.

Ask a specific question about this device

The ABX PENTRA 60 and 60C+ Hematology Analyzer are fully automated (microprocessor controlled) hematology analyzer used for the in vitro diagnostic testing of whole blood specimens.

The ABX PENTRA 60 and 60C+ Hematology Analyzer are able to operate either in complete blood count (CBC) mode or in CBC + 5 differential leucocyte count (5DIFF) mode.

The ABX PENTRA 60 & PENTRA 60C+ are benchtop, clinical laboratory instrument which analyzes in-vitro samples of whole blood to provide complete blood count and leucocyte differential count using principles of cytochemistry, focused flow impedance and light transmission using a halogen light source.

The PENTRA 60 is an standalone device using a keyboard and LCD screen integrated into the device. Whereas the PENTRA 60C+ is the PENTRA 60 connected to a dedicated workstation with user interfacing software.

The ABX PENTRA 60 and PENTRA 60C+ Hematology Analyzers underwent a study to demonstrate their performance against pre-defined acceptance criteria, primarily focusing on expanded linearity ranges and maintaining accuracy.

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

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

The ABX PENTRA 80 Hematology Analyzer is a fully automated (microprocessor controlled) hematology analyzer used for the in vitro diagnostic testing of whole blood specimens.

The ABX PENTRA 80 is able to operate either in complete blood count (CBC) mode or in CBC + 5 differential leucocyte count (5DIFF) mode.

The PENTRA 80 Hematology analyzer is a benchtop, clinical laboratory instrument which analyzes in-vitro samples of whole blood to provide complete blood count and leucocyte differential count using principles of cytochemistry, focused flow impedance and light transmission using a halogen light source. The instrument is microprocessor driven, with an internal PC that performs further data processing and hosts the user interface.

The provided text describes the ABX PENTRA 80 Hematology Analyzer and its performance in a 510(k) premarket notification. However, it does not contain a detailed table of acceptance criteria or performance metrics with specific numerical values for a direct comparison. The information is presented in a narrative format, highlighting that the device met certain standards and showed good correlation with a predicate device.

Here's an attempt to extract the requested information based on the available text:

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

The ABX PENTRA 120 Hematology Analyzer is an automated hematology analyzer providing complete blood count (CBC) and differential leucocyte count (DIFF) for the in vitro diagnostic use in clinical laboratories.

The ABX PENTRA 120 RETIC Hematology Analyzer is an automated hematology analyzer providing complete blood count (CBC), differential leucocyte count (DIFF) as well as reticulocyte count (RET) for the in vitro diagnostic use in clinical laboratories. The clinical use in the ABX PENTRA 120 RETIC Hematology Analyzer of the reticulocyte count, specifically the immature reticulocyte fraction (IRF), is to monitor erythropoietic activity in patients.

The option of the SPS (Slide Preparation System) smears and stains on a clean microscope slide.

The PENTA 120 / P120 RETIC Automated Hematology Analyzer is a bench-top, clinical laboratory instrument which analyzes in-vitro samples of whole blood to provide complete blood count, leukocyte differential count and reticulocyte count using principles of cytochemistry, focused flow impedance, light absorbance and fluorescence. The instrument is microprocessor driven.

Controlled by the PENTRA 120 the optional device SPS (Slide Preparation System) smears and stains the slides.

Here's a breakdown of the acceptance criteria and study information for the ABX PENTRA 120/120 RETIC Hematology Analyzer and its SPS option, based on the provided text:

Acceptance Criteria and Reported Device Performance

The document describes improvements to the device, specifically the increase of linearity ranges for White Blood Cell (WBC) and Platelet (PLT) counts. For the SPS (Slide Preparation System), the focus was on the correlation of results between manual and automated methods.

Device Performance for ABX PENTRA 120/120 RETIC:

Device Performance for SPS (Slide Preparation System):

General Acceptance:

• Clinical testing met all acceptance criteria.
• The device meets the IEC 1010-1 standard for electrical equipment for measurement, control, and laboratory use.
• All clinical and non-clinical tests show appropriate levels of safety and effectiveness.

Study Details

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

   • Sample Size: Not explicitly stated for specific tests (e.g., how many samples were used for linearity assessment, imprecision, or accuracy). The document mentions "all WBC results compared" and "all platelet results compared," suggesting a comprehensive comparison across the tested range.
   • Data Provenance: Not specified (e.g., country of origin, specific hospitals). The studies are described as "clinical testing." "Retrospective or prospective" is not mentioned.

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

   • Not mentioned. For automated hematology analyzers, ground truth often comes from established predicate devices and internal validation standards (e.g., reference methods, manual microscopy by trained professionals). For the SPS, the "manual method" served as the comparison, implying human expert evaluation.

3. Adjudication method for the test set:

   • Not mentioned.

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

   • No, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or described. This type of study is more common for diagnostic imaging AI systems where human interpretation is a primary output. The ABX PENTRA is an automated analyzer, and the SPS automates slide preparation, not interpretation.

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

   • Yes, the performance data presented (linearity, imprecision, accuracy) for the ABX PENTRA 120/120 RETIC represents the standalone performance of the algorithm/instrument. For the SPS, its function is automated slide preparation, which is inherently a "standalone" or automated process that is then evaluated against a manual process.

6. The type of ground truth used:

   • For the ABX PENTRA 120/120 RETIC (WBC and PLT counts): The ground truth was established by comparison to predicate devices (ABBOTT CD 4000 for leukocytes and BAKER 9110 Plus for platelets), which are considered established and accurate methods. Linearity data was "generated according to FDA guidelines," implying recognized reference standards.
   • For the SPS: The ground truth was the "manual method" of smearing and staining slides, which would involve human expertise in microscopy for evaluation.

7. The sample size for the training set:

   • Not mentioned. As this is an automated analyzer dealing with fundamental blood cell counts and not a machine learning model in the contemporary sense, the concept of a distinct "training set" for algorithm development as seen in AI is not directly applicable in the same way. The device is likely calibrated and validated through engineering and typical quality control samples.

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

   • Not applicable in the context of "training set" for an AI model. For general instrument calibration and validation, ground truth would be established using reference materials, assayed controls, and comparisons to established, highly accurate (often manual or predicate) methods.

Ask a specific question about this device

The ABX MICROS 60 Hematology Analyzer is a fully automated (microprocessor controlled) hematology analyzer used for the in vitro diagnostic testing of whole blood specimens or blood cell concentrates. It operates in complete blood count (CBC) mode.

The ABX MICROS 60 Hematology Analyzer is a bench top clinical laboratory instrument which analyzes in vitro samples of whole blood to provide complete blood count data using principles of cytochemistry, focused flow impedance, and light transmission technology. The system is equipped with automatic calibration; Automated smart cards based for: calibration, QC with 93 multiple range files and memory with 60 erasable results.

Here's an analysis of the provided text regarding the acceptance criteria and study for the ABX MICROS 60 Hematology Analyzer:

Due to the nature of the provided document (a 510(k) summary for a legacy device from 2001), some of the requested information (especially regarding modern AI/ML study practices like multi-reader multi-case studies, detailed ground truth establishment for training, or specific acceptance criteria tables with numerical thresholds) is not explicitly present in the document. The document focuses on demonstrating substantial equivalence to a predicate device and broadly describing performance, rather than detailing a rigorous, pre-defined acceptance criteria study in the way a modern AI/ML device would.

However, I will extract and present all available information and highlight what is missing based on your request.

Acceptance Criteria and Device Performance Study for ABX MICROS 60 Hematology Analyzer

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria in a table format. Instead, it describes performance characteristics and concludes that they are "acceptable" or "highly correlated." The predicate device comparison implies that the ABX MICROS 60 performance should be at least comparable to the BAKER SYSTEM 9110* PLUS.

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

The document does not specify the sample size used for the test set. It mentions testing a "high level control 10 times in succession on a single day" for precision, but this is not the full test set.

The data provenance is also not explicitly stated. It can be inferred that the testing was conducted prospectively as part of the device development and submission process. The country of origin of the data is not mentioned, but given the company's US address (Irvine, CA), it is likely to be from the USA.

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 a hematology analyzer measuring objective parameters like cell counts, the "ground truth" would typically be established by established reference methods, manual microscopy by trained laboratory personnel, or internal laboratory standards and controls, rather than a panel of "experts" in the context of image interpretation.

4. Adjudication Method for the Test Set

This information is not applicable/provided. Adjudication methods (like 2+1, 3+1) are typically used for subjective assessments (e.g., image interpretation by multiple readers) to establish a consensus ground truth. For an automated hematology analyzer measuring numerical parameters, the "ground truth" would likely come from an objective reference method or a reference instrument, not through human adjudication of differing interpretations.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This type of study (comparing human readers with and without AI assistance) is relevant for AI/ML devices where the algorithm interacts with human interpretation. The ABX MICROS 60 is a standalone automated analyzer, not an AI-assisted diagnostic tool.

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

Yes, the study described is a standalone performance study. The ABX MICROS 60 Hematology Analyzer is an automated device designed to measure parameters directly. The performance data presented (precision, linearity, correlation, carry-over) reflects the direct output of the instrument without human intervention in the primary measurement process itself.

7. The Type of Ground Truth Used

The ground truth for this device would have been established through a combination of:

• Reference Methods: Comparison to established standard laboratory methods for cell counting. While not explicitly stated, this is standard practice.
• Predicate Device Comparison: The study explicitly mentions correlation with the BAKER SYSTEM 9110+ PLUS, which serves as a type of "ground truth" or reference for establishing substantial equivalence.
• Calibrators and Controls: Mention of "high level control" indicates the use of known reference materials.

Pathology reports or outcomes data are generally not the direct ground truth for individual numerical cell counts from a hematology analyzer, although clinical outcomes can validate the utility of the parameters measured. Expert consensus is also less direct for objective numeric measurements, compared to subjective interpretations.

8. The Sample Size for the Training Set

The document does not mention a "training set". This term is primarily associated with machine learning or artificial intelligence devices that are trained on data. The ABX MICROS 60, being a 2001 device, is a classical, rule-based or impedance-based instrument, not an AI/ML device that undergoes a training phase in the modern sense. Its development would have involved extensive calibration and internal validation rather than training on a separate dataset.

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

As there is no mention of a "training set" in the context of an AI/ML device, this question is not applicable to the information provided. The "ground truth" for the development and calibration of such a device would have been established through traditional laboratory methods, reference instruments, and certified control materials during its engineering and validation phases.

Ask a specific question about this device

Ask a specific question about this device

Ask a specific question about this device

The ABX PENTRA 60™ Hematology Analyzer is a fully automated (microprocessor controlled) hematology analyzer used for the in vitro diagnostic testing of whole blood specimens. The ABX PENTRA 60™ is able to operate either in complete blood count (CBC) mode or in CBC + 5 differential leucocyte count (5DIFF) mode.

The ABX PENTRA 60™ Hematology Analyzer is a benchtop, clinical laboratory instrument which analyzes in-vitro samples of whole blood to provide complete blood count and leucocyte differential count using principles of cytochemistry, focused flow impedance and light transmission using a halogen light source. The instrument is microprocessor driven.

The document describes the ABX PENTRA 60™ Hematology Analyzer and its comparison to a predicate device, the VEGA Hematology Analyzer (K962633), to establish substantial equivalence.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly define "acceptance criteria" in a quantitative table format with specific thresholds (e.g., "accuracy > 95%"). Instead, it describes performance studies demonstrating comparability to the predicate device. The primary "acceptance criterion" appears to be substantial equivalence to the predicate device, demonstrated through various performance evaluations.

2. Sample Sizes used for the Test Set and Data Provenance:

• Sample Size for Clinical Comparison:
  • 105 clinical specimens from patients with normal complete blood count.
  • 104 clinical specimens from patients with at least one parameter outside the normal range.
  • Total:* 209 human blood samples for predicate device comparison.
• Sample Size for Linearity/Sensitivity and Carry-over: "Commercially available low range and high (full) range specimens." (Number not specified)
• Sample Size for Precision: "Three commercially available control specimens having leukocytes, erythrocytes, platelets, and hemoglobin the low, normal and high range." (Number of runs/days not specified)
• Data Provenance: "Human blood samples" and "clinical specimens." The country of origin is not explicitly stated, but the company is based in Irvine, CA, suggesting the samples were likely from the US, though this is not confirmed. The study appears to be retrospective in the sense that the samples were already collected and then analyzed on both devices, or prospective in analyzing new samples on both. Given the phrasing, it's more likely a direct comparison study on a set of clinical samples.

3. Number of Experts used to establish the ground truth for the test set and their qualifications:

The document does not mention the use of experts to establish ground truth for the test set in the traditional sense of diagnostic image interpretation. The "ground truth" for hematology analyzers is typically considered the reference method or the predicate device's results, which are themselves subject to established clinical laboratory standards. There is no mention of radiologists, pathologists, or other human experts manually reviewing the blood samples to establish a "ground truth" against which the device's performance was compared beyond the predicate device.

4. Adjudication Method for the test set:

Not applicable in the context of this device. Adjudication methods (like 2+1, 3+1) are typically used for interpreting subjective findings like medical images where human consensus is needed to establish ground truth for an AI system. For a hematology analyzer, the comparison is against the predicate device's quantitative results or established control values.

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 a standalone diagnostic laboratory instrument, not an AI-assisted interpretation tool for human readers. Therefore, an MRMC study examining reader improvement with AI assistance was not performed.

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

Yes, this entire study describes the standalone performance of the ABX PENTRA 60™ Hematology Analyzer. It is an automated instrument that provides complete blood count and leukocyte differential count without direct human interpretation of individual cellular images or raw data. The "algorithm" here refers to the device's inherent cytochemistry, flow impedance, and light transmission principles, and its microprocessor-driven analysis.

7. The type of ground truth used:

The primary "ground truth" used for establishing substantial equivalence was:

• Predicate Device Performance: The results from the CE-cleared VEGA Hematology Analyzer (K962633). The ABX PENTRA 60™'s performance was compared directly to this device for various hematological indices.
• Commercially Available Controls/Specimens: Used for evaluating linearity, carry-over, and precision. These controls have known or expected values.

8. The sample size for the training set:

The document does not specify a separate training set or details about how the internal algorithms of the ABX PENTRA 60™ were trained. This is typical for a 510(k) summary for a traditional laboratory instrument, where the focus is on the validation of the final product's performance against a predicate and established methods rather than detailing the internal development/training of the proprietary analytical methods.

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

Since a training set is not explicitly mentioned or detailed, the method for establishing its "ground truth" is also not described. The instrument's underlying principles (cytochemistry, flow impedance, light transmission) are well-established analytical techniques in hematology, rather than a machine learning model that requires explicit "ground truth" labeling during a training phase in the AI sense.

Ask a specific question about this device

The ABX PENTRA 120 RETIC Automated Hematology Analyzer is an automated hematology analyzer providing complete blood count (CBC), differential leucocyte count (DIFF) as well as reticulocyte count for in vitro diagnostic use in clinical laboratories. The ABX PENTRA 120 RETIC Automated Hematology Analyzer provides appropriate flags and alarms to assist users in final checking and identification of abnormal cell populations.

The clinical use of the reticulocyte count, specifically the immature reticulocyte fraction (IRF), is to monitor erythropoietic activity in patients.

The ABX PENTRA 120 RETIC Automated Hematology Analyzer is a benchtop, clinical laboratory instrument which analyzes in-vitro samples of whole blood to provide complete blood count, leucocyte differential count and reticulocyte count using principles of cytochemistry, focused flow impedance, light scattering, and fluorescence. The instrument is microprocessor driven.

The provided 510(k) summary for the ABX PENTRA 120 RETIC Automated Hematology Analyzer describes its performance against a predicate device, rather than explicit acceptance criteria and device performance in a table format. However, the document states that "All studies confirmed that the IRF clinical parameter of the ABX PENTRA 120 RETIC Automated Hematology Analyzer is substantially equivalent to the Sysmex IRF clinical parameter."

Here's an attempt to structure the information based on your request, acknowledging that specific numerical acceptance criteria and reported performance values are not detailed in this document.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Size: 203 patients.
  • 100 patients with normal reticulocyte counts.
  • 103 patients with abnormal reticulocyte counts.
• Data Provenance: Retrospective or prospective is not explicitly stated. The study involved "whole blood samples from 100 patients with normal reticulocyte counts and 103 patients with abnormal counts." The country of origin is not specified but is presumably where the clinical study was conducted.

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

This information is not provided in the document. The comparison is made against the Sysmex R-3000 analyzer, which serves as the reference, rather than against expert-established ground truth.

4. Adjudication Method for the Test Set

Not applicable. The study compares the device's output directly to a predicate device (Sysmex R-3000 analyzer), not against expert adjudication of individual cases.

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

Not applicable. This is a study comparing an automated hematology analyzer to a predicate device, not an MRMC study involving human readers with and without AI assistance.

6. Standalone Performance Study (Algorithm Only)

Yes, a standalone study was performed. The "Discussion of Performance Data" describes a clinical study where "samples were processed in the ABX PENTRA 120 RETIC Automated Hematology Analyzer and the SYSMEX R-3000 analyzer." This indicates the performance of the ABX PENTRA 120 RETIC as an automated system.

7. Type of Ground Truth Used

The "ground truth" for the performance study establishing substantial equivalence was the results obtained from a legally marketed predicate device, the Sysmex R-3000 analyzer, specifically its IRF parameter.

8. Sample Size for the Training Set

The document does not specify a separate training set. The performance data discussed relates to a clinical study used to demonstrate substantial equivalence, implying it was the main "test set" for this purpose.

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

As no separate training set is mentioned, this information is not provided. The comparison was against the predicate device.

Ask a specific question about this device

The VEGA RETIC Automated Hematology Analyzer is an automated hematology analyzer providing complete blood count (CBC), differential leucocyte count (DIFF) as well as reticulocyte count for in vitro diagnostic use in clinical laboratories. The VEGA RETIC Automated Hematology Analyzer provides appropriate flags and alarms to assist users in final checking and identification of abnormal cell populations.

The VEGA RETIC Automated Hematology Analyzer is a benchtop, clinical laboratory instrument which analyzes in-vitro samples of whole blood to provide complete blood count, leucocyte differential count and reticulocyte count using principles of cytochemistry, focused flow impedance, light scattering, and fluorescence. The instrument is microprocessor driven.

The provided text describes the VEGA RETIC Automated Hematology Analyzer and its performance assessment for 510(k) clearance. However, it does not explicitly state "acceptance criteria" in a tabulated format. Instead, it discusses the study conducted to demonstrate "substantial equivalence" to predicate devices, which implies meeting performance benchmarks comparable to those devices.

Here's an interpretation of the performance data as "acceptance criteria" and how the study addresses them:

1. Table of Acceptance Criteria and Reported Device Performance

Based on the "Discussion of Performance Data" and "Conclusions" sections, the implied acceptance criteria are that the VEGA RETIC performs comparably to the SYSMEX R-3000 for reticulocyte analysis and to the VEGA Hematology Analyzer for CBC and differential counts, meeting certain standards for correlation, precision, linearity, stability, and carry-over.

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

• Sample Size: 200 human whole blood samples.
• Data Provenance: The data used for comparative equivalence testing primarily focused on human whole blood samples. The document does not specify the country of origin, but given the submission is to the FDA, it is highly likely to be U.S. or internationally applicable clinical data. The study is prospective in the sense that these 200 samples were processed and then compared, implying a planned data collection for this evaluation rather than solely analyzing pre-existing records.

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

The document does not provide information regarding:

• The number of experts used.
• The qualifications of those experts.

The ground truth for the comparison was established by the predicate device (SYSMEX R-3000) and the VEGA Hematology Analyzer, which themselves are established and cleared devices. The study focuses on correlation between the devices rather than direct comparison to a human expert's judgment of cell counts.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method involving human experts for the test set. The comparison is directly between the new device and 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

• No, an MRMC comparative effectiveness study involving human readers and AI assistance was not done.
• This device is an automated hematology analyzer, not an AI-assisted diagnostic tool that supports human readers in interpreting images. Its output is quantitative measurements (cell counts) rather than qualitative interpretations requiring human review and potential AI enhancement.

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

• Yes, a standalone performance evaluation was conducted. The VEGA RETIC Automated Hematology Analyzer is designed to operate as a standalone instrument, providing complete blood counts, differential leukocyte counts, and reticulocyte counts without direct human intervention in the primary measurement process. The study evaluates the device's performance (correlation, precision, linearity, stability, carry-over) independently against predicate devices, which is a standalone assessment.

7. The Type of Ground Truth Used

The ground truth for the reticulocyte analysis was based on the performance of the legally marketed predicate device, the SYSMEX R-3000 Automated Reticulocyte Analyzer. For CBC and differential counts, the ground truth was based on the VEGA Hematology Analyzer. This is essentially a "predicate device comparison" as the ground truth.

8. The Sample Size for the Training Set

The document does not provide information about a specific "training set" or its size. As this is a 510(k) submission focused on demonstrating substantial equivalence to existing devices, the focus is on verification and validation against those predicate devices, rather than a de novo development process that might extensively detail training sets for machine learning models.

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

Since no training set information is provided, the method for establishing its ground truth is also not described. For an automated device like this, the "ground truth" for its internal calibration and operational algorithms would typically be established during its development using reference methods and extensive internal validation, but these details are not part of this 510(k) summary.

Ask a specific question about this device