Search Results

The Immunicon CellTracks Analyzer II is a semi-automated fluorescence microscope used to enumerate fluorescently labeled cells that are immuno-magnetically selected and aligned. The system is for in-vitro diagnostic use when used in tandem with specimen preparation equipment and reagents that are legally marketed for in vitro diagnostic use with this device.

The CellTracks® Analyzer II is a semi-automated fluorescence microscope. The product consists of the CellTracks® Analyzer II, a dedicated computer loaded with CellTracks® software, monitor, keybord and mouse.

The Cell Tracks Analyzer II is for analysis of rare cells that are isolated from biological fluids including whole blood. It is used in conjunction with the CellTracks® AutoPrep System, which automates, standading wild optimizes the sample preparation with specific reagent kits.

The CellTracks Analyzer II is used in conjunction with the CellTracks AutoPrep System and in vitro diagnostic reagent kits that contain a ferrofluid-based capture reagent and immunofluonescent my one of or the detection and characterization of the captured cells. The ferrofluid reagent consists of naro-partigles with a magnetic core surrounded by a polymeric layer coated with antibodies targeting the cells of partiers. After Immunomagnetic capture and enrichment, fluorescent reagents are added for identification and enumeration of the target cells.

The processed reagent/sample mixture is dispensed by the CellTracks AutoPrep System into a cartridge that is inserted into a MagNest® cell presentation device. The strong magnetic field of the MagNest causes the magnetically-labeled target cells to move to the surface of the CallTracks Analyzer II sans the entire surface of the cartridge with a series of fluorescence filters that are defined for the assay. Cellimages from the filter are compiled and presented in a gallery format for final cell classification busths user.

What follows is an analysis of the provided text, outlining the acceptance criteria and study details based on the information given.

Acceptance Criteria and Device Performance

The provided text focuses on a 510(k) submission for the Immunicon CellTracks® Analyzer II, where the key modification is the change in the operating system from Microsoft Windows XP to Mandrake Linux and a new Graphical User Interface (GUI). The submission asserts that "These modifications of the CellTracks Analyzer II do not raise any new issues of safety or effectiveness. The intended use of the device is the same." The conclusion drawn is "that the CellTracks Analyzer II is as safe and effective as the predicate device."

This implies that the primary acceptance criterion is equivalence in safety and effectiveness to the predicate device (Immunicon CellTracks Analyzer II K050145). However, specific quantitative performance metrics (e.g., sensitivity, specificity, accuracy, precision for cell enumeration) for either the predicate or the modified device are not provided in the given document.

Therefore, the table below reflects the stated acceptance criterion based on the 510(k) summary, rather than explicit numerical targets.

Study Information

Based on the provided text, here's a breakdown of the study attributes:

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

   • Sample Size: The document does not explicitly state the sample size (number of cases/samples) used for testing. It describes the software testing methodology but does not quantify the test data.
   • Data Provenance: Not specified. The document describes software testing against requirements and design documents, but doesn't mention if biological samples or patient data were used for performance evaluation of the new software/OS. Given that the underlying algorithms remained unchanged, the focus seems to be on software functionality and integrity rather than re-validating the biological performance with new samples.

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

   • Not applicable/Not specified. The document describes software validation focused on requirements, design, and fault testing of the OS and GUI changes. It does not mention any expert review or ground truth establishment for a test set in the context of the device's diagnostic performance. The device is a "semi-automated fluorescence microscope" where "Cell images from the filter are compiled and presented in a gallery format for final cell classification by the user." This indicates the user is responsible for final classification, implying the algorithm provides candidates, but the document doesn't detail how the accuracy of these candidates was validated post-OS change using expert-derived ground truth.

3. Adjudication method for the test set:

   • Not applicable/Not specified. As no ground truth establishment by experts is described, no adjudication method is 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. The document describes software-centric testing related to changes in the operating system and graphical user interface. It does not mention any MRMC studies or human reader performance with or without AI assistance. The device is described as semi-automated, with the user performing final cell classification.

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

   • The document implies the core algorithms for image acquisition, analysis, and cell selection remain unchanged from the predicate device. The testing described primarily validates the new operating system and GUI, ensuring they do not negatively impact the existing algorithms' function or the system's overall operation. It does not detail a standalone performance study of the algorithm itself, likely because the algorithm itself was not modified in this submission.

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

   • For the software changes, the "ground truth" was defined by the software requirements specification (SRS) and design documents (software and database). Tests were developed to ensure the software met these specifications. There is no mention of biological or clinical ground truth (e.g., pathology, outcomes data, expert consensus on cell enumeration) being used for the validation of these specific changes.

7. The sample size for the training set:

   • Not applicable/Not specified. The document does not describe the development or training of new algorithms. It focuses on changes to the operating system and GUI of an existing device, where the "algorithms associated with image acquisition, analysis, cell selection, review, reporting and archiving" remain the same as the predicate device.

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

   • Not applicable/Not specified, as no new training set or algorithm training is mentioned in this submission. The ground truth for the original algorithms of the predicate device would have been established during its development, but this information is not provided here.

Ask a specific question about this device

The Immunicon CellTracks Analyzer II is a semi-automated fluorescence microscope used to enumerate fluorescently labeled cells that are immuno-magnetically selected and aligned. The system is for in vitro diagnostic use when used in tandem with specimen preparation equipment and reagents that are legally marketed for in vitro diagnostic use with this device.

The CellTracks® Analyzer II is a semi-automated fluorescence microscope. The product consists of the CellTracks® Analyzer II, a dedicated computer loaded with CellTracks® software, monitor, keyboard and mouse. The CellTracks Analyzer II is for analysis of rare cells that are isolated from biological samples. It is used in conjunction with the CellTracks® AutoPrep System, which automates, standardizes and optimizes the sample preparation with specific reagent kits. The CellTracks Analyzer II is used in conjunction with the CellTracks AutoPrep System and specific reagent kits that contain a ferrofluid-based capture reagent and fluorescent reagents for the detection and characterization of the captured cells. The ferrofluid reagent consists of nano-particles with a magnetic core surrounded by a polymeric layer coated with antibodies targeting the cells of interest. After immunomagnetic capture and enrichment, fluorescent reagents are added for identification and enumeration of the target cells. The processed reagent/sample mixture is dispensed by the CellTracks AutoPrep System into a cartridge that is inserted into a MagNest® cell presentation device. The strong magnetic field of the MagNest causes the magnetically-labeled target cells to move to the surface of the cartridge. The CellTracks Analyzer II scans the entire surface of the cartridge with a series of fluorescence filters that are defined for the assay. Cell images from the filter are compiled and presented in a gallery format for final cell classification by the user.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The document doesn't explicitly state pre-defined "acceptance criteria" in a structured list with target values. Instead, it demonstrates substantial equivalence to a predicate device by showing high correlation and comparable performance in several metrics. For this analysis, I will infer the implicit acceptance criteria from the reported findings, primarily focusing on correlation with the predicate device and the specified performance characteristics.

Note on "Meets Criteria?": The document focuses on demonstrating substantial equivalence to the predicate device. Therefore, "meets criteria" implies that the new device's performance is comparable to or better than the predicate's, and the statistical metrics (correlation coefficients, slopes, r-values) indicate a very strong agreement between the two systems. While some individual r-values or slopes might not perfectly match '1' or '0.98', the overall conclusion consistently asserts comparability and high correlation. The intercept values were also deemed "not statistically different than 0."

Study Details

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

   • Clinical Samples Study: 83 specimens with an average of ≥ 1.5 circulating tumor cells. Samples were obtained from thirteen geographically dispersed sites. Based on the mention of "cancer patients," this data is retrospective and of clinical origin. The country of origin is not specified but implied to be the US given the FDA submission.
   • Spiked Cell-Line Samples Study: 45 samples were analyzed on each of the two platforms (CellTracks Analyzer II and CellSpotter Analyzer). These were normal donor whole blood samples spiked with tissue culture cell lines (SKBr-3, PC3-9, and MCF-7) at three different levels (~5, ~50, and ~1000 cells). This is a prospective, controlled laboratory study.

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

   • The document does not specify the number of experts or their qualifications for establishing ground truth for the clinical or spiked samples.
   • For the clinical samples, "analysis was performed by Medical Technologists." This refers to the operators of the devices, not necessarily experts establishing a separate ground truth.
   • For the spiked samples, the "ground truth" is defined by the known number of cells spiked into the normal donor blood.

3. Adjudication method for the test set:

   • The document does not mention an adjudication method for the test set. For the clinical samples, it's implied that the device outputs were compared to each other. For spiked samples, it's a comparison to the known spiked quantity.

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 MRMC comparative effectiveness study was done as described. This study is a device-to-device comparison, not an assessment of human reader performance with or without AI assistance. The device is a semi-automated fluorescence microscope where a user classifies cells; however, the study design does not directly evaluate the impact on human reader performance, but rather the performance consistency between the new and predicate device.

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

   • The device, CellTracks Analyzer II, is described as a "semi-automated fluorescence microscope" where "Cell images from the filter are compiled and presented in a gallery format for final cell classification by the user." This indicates it's fundamentally a human-in-the-loop system. Therefore, a standalone (algorithm only) performance study, without human classification, was not performed nor would it be relevant for this device's intended use according to its description. The studies performed compare the system's output (which includes the final user classification) between the new and predicate device.

6. The type of ground truth used:

   • Clinical Samples: The ground truth for this comparison study was the predicate device's output (CellSpotter predicate device), as the study compared the CellTracks Analyzer II to the CellSpotter predicate device using clinical samples.
   • Spiked Cell-Line Samples: The ground truth was the known spiked quantity of cells. This is a form of engineered or "gold standard" ground truth.
   • Linearity & Precision Studies: The ground truth for linearity was the known dilution of cells. For precision, it was the known fixed, pre-stained cells in the control kit.

7. The sample size for the training set:

   • The document does not mention a "training set" in the context of machine learning or AI. The studies performed are verification and validation studies for hardware and integrated system performance against a predicate device or known inputs.

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

   • As there's no mention of a "training set" in the AI/ML sense, this question is not applicable. The device appears to be an optical detection and enumeration system, not an AI/ML-driven classifier that requires a training set. The "software" mentioned likely refers to control and visualization software, not a self-learning algorithm.

Ask a specific question about this device

The intended use for the Immunicon CellTracks™ AutoPrep System is as a generalpurpose laboratory instrument used with immunomagnetic reagents that capture and enrich target cells, and labeling reagents that differentiate cells in whole blood. Cell analyzers such as the CellTracks™ Analyzer, CellSpotter™ System, flow cytometers or microscopes may be used for cell identification and enumeration. The system is for in vitro diagnostic use.

The CellTracks™ AutoPrep System is an automated sample-handling instrument that starts with a tube of anticoagulated whole blood and delivers an enriched, processed sample that is ready to analyze by flow-cytometry, fluorescent microscopy, CellSpotter™ System or by the CellTracks™ Analyzer. The AutoPrep System performs several steps, including red cell detection, plasma aspiration and filling of a sample chamber or test tube. The principal of operation relates to the addition of a ferrofluid, which has been conjugated with monoclonal antibodies that act with the system to magnetically separate the cells of interest and in subsequent steps, within the system, to add fluorescencelabeled monoclonals to further differentiate the captured cells. The first reagent added is ferrofluid, which consists of a magnetic core surrounded by a protein layer coated with antibodies for attachment to cells. Ferrofluid particles are colloidal and when mixed with a sample containing the target cells, they interact and attach to the target cells. The ferrofluid/sample mixture is placed in a strong magnetic field, which causes the labeled target cells to move to the side of the tube. The blood is aspirated, the magnetic field is removed and the cells are resuspended in a small volume of buffer and fluorescent reagents are added for the identification and enumeration of the target cells. Another magnetic separation step and resuspension is performed and the sample is now ready for analysis. The immunomagnetic enrichment process is the new technology but does not raise any new issues of safety and effectiveness.

The provided document is a 510(k) summary for the Immunicon CellTracks™ AutoPrep System. It does not contain information about acceptance criteria or a study proving that a device meets specific performance criteria in the context of an AI/ML medical device, as the prompt's structure implies. This device is a sample-handling instrument for in vitro diagnostic use, not an AI-based system.

However, I can extract the relevant performance data that was collected as part of the 510(k submission.

Here's an analysis based on the information provided, framed to best fit the request, while acknowledging the limitations of the document's content for an AI/ML context:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a tabular format with predefined numerical targets. Instead, it describes performance characteristics observed during clinical and non-clinical testing. I will present the reported performance as if these were the metrics assessed.

The document discusses two main types of studies: a precision study and a method comparison study.

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

• Test Set Sample Size: The document states a "20 day precision study" was performed and a "method comparison was performed." It does not explicitly state the number of samples or patients used in these studies. The precision study implies repeated measurements over 20 days.
• Data Provenance: Clinical testing was performed at "three clinical sites." The document does not specify the country of origin, but given the FDA submission, it's highly likely to be within the United States. The studies are prospective in nature, as they involve performing tests with the device to evaluate its performance.

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

The document does not mention the use of experts to establish a "ground truth" for the test set in the context of diagnostic interpretation. The studies are technical performance evaluations of an automated sample preparation system. The "ground truth" for the precision study would be the known spike levels of control cells, and for the method comparison, it would be the results obtained by the predicate device. Therefore, no external experts were explicitly mentioned for ground truth establishment.

4. Adjudication Method for the Test Set

Not applicable. This is not a study requiring adjudication of diagnostic interpretations. The studies described are analytical performance evaluations.

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

No. This is not an AI/ML diagnostic device; it's an automated sample preparation system. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to this submission and was not conducted.

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

Yes, in the sense that the performance evaluations (precision, sensitivity, linearity, method comparison) assess the device's technical capabilities as a standalone automated system. There's no "human-in-the-loop" component for the sample preparation itself, although subsequent analysis of the processed samples would involve human operators and/or other analytical instruments.

7. Type of Ground Truth Used

• Precision Study: The ground truth for the precision study was based on "control cells" at "spike levels" (38 cells and 264 cells). This implies a known, controlled input to assess reproducibility.
• Nonclinical Testing (Sensitivity, Linearity): The ground truth for sensitivity and linearity was derived from known cell counts introduced into the system to determine its ability to detect and accurately quantify them.
• Method Comparison: The ground truth for the method comparison was the results obtained from the "predicate device." This establishes a comparative baseline against an already legally marketed device for the same intended use.

8. Sample Size for the Training Set

Not applicable. This is not an AI/ML device that requires a training set. The device operates based on pre-programmed protocols and immunomagnetic separation principles, not on learned patterns from a training dataset.

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The intended use for the Immunicon CellTracks™ System is as a general-purpose laboratory bench top scanning cytometer designed to enumerate fluorescently labeled leukocyte subsets that are immuno-magnetically selected and aligned. The system is for in vitro diagnostic use.

To enumerate fluorescently labeled leukocyte subsets that are immuno-magnetically selected and aligned.

The CellTracks Analyzer is used in conjunction with reagents containing ferrofluids and fluorescent conjugates. Depending on the application, samples may be prepared manually or using the CellTracks AutoPrep Sample Preparation System. Ferrofluid consists of a magnetic core surrounded by a polymeric layer coated with antibodies for capturing cells. Ferrofluid particles are colloidal (25-100 nanometers in radius) and when mixed with a sample containing target cells, the antibodies bound to the ferrofluid bind the associated antigens to the target cells. Fluorescent reagents are added for the identification and the enumeration of the target cells. The ferrofluid/sample mixture is placed in a magnetic field (Magnest), to select and align the labeled target cells. The Magnest, containing the fluorescence-labeled magnetically aligned target cells, is placed on the CellTracks analyzer and is ready for analysis.

1. Table of Acceptance Criteria and Reported Device Performance

*Note: The document

Ask a specific question about this device

CellSave tubes are evacuated blood collection tubes that are designed to be used with standard phlebotomy supplies for venous blood collections. The tube contains 300µl of a solution that contains Na2EDTA and a cell preservative preservative preserves morphology and cell surface antigen expression of the epithelial cells and leukocytes. This tube may be used for monitoring of circulating epithelial cells (tumor cells) which may aid in the management of cancer patients. This tube may be used for monitoring CD3+/CD4+ T lymphocyte subsets which may aid in the management of patients with HIV/AIDS.

The CellSave™ tube is an evacuated closed glass tube for collecting, transporting and processing blood. The assembly consists of a rubber stopper, a glass tube and anticoagulant. The anticoagulant contains EDTA (disodium EDTA), polyethylene glycol and a preservative reagent.

Here's an analysis of the acceptance criteria and study detailed in the provided text, formatted as requested:

Acceptance Criteria and Device Performance

Device Name: The Immunicon CellSave™ Preservation Tube
Intended Use: Collection and preservation of circulating epithelial cells (tumor cells) and mature human T lymphocytes (CD3+) and helper/inducer (CD3+/CD4+) T lymphocyte subsets in whole blood, for enumeration and phenotyping.

Table of Acceptance Criteria and Reported Device Performance

Detailed Study Information:

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

   • Circulating Epithelial Cell Preservation Study:
     • Test Set Size: 102 metastatic cancer patients providing 107 blood specimens. 70 specimens had sufficient volume for 24-hour and 96-hour testing, with 21 of these having ≥3 CTCs at both time points.
     • Data Provenance: Blood samples obtained from five geographically dispersed sites in the US. Retrospective or prospective is not explicitly stated but implies prospective collection for the study.
   • CD3/CD4 Immunophenotyping Study:
     • Test Set Size: 50 healthy volunteers and 12 patients with confirmed HIV.
     • Data Provenance: Not explicitly stated, but likely US given the context of other studies. Retrospective or prospective is not explicitly stated but implies prospective collection for the study.
   • Recovery and Interfering Substances Studies (Nonclinical):
     • Test Set Size: Blood from 5 normal donors for recovery; blood from 5 normal donors for interfering substances.
     • Data Provenance: Not explicitly stated, but likely originating from the US where Immunicon Corporation is based. These are in vitro spiking studies using donated blood.

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

   • No external human experts were explicitly stated as establishing ground truth. The method relies on flow cytometry measurements (using FACSCalibur flow cytometer) for enumeration and phenotyping, which is an objective measurement rather than an expert interpretation. The "ground truth" for recovery studies was the known number of spiked cells or the initial count at 24 hours (for preservation studies).

3. Adjudication Method for the Test Set:

   • Not applicable as the ground truth relies on objective technical measurements (flow cytometry) rather than human interpretation requiring adjudication.

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

   • No, a MRMC comparative effectiveness study was not done. This device is a blood collection tube intended for sample preservation, not an imaging or diagnostic algorithm that human readers would interpret. Therefore, the effect size of human readers improving with AI vs. without AI assistance is not relevant to this device.

5. Standalone (Algorithm-Only) Performance:

   • Yes, the performance presented for recovery, interference, and preservation is standalone (i.e., the performance of the tube in maintaining cell viability and antigen expression for subsequent automated analysis). There is no "algorithm" in the traditional sense, but the studies assess the device's ability to preserve the sample for downstream laboratory processing and machine-based analysis.

6. Type of Ground Truth Used:

   • For Recovery Studies: The ground truth was the known number of spiked cells (SKBR-3 breast cancer cell line).
   • For Preservation Studies (Epithelial Cells): The ground truth was the initial count of circulating epithelial cells at 24 hours using flow cytometry, which was then compared to subsequent counts at 96 hours.
   • For Preservation Studies (T Lymphocyte Subsets): The ground truth was the initial counts of CD3/CD4 positive lymphocytes on Day 1 using flow cytometry, which was then compared to subsequent counts on Day 2 and Day 3.
   • For Interfering Substances Studies: The ground truth was the known number of spiked cells which was used to calculate percentage recovery.
   • In all cases, the primary measurement method for "ground truth" was flow cytometry.

7. Sample Size for the Training Set:

   • Not applicable. This device is a physical blood collection tube, not an AI/ML algorithm that requires a training set. The studies described are validation studies for the device's performance characteristics.

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

   • Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The Immunicon CellPrep™ Sample Preparation System is a general-purpose laboratory instrument used with immunomagnetic reagents that capture and enrich target cells, and labeling reagents that differentiate cells in whole blood. Cell analyzers such as the CellTracks™ Analyzer, flow cytometers or microscopes may be used for cell identification and enumeration. The system is for in vitro diagnostic use.

The CellPrep System is a semi-automated sample-handling instrument that starts with a tube of anticoagulated whole blood and delivers an enriched, processed sample that is ready to analyze by flow-cytometry, fluorescent microscopy or by the CellTracks™ Analyzer. The CellPrep™ System performs several steps, including red cell detection, plasma aspiration and filling of a sample chamber or test tube. The user is prompted to perform various operations such as reagent addition and mixing. The principal of operation relates to the addition of a ferrofluid, which has been conjugated with monoclonal antibodies that act with the system to magnetically separate the cells of interest and in subsequent steps, within the system, to add fluorescence-labeled monoclonals to further differentiate the captured cells. The first reagent added is ferrofluid, which consists of a magnetic core surrounded by a protein layer coated with antibodies for attachment to cells. Ferrofluid particles are colloidal and when mixed with a sample containing the target cells, they interact and attach to the target cells. The ferrofluid/sample mixture is placed in a strong magnetic field, which causes the labeled target cells to move to the side of the tube. The blood is aspirated, the magnetic field is removed and the cells are resuspended in a small volume of buffer and fluorescent reagents are added for the identification and enumeration of the target cells. Another magnetic separation step and resuspension is performed and the sample is now ready for analysis.

The provided text describes the Immunicon CellPrep™ Sample Preparation System and summarizes the testing performed to demonstrate its safety and effectiveness. However, it does not explicitly present a table of acceptance criteria or a detailed, structured study report in the format requested. Instead, it provides a narrative summary of performance findings.

Based on the provided text, here's an attempt to extract and infer the requested information:

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

The document does not explicitly state "acceptance criteria" as a separate, defined list. However, we can infer the performance targets/criteria from the reported results.

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

• Sample Size for Test Set: The text states, "Clinical testing was performed at five clinical sites." It mentions the device was "capable of removing small numbers of cells (~950) from a 7.5 ml volume of blood" and that the CV range was for "duplicate samples." However, it does not explicitly state the total number of patient samples, runs, or analyses conducted within the clinical trial. It only refers to "small numbers of cells (~950)". For non-clinical testing, it mentions "very low levels of approximately 10 cells" and "range of 50 to 200 cells" in a 7.5ml sample, but again, no specific sample size (i.e., number of spiked samples or replicates) is provided.
• Data Provenance:
  • Country of Origin: Not specified.
  • Retrospective or Prospective: "Clinical testing was performed at five clinical sites" implies a prospective study, where samples were processed and analyzed as part of the trial. The term "nonclinical testing" typically refers to laboratory-based, controlled studies, which are also generally prospective in nature.

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

This information is not provided in the document. The text states, "Clinical testing was performed at five clinical sites by Medical technicians or degreed biologists." While these individuals performed the testing, the method and number of experts establishing the ground truth (e.g., the true cell count before processing, or an independent verification of captured cells) are not detailed.

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

This information is not provided in the document. The text does not describe any adjudication process for the results obtained.

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

The Immunicon CellPrep™ Sample Preparation System is described as a "semi-automated sample-handling instrument" designed to prepare samples for analysis by "flow cytometers or microscopes." It processes blood and delivers an enriched sample. It is not an AI-powered diagnostic tool for image interpretation or diagnosis that would typically be evaluated in an MRMC study involving human readers with and without AI assistance. Therefore, an MRMC study as described, and its effect size, are not applicable and were not performed for this device type based on the provided text.

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

The device is a "semi-automated sample-handling instrument." It performs physical steps to prepare blood samples. While it has automated components, it is not an "algorithm only" device in the sense of an AI model. The performance metrics (recovery, precision, sensitivity, linearity) are for the device's ability to process samples, which is inherently a "standalone" performance evaluation of the instrument itself in its intended function.

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

The document implies that the ground truth for cell recovery and linearity studies would have been established by:

• Known input concentrations: For nonclinical sensitivity and linearity testing, cells are typically spiked into samples at known concentrations.
• Baseline measurements or reference methods: For clinical recovery, it would involve knowing the initial cell count in the 7.5 ml blood volume before the CellPrep device processes it. This might be done using a highly accurate reference method or manual counting.
  The document does not explicitly state the exact method used, but for "recovery" and "sensitivity" of a sample preparation system, the ground truth is generally a quantified, validated initial cell count or concentration.

8. The sample size for the training set

The device is a sample preparation instrument. It does not use machine learning or AI models that require a "training set" in the typical sense of AI/ML software development. Therefore, this concept is not applicable to the Immunicon CellPrep™ Sample Preparation System as described.

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

As explained in point 8, the concept of a "training set" for an AI/ML model does not apply to this device.

Ask a specific question about this device