FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The CAPILLARYS HEMOGLOBIN(E) kit is designed for the detection and the characterization of hemoglobins in human blood with the Sebia CAPILLARYS system, for capillary electrophoresis. The CAPILLARYS performs all procedural sequences automatically to obtain a hemoglobin profile. The CAPILLARYS system automatically mixes the blood sample with hemolysing solution The hemoglobins, separated in silica capillaries, are directly detected by their absorbance at 415 nm. The electrophoregrams are evaluated visually for the pattern abnormalities. Direct detection of the hemoglobins provides relative quantification of individual hemoglobin fraction of the normal hemoglobin fractions A, A2, F and for the detection of major hemoglobin variants as S, C, E and D using Capillarys electrophoresis

For in vitro diagnostic use

Device Description

AI/ML Overview

The provided document is a 510(k) clearance letter from the FDA for the Capillarys Hemoglobin (E), PN 2007 device. This device is an in-vitro diagnostic (IVD) device used for the detection and characterization of hemoglobins in human blood for conditions like hemoglobinopathies.

The document does not contain the detailed study information typically found in a clinical trial report or a performance evaluation study. It is a regulatory clearance letter, which confirms that the device has been found substantially equivalent to a predicate device. Therefore, I cannot provide all the requested information.

However, I can extract the relevant information that is present and explain what is missing.

Missing Information: It's crucial to understand that for an IVD device like this, the "acceptance criteria" and "device performance" are typically defined in terms of analytical performance characteristics, such as:

Accuracy: How close are the measured values to the true values (often assessed by comparison to a reference method, like HPLC or another established electrophoresis method). This would involve metrics like concordance rates, correlation coefficients, or direct comparisons of hemoglobin fraction percentages.
Precision/Reproducibility: How consistent are the measurements when performed repeatedly under the same conditions (intra-assay, inter-assay, inter-instrument variability). This would be expressed as coefficients of variation (CV%).
Sensitivity: The ability to detect a positive result when a condition is present (e.g., detecting a specific hemoglobin variant).
Specificity: The ability to provide a negative result when a condition is absent.
Limit of Detection (LoD) / Limit of Quantitation (LoQ): The lowest concentration of an analyte that can be reliably detected or quantified.
Interference: Assessment of substances that might falsely alter the results.

Given that this is an FDA clearance letter for substantial equivalence for an in vitro diagnostic device, the submission would have included studies demonstrating these analytical performance characteristics against a predicate device. The letter itself does not detail these studies.

Here's what can be gleaned or inferred from the provided text, and what remains unknown:

1. Table of Acceptance Criteria and Reported Device Performance

As stated above, the specific acceptance criteria and detailed quantitative performance metrics (e.g., concordance rates for variants, CVs for percentages) are not provided in this FDA clearance letter. The letter confirms substantial equivalence, which implies that the submitted data demonstrated acceptable performance in comparison to a predicate device for the stated indications for use.

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

Test Set Sample Size: Unknown. This information is not present in the 510(k) clearance letter. This would typically be detailed in the manufacturer's submission.
Data Provenance (e.g., country of origin, retrospective or prospective): Unknown. This information is not present in the 510(k) clearance letter.

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

Number of Experts/Qualifications: Not applicable in the typical sense for an IVD like this. For diagnostic tests that interpret data (like imaging), expert consensus is crucial. However, for a hemoglobin electrophoresis device, the "ground truth" for the test set would primarily be established by a reference method (e.g., confirmatory testing by HPLC, DNA sequencing if variants are complex, or another established electrophoresis method known to be accurate). If visual interpretation of electrophoregrams was involved (which the "Indications for Use" mentions: "The electrophoregrams are evaluated visually for the pattern abnormalities"), then qualified laboratory professionals or clinical chemists would perform this, but their number and specific qualifications are unknown from this document.

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

Adjudication Method: Not applicable/Unknown. As explained above, for an IVD device measuring specific analytes, the ground truth typically relies on objective reference methods rather than multiple expert adjudications in the same way an imaging study would. If there were discrepancies between the new device and the reference method, these would be investigated, possibly by a higher-level confirmatory test. The specific method used to resolve discrepancies or interpret visual patterns (if any multi-reader process was used) is unknown from this document.

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.

MRMC Study / AI Improvement: Not applicable. This device is an automated capillary electrophoresis system for hemoglobin analysis. It directly measures and quantifies hemoglobin fractions. It is not an AI-assisted diagnostic imaging device that human readers interpret. Therefore, an MRMC study assessing human reader improvement with AI assistance is not relevant to this type of device.

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

Standalone Performance: The device itself, the Capillarys Hemoglobin (E) system, performs all procedural sequences automatically and provides a hemoglobin profile. The "Indications for Use" state: "The CAPILLARYS performs all procedural sequences automatically to obtain a hemoglobin profile." and "The electrophoregrams are evaluated visually for the pattern abnormalities." This suggests the measurement is automated (standalone), and the interpretation of pattern abnormalities might involve human visual evaluation. Therefore, the core analytical function is "standalone." The performance evaluation would have focused on the accuracy and precision of these automated measurements.

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

Type of Ground Truth: The ground truth for this type of IVD would typically involve:
- Reference Methods: Comparison against established, high-accuracy methods for hemoglobinopathy diagnosis, such as:
  - High-Performance Liquid Chromatography (HPLC): A gold standard for quantifying hemoglobin fractions and detecting variants.
  - Other established electrophoresis methods: Such as cellulose acetate electrophoresis or isoelectric focusing, often followed by confirmatory tests.
  - Molecular Methods (DNA sequencing): For unequivocal identification of specific genetic mutations causing hemoglobin variants, especially for complex or rare cases.
    The specific method(s) used in the submission are unknown from this document.

8. The sample size for the training set.

Training Set Sample Size: Not applicable/Unknown. For a traditional IVD device like this, there isn't a "training set" in the machine learning sense. The device's algorithms are built upon established principles of capillary electrophoresis. Any initial development or optimization would use internal samples, but the final performance evaluation would be on a distinct "test set."

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

Ground Truth for Training Set: Not applicable/Unknown. See point 8. The device's operational parameters are often set based on physical and chemical principles, then refined and validated using known samples whose characteristics (e.g., hemoglobin types and concentrations) are established by reference methods.

Summary of what's available and what's missing from the FDA clearance letter:

The FDA clearance letter confirms the device's regulatory status and its intended use. It does not provide the detailed technical specifications or study results that would describe specific acceptance criteria (e.g., X% concordance with HPLC, Y% CV for A2 quantification) or the minutiae of the performance study (sample sizes, ground truth establishment methods, expert qualifications). This level of detail is typically found in the manufacturer's 510(k) submission, specifically the sections related to device performance and analytical validation studies, which are not publicly detailed in the clearance letter itself.

Summary

Regulation Number and Section

§ 864.7415 Abnormal hemoglobin assay.

(a)
Identification. An abnormal hemoglobin assay is a device consisting of the reagents, apparatus, instrumentation, and controls necessary to isolate and identify abnormal genetically determined hemoglobin types.(b)
Classification. Class II (special controls). A control intended for use with an abnormal hemoglobin assay is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.