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

Control Plasma N is a lyophilized control prepared from pooled human plasma, stabilized with HEPES buffer solution. Control Plasma P is a lyophilized control prepared from pooled human plasma, adjusted to defined factor concentrations, and then stabilized with HEPES buffer solution.

AI/ML Overview

This 510(k) summary (K042209) is for Control Plasma N and Control Plasma P, which are assayed controls for monitoring in vitro coagulation studies. It does not describe an AI medical device, but rather a laboratory control product. Therefore, many of the requested details, such as those related to AI performance, human reader studies, and training/test set specifics, are not applicable to this document.

Here's an analysis based on the provided text, focusing on the concepts that are relevant to this type of device:

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

The document does not explicitly state "acceptance criteria" in a quantitative, measurable table as one would for an AI device's performance metrics (e.g., sensitivity, specificity thresholds). Instead, the acceptance criterion for these control plasmas is substantial equivalence to their legally marketed predicate devices.

Acceptance Criteria (Implicit)	Reported Device Performance
Substantial Equivalence to Predicate Devices (K023309 and K023312)	"Control Plasma N and Control Plasma P values are substantially equivalent to the current legally marketed devices, K023309 and K023312."
Functionality as an assayed control for specified coagulation parameters in normal (Control Plasma N) or pathological (Control Plasma P) ranges.	Intended Use statements explicitly list the coagulation parameters for each control, indicating they function as designed for monitoring these.

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

This information is not provided in the 510(k) summary. For a medical device like a control plasma, the "test set" would typically refer to the samples used during the internal validation studies to demonstrate its performance and equivalence. The summary only states that the "value assignment process has changed for some of the reagents," implying internal testing was conducted to re-establish values and demonstrate equivalence, but no details on sample size or provenance are given.

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)

This is not applicable in the context of this device. "Ground truth" for an in vitro diagnostic control like this is established through analytical methods and calibration processes against reference materials, not typically by expert review in the way it would be for an image-based AI diagnostic. The "values" for the control plasmas are determined through laboratory procedures.

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

This is not applicable for this type of device. Adjudication methods are used to establish ground truth in complex, subjective diagnostic tasks, often in image interpretation or clinical diagnosis. For a coagulation control, the "truth" (i.e., the assigned values) is determined through analytical testing and statistical methods, not by expert consensus or adjudication.

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

This is not applicable. MRMC studies are used to evaluate diagnostic imaging devices with human readers, often involving AI assistance. This document describes a quality control plasma, which does not involve "human readers" interpreting an output in the same way.

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

This is not applicable. This device is a consumable, assayed control plasma, not an algorithm.

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

For this device, the "ground truth" (the assigned values for the various coagulation parameters in the control plasmas) is established through analytical testing and calibration against reference methods/materials. The summary indicates a "value assignment process has changed for some of the reagents," suggesting a laboratory-based method for determining these values. It is not expert consensus, pathology, or outcomes data.

8. The sample size for the training set

This is not applicable. This is not an AI/machine learning device that requires a training set.

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

This is not applicable. As it's not an AI/machine learning device, there is no training set or ground truth in that context.

Summary

Regulation Number and Section

§ 864.5425 Multipurpose system for in vitro coagulation studies.

(a)
Identification. A multipurpose system for in vitro coagulation studies is a device consisting of one automated or semiautomated instrument and its associated reagents and controls. The system is used to perform a series of coagulation studies and coagulation factor assays.(b)
Classification. Class II (special controls). A control intended for use with a multipurpose system for in vitro coagulation studies is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.