Search Results

Hemodialysis with SyntraTM + dialyzers is indicated for patients with renal failure when conservative therapy is judged to be inadequate. It also may be indicated in the treatment of patients intoxicated with poisons or drugs.

Model 200 Dialyzer

Here's a breakdown of the acceptance criteria and study information based on the provided text, recognizing that this is a 510(k) summary for a medical device (dialyzer) and not an AI/software-as-a-medical-device (SaMD) submission, so most of the AI-specific questions will be "N/A."

The provided document is a 510(k) Premarket Notification for the Syntra™ + Dialyzer, a conventional medical device (high permeability hemodialysis system), not a software or AI-driven device. As such, many of the requested categories related to AI/software performance, ground truth, expert review, and MRMC studies are not applicable. The acceptance criteria and "study" (validation) for this device focus on biological safety, sterilization, manufacturing quality, and functional equivalence to a predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not explicitly stated as a single "test set" in the context of an AI device. The validation activities involve testing of device components and samples according to the referenced standards (ISO, AAMI/ISO, USP). The specific number of devices or components sampled for each test (e.g., biological testing, pyrogen testing, particle count) is not provided in this summary.
• Data Provenance: Not applicable in the context of patient data for a software/AI device. The data provenance would refer to the origin of the physical device samples used for testing (e.g., from the manufacturing line).

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 (N/A). This is a hardware medical device submission. Ground truth, in the AI context of expert consensus, is not relevant here. The ground truth for device performance is based on established engineering, material, and biocompatibility standards.

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

• N/A. Adjudication methods like 2+1 or 3+1 are used in expert consensus for AI model ground truth establishment. For this physical device, conformity to standards is typically assessed against predefined pass/fail criteria established by the standards themselves, not through expert adjudication of images or outputs.

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

• N/A. MRMC studies are specific to AI-assisted human performance evaluations. This submission is for a physical dialyzer.

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

• N/A. This is a physical hardware device; there is no algorithm to evaluate in standalone mode.

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

• The "ground truth" for this device's performance is established by compliance with recognized international and national standards for medical device safety and performance (e.g., ISO 10993-1 for biocompatibility, AAMI/ISO 11137 for sterilization, USP 24 <161> for pyrogenicity, USP XXIII Monograph <788> for particle count). Additionally, functional testing and conformance to manufacturing specifications serve as the ground truth for acceptable product quality.

8. The sample size for the training set

• N/A. There is no "training set" as this is not an AI/machine learning device.

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

• N/A. As there is no training set, there is no ground truth for a training set to establish.

Ask a specific question about this device