Search Results

The Tablo® Hemodialysis System is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute or chronic care facility. Treatments must be administered under physician's prescription and observed by a trained individual who is considered competent in the use of the Tablo Hemodialysis System is also indicated for use in the home.

The Tablo Hemodialysis System is a self-contained hemodialysis system intended for acute and chronic dialysis therapy, with or without ultrafiltration, in an acute or chronic care facility or in the home. The device includes the:

• Tablo Console, a single module consisting of multiple fluidic systems that perform the activities of a water purification system (WPS) and a conventional dialysis delivery system (DDS), and
• Table Cartridge

The provided text is a 510(k) premarket notification summary for the Tablo® Hemodialysis System (software version 4.8). This document primarily focuses on demonstrating substantial equivalence to a predicate device, rather than presenting a detailed clinical study for a new device requiring a comprehensive performance evaluation against defined acceptance criteria.

Therefore, the information required to answer your specific questions about acceptance criteria and study details (like sample size, number of experts, adjudication methods, MRMC studies, standalone performance, ground truth types, and training set information for an AI/software device) is not present in this type of FDA submission.

This document describes a software update (version 4.8) to an existing hemodialysis system. The performance data provided is limited to bench testing, biocompatibility, electrical safety, and software verification and validation testing. The software is considered "major" level of concern, and verification and validation were conducted. However, the document does not detail specific acceptance criteria for performance metrics that would be relevant to an AI/ML-driven diagnostic device.

Here's an attempt to answer based on the limited information available in the provided text:

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

The document provides very high-level acceptance criteria for specific non-clinical tests, rather than detailed performance metrics for an AI/ML system.

For an AI/ML device, you would expect detailed performance metrics like sensitivity, specificity, AUC, F1-score, etc., with associated acceptance thresholds for "Pass." This is not present here.

2. Sample sized 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 document as it is not a clinical study on patient data for an AI/ML diagnostic. The software V&V would involve testing against various scenarios and inputs, but the "sample size" in the context of patient data for AI model evaluation is not applicable here.

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 information is not provided. Ground truth establishment by experts is relevant for diagnostic AI/ML systems where human-annotated data is used for evaluation. This document describes a software update for a hemodialysis system, not an AI diagnostic.

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

This information is not provided, as it pertains to expert consensus on ground truth in studies of diagnostic AI/ML systems.

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 MRMC study was conducted or reported. The document explicitly states: "No clinical studies were conducted to support the modified device." MRMC studies are typically performed for diagnostic AI/ML tools to assess their impact on human reader performance.

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

While "Software Verification and Validation Testing" was conducted, the document does not specify standalone algorithm performance in terms of diagnostic metrics. It only states that the testing "passed" and "supports safety and effectiveness." The software's function is to control a hemodialysis system, not to perform a standalone diagnostic task.

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

This information is not provided. Ground truth in the context of this device's software V&V would relate to the correct functional behavior of the system under various conditions, not diagnostic outcomes based on expert consensus, pathology, or outcomes data.

8. The sample size for the training set

This information is not provided. Training set details are relevant for AI/ML model development. This document is about a software update for a medical device's control system, not the development of a predictive AI model.

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

This information is not provided. As above, this is relevant for AI/ML model training, which is not the focus of this 510(k) submission.

In summary: The provided document is an FDA 510(k) clearance letter and summary for a software update to an existing hemodialysis system. It demonstrates substantial equivalence to a predicate device through non-clinical testing and verification/validation of software changes. It does not contain the detailed performance study information, particularly for AI/ML-driven diagnostics, that your questions are designed to elicit. The "acceptance criteria" presented are for general device performance and regulatory compliance, not for algorithmic diagnostic accuracy.

Ask a specific question about this device