Search Results

IDx-DR is indicated for use by healthcare providers to automatically detect more than mild diabetic retinopathy in adults diagnosed with diabetes who have not been previously diagnosed with diabetic retinopathy. IDx-DR is indicated for use with the Topcon NW400.

The IDx-DR device consists of several component parts. A camera is attached to a computer, where IDx-DR client is installed. Guided by the Client, users acquire two fundus images per eye to be dispatched to IDx-Service. IDx-Service is installed on a server hosted at a secure datacenter. From IDx-Service, images are transferred to IDx-DR Analysis. No information other than the fundus images is required to perform the analysis. IDx-DR Analysis, which runs on dedicated servers hosted in the same secure datacenter as IDx-Service, processes the fundus images and returns information on the exam quality and the presence or absence of mtmDR to IDx-Service. IDx-Service then transports the results to the IDx-DR Client that displays them to the user.

Here's an analysis of the acceptance criteria and study information for the IDx-DR device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided 510(k) summary (K203629) states that the device modifications do not affect clinical performance and refers to the predicate device (DEN180001) for clinical trial details. Therefore, the acceptance criteria and reported device performance are identical to the predicate device. To provide complete information, one would need to refer to the DEN180001 submission. However, based solely on the provided document K203629, the table would look like this:

Important Note: To get the actual numerical acceptance criteria (e.g., sensitivity, specificity thresholds) and the reported performance values, the DEN180001 submission would need to be reviewed. This document explicitly avoids providing those details for the current submission.

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

Since the current submission (K203629) states that "The determination of substantial equivalence is not based on an assessment of clinical performance data" and refers to DEN180001 for clinical trial details, this information is not available in the provided text.

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

This information is not provided in the K203629 document. It would be found in the clinical trial details for the predicate device (DEN180001).

4. Adjudication Method for the Test Set

This information is not provided in the K203629 document. It would be found in the clinical trial details for the predicate device (DEN180001).

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance is not mentioned in the furnished K203629 document. The document explicitly states that the substantial equivalence determination is not based on new clinical performance data and refers to the predicate device's clinical trial.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Study Was Done

The K203629 document describes the IDx-DR Analysis component as "Software that analyzes the patient's images and determines exam quality and the presence/absence of diabetic retinopathy." This implies a standalone algorithmic assessment. However, the performance metrics of this specific version of the standalone algorithm are not presented in this document, as it relies on the predicate device's clinical performance. The "Outputs" section of Table 1 supports the standalone nature of the output, as it directly states the detection of DR and referral decisions.

7. The Type of Ground Truth Used

This information is not provided in the K203629 document. It would be found in the clinical trial details for the predicate device (DEN180001). Typically, for diabetic retinopathy, ground truth is established by a panel of expert ophthalmologists or retina specialists through consensus reading of images, potentially correlated with other clinical findings.

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set. It mentions "Future algorithm improvements will be made under a consistent medically relevant framework" and "A protocol was provided to mitigate the risk of algorithm changes," but no details on training data for the current or previous versions are given.

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

The document does not provide details on how the ground truth for the training set was established.

Ask a specific question about this device