Search Results

The Altris IMS is a standalone, browser-based software application intended for use by healthcare professionals to import, store, manage, display, and measure data from ophthalmic diagnostic instruments, including patient data, diagnostic data, clinical images and information, reports, and measurement of DICOM-compliant images. The device is also indicated for manual labeling and annotation of retinal OCT scans.

Altris IMS is a cloud-based software program to assist healthcare professionals, specifically Eye Care Practitioners (ECPs) with OCT interpretation. Altris IMS utilizes commonly available internet browsers to locally manage and review data which is uploaded to an Amazon AWS cloud-based server. Its intended use is to import, store, manage, display, analyze and measure data from ophthalmic diagnostic instruments, including patient data, diagnostic data, clinical images and information, reports, and measurement of DICOM-compliant images. The platform allows the user to manually annotate areas of interest in the images, calculate the layer thickness and volume from annotated images and present the progression of the measurements. Altris IMS also provides a tool for linear distance measuring of ocular anatomy and ocular lesion distances. The platform supports DICOM format files. Altris IMS is focused on the center sector of the retina. Altris IMS does not perform optic nerve analysis. Altris IMS has tools for manual area of interest image segmentation and labeling/annotation for healthcare professionals to use and review for their own diagnosis. The Subject device neither performs any diagnosis, nor provides treatment recommendations. It is solely intended to be used as a support tool by trained healthcare professionals. The software does not use artificial intelligence or machine learning algorithms. The Subject device is a client-server model. It utilizes a local user/client internet browser-based (frontend) interface used to upload, manage, annotate, and review imaging data. Data is stored and processed on a remote web-based server (backend).

The provided text does not contain detailed information about the acceptance criteria or a specific study that proves the device meets those criteria for the Altris IMS. The document is a 510(k) summary for a medical device (Altris IMS) seeking FDA clearance, focusing on demonstrating substantial equivalence to a predicate device rather than outright performance claims.

However, based on the information provided, we can infer some aspects and highlight what is missing.

The Altris IMS is a software application for managing and displaying ophthalmic diagnostic data, including manual labeling and annotation of retinal OCT scans. It explicitly states it does not use AI or ML algorithms and does not perform diagnosis or provide treatment recommendations.

Given this, the performance data section is likely to focus on the software's functionality, accuracy of manual measurements, and data handling, rather than diagnostic accuracy or clinical effectiveness in a medical sense.

Here's an attempt to answer your questions based on the provided text, and where information is missing, it will be noted:

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

The document does not provide a formal table of acceptance criteria or specific quantitative performance metrics like sensitivity, specificity, accuracy, or measurement error rates. The "Performance Data" section states: "Due to the difficulty in evaluating this type of software, no direct performance bench testing of software to an established standard was performed."

Instead, performance was demonstrated through:

• Software Verification
• Software Validation
• Comparative Software measurement study with the K170164 Reference device.

Without the actual study report, specific performance numbers are unavailable. The goal was to prove the device "performs as intended similarly to the Predicate device."

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

The document mentions "a Comparative Software measurement study with the K170164 Reference device." However, it does not provide details on:

• The sample size of images/cases used in this comparative study.
• The data provenance (country of origin, whether it was retrospective or prospective data).

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)

Given the device allows for "manual labeling and annotation of retinal OCT scans" by "healthcare professionals," and it does not use AI/ML for diagnosis, the "ground truth" for the comparative measurement study would likely involve comparing the device's manual measurement capabilities against the reference device or perhaps against expert manual measurements performed independently.

The document does not specify the number of experts or their qualifications involved in establishing any form of "ground truth" or reference measurements for the comparative study.

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

The document does not describe any adjudication method used for establishing ground truth or conducting the comparative measurement study.

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

Given that the device "does not use artificial intelligence or machine learning algorithms" and "neither performs any diagnosis, nor provides treatment recommendations," an MRMC study comparing human readers with AI vs. without AI assistance would be irrelevant and was not performed. The study mentioned is a "Comparative Software measurement study" which likely focuses on the accuracy or consistency of the manual measurement tools provided by the software.

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

Since the device "does not use artificial intelligence or machine learning algorithms," and its primary functions are data management, display, and manual annotation/measurement, the concept of an "algorithm only" standalone performance is not applicable in the typical sense of AI diagnostic devices. The software supports human-in-the-loop actions.

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

For the "Comparative Software measurement study," the "ground truth" would most likely be a comparison of measurements obtained using the Altris IMS's manual tools against those obtained using the K170164 Reference device, which is an imaging system with storage/management software and supports image annotation and measurement. It could also involve comparing against expert manual measurements using established clinical standards. The document does not explicitly state the type of ground truth used beyond "measurement validation."

8. The sample size for the training set

Since the device "does not use artificial intelligence or machine learning algorithms," there is no concept of a training set in the machine learning sense for this device.

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

As there is no training set (due to the absence of AI/ML), there is no ground truth established for a training set.

In summary, the provided FDA 510(k) summary focuses on demonstrating substantial equivalence based on indications for use and technological principles, supported by general software verification and validation, and a comparative measurement study. It explicitly states the device does not employ AI/ML, which changes the nature of the performance data required compared to an AI-powered diagnostic device. The document lacks the specific quantitative performance metrics, sample sizes, and expert details typically found in studies validating AI/ML-driven medical devices.

Ask a specific question about this device