Search Results

The Preview® Treatment Planning Software is intended to provide accurate, alternative two-dimensional images, as well as three-dimensional models, of patient specific anatomy from existing two-dimensional scan data of organs and tissues. The Preview® product offers the physician the capability to view existing scan data in a format that is more user friendly, and thus enhances the physician's capability to plan treatment. The Preview® product is not intended to provide medical diagnosis or a recommended treatment approach.

The Preview® Treatment Planning Software is intended to provide accurate, alternative two-dimensional images, as well as three-dimensional models, of patient specific anatomy from existing two-dimensional scan data of organs and tissues. The Preview® product offers the physician the capability to view existing scan data in a format that is more user friendly, and thus enhances the physician's capability to plan treatment. The Preview® product is not intended to provide medical diagnosis or a recommended treatment approach.

This Premarket Notification (510(k)) for the Preview® Treatment Planning Software describes the device and claims substantial equivalence to a predicate device, the Preview™ Surgery Planning Software. It does not contain a study demonstrating that the device meets acceptance criteria. The document is primarily a comparison against a predicate device to establish substantial equivalence for regulatory approval.

Therefore, most of the requested information regarding acceptance criteria, study details, sample sizes, expert involvement, and ground truth establishment is not present in the provided text.

Here's what can be extracted and what is missing:

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

The document provides a comparison of features between the new device (Preview® Treatment Planning Software) and its predicate (Preview™ Surgery Planning Software) to show substantial equivalence, rather than a direct table of acceptance criteria and performance against those criteria. The implicit acceptance criteria are that the new device performs at least as well as, or offers additional features beyond, the predicate device.

Study Proving Device Meets Acceptance Criteria:

The provided document does not describe a specific study designed to prove the device meets pre-defined acceptance criteria in the manner usually associated with an AI/ML medical device performance study. Instead, it relies on a comparison to a predicate device to establish substantial equivalence. The "study" here is essentially the comparison table provided, demonstrating that the new device possesses capabilities that are either identical to or enhanced compared 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):

• Sample size for test set: Not mentioned.
• Data provenance: Not mentioned. The document describes software for viewing existing scan data, implying it could use various clinical image data, but no specific dataset for testing is detailed.
• Retrospective or prospective: Not mentioned.

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):

• Number of experts: Not mentioned.
• Qualifications of experts: Not mentioned.

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

• Adjudication method: Not mentioned.

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:

• MRMC study: No, an MRMC comparative effectiveness study is not described. The device is a "Treatment Planning Software" intended to provide "accurate, alternative two-dimensional images, as well as three-dimensional models" and enhance the physician's capability to plan treatment, not to provide medical diagnosis. It's a visualization and measurement tool, not an AI diagnostic algorithm that assists human readers in lesion detection or diagnosis.
• Effect size: Not applicable, as no such study was conducted or described.

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

• This device is a software tool for physicians to use with existing scan data. Its purpose is to enhance the physician's capability, not to operate as an autonomous diagnostic algorithm. Therefore, a "standalone algorithm-only" performance study in the sense of an AI diagnostic tool is not applicable and not described.

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

• Given the nature of the device as a visualization and measurement tool, the "ground truth" for its accuracy would likely relate to the fidelity of its reformatted images, 3D models, and measurements compared to the input 2D scan data and established anatomical references. However, the specific method for establishing this ground truth is not described in the document.

8. The sample size for the training set:

• Sample size for training set: Not mentioned. This document describes a software product, not necessarily an AI/ML algorithm that requires a "training set" in the conventional sense. While it processes existing scan data, the text does not indicate that it uses machine learning trained on a dataset.

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

• Ground truth for training set: Not applicable/Not mentioned, as a training set and its associated ground truth are not described for this software product.

Ask a specific question about this device