Search Results

The SKOUT® system is a software device designed to detect potential colorectal polyps in real time during colonoscopy examinations. It is indicated as a computer-aided detection tool providing colorectal polyps location information to assist qualified and trained gastroenterologists in identifying potential colorectal polyps during colonoscopy examinations in adult patients undergoing colorectal cancer screening or surveillance.

The SKOUT® system is only intended to assist the gastroenterologist in identifying suspected colorectal polyps and the gastroenterologist is responsible for reviewing SKOUT® suspected polyp areas and confirming the presence or absence of a polyp based on their own medical judgment. SKOUT® is not intended to replace a full patient evaluation, nor is it intended to be relied upon to make a primary interpretation of endoscopic procedures, medical diagnosis, or recommendations of treatment/course of action for patients. SKOUT® is indicated for white light colonoscopy only.

The SKOUT® system is a software-based computer aided detection (CADe) system for the analysis of high-definition endoscopic video during colonoscopy procedures. The SKOUT® system is intended to aid gastroenterologists with the detection of potential colorectal polyps during colonoscopy by providing an informational visual aid on the endoscopic monitor using trained software that processes the endoscopic video in real time.

Users will primarily interact with the SKOUT® system by observing the software display, including the polyp detection box and device status indicator signal.

The provided FDA 510(k) clearance letter for the SKOUT® system (K251126) indicates that this submission is for a modified version of a previously cleared device (K241508) and asserts that the "inference algorithms have remained the same, therefore clinical performance remains unchanged from the clinical testing submitted in K213686." This means the detailed clinical performance data and ground truth establishment would likely reside in the K213686 submission, which is not provided in this document.

However, based on the information present in the K251126 clearance letter, we can describe the non-clinical performance testing that was conducted to demonstrate substantial equivalence to the predicate device. The letter explicitly states:

"Algorithm performance testing was performed for evaluation of true positives, false positives, and polyp detection time, with an expanded dataset for the added video processing tower."

This indicates that some form of performance evaluation was done for the algorithm, even if the core clinical performance from K213686 is simply being referenced.

Given the limitations of the provided document, here's a structured response based on the available information, with clear indications where information is not provided in K251126 and would require reviewing K213686:

Acceptance Criteria and Device Performance for SKOUT® System (K251126)

The SKOUT® system (K251126) is a modified version of a predicate device (K241508). The clearance letter explicitly states that "the inference algorithms have remained the same, therefore clinical performance remains unchanged from the clinical testing submitted in K213686." This implies that the core clinical performance metrics and their acceptance criteria were established and met in the K213686 submission.

For the K251126 submission, non-clinical performance testing was conducted to demonstrate substantial equivalence. This included "Algorithm performance testing... for evaluation of true positives, false positives, and polyp detection time, with an expanded dataset for the added video processing tower." However, the specific quantitative acceptance criteria and the reported performance metrics (true positives, false positives, detection time) are NOT provided in this document.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The specific quantitative acceptance criteria and reported device performance (True Positives, False Positives, Polyp Detection Time) for the algorithm from the K251126 submission are NOT explicitly provided in this document. The document refers to the unchanged clinical performance from K213686. The table below represents the types of metrics that would have been evaluated, as stated in the document, but the actual numerical values are missing.

2. Sample Size and Data Provenance for Test Set

• Sample Size Used for Test Set: The document mentions "an expanded dataset for the added video processing tower" for algorithm performance testing. However, the specific sample size (number of cases, images, or polyps) is NOT provided in this document for either the K251126 testing or the referenced K213686 clinical testing.
• Data Provenance: Not explicitly stated in this document. For K251126, it implies additional video data for specific hardware validation. For the core clinical performance (K213686), this information would be detailed in that submission. It is generally assumed, for FDA clearance, that data would represent diverse patient populations.
• Retrospective or Prospective: Not explicitly stated in this document for the algorithm performance testing in K251126. Clinical studies underpinning K213686 might have been retrospective or prospective, but this is not discussed in the provided text.

3. Number and Qualifications of Experts for Ground Truth

• Number of Experts: Not provided in this document for either the K251126 testing or the referenced K213686 clinical testing.
• Qualifications of Experts: Not provided in this document. For ground truth in medical imaging, experts are typically board-certified specialists (e.g., gastroenterologists or pathologists) with significant experience.

4. Adjudication Method for Test Set

• Adjudication Method: Not provided in this document. For K251126, the performance testing was focused on validating the algorithm with expanded data, not necessarily re-establishing clinical ground truth for a human-in-the-loop study. For K213686, the adjudication method for ground truth establishment for polyp detection would be detailed in that submission. Common methods include consensus reading (e.g., 2+1, where two readers agree, or a third adjudicates disagreement) or pathology correlation.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• MRMC Study Conducted: The document for K251126 does not describe an MRMC comparative effectiveness study directly for this submission. It states that "clinical performance remains unchanged from the clinical testing submitted in K213686." An MRMC study would be common for a device that assists human readers (CADe), and such a study would likely have been part of the original K213686 submission to demonstrate clinical benefit.
• Effect Size of Human Reader Improvement: Since an MRMC study is not detailed for K251126, the effect size is not provided here. If such a study was performed for K213686, the effect size (e.g., improvement in adenoma detection rate, per-lesion sensitivity) would be reported in that submission.

6. Standalone (Algorithm Only) Performance

• Standalone Performance Done: Yes, "Algorithm performance testing was performed for evaluation of true positives, false positives, and polyp detection time." This indicates a standalone evaluation of the algorithm's detection capabilities. However, the specific quantitative metrics (e.g., sensitivity, specificity, FROC curves) are NOT provided in this document. It only states that the testing demonstrated "passing results." The document also notes that "SKOUT® is not intended to replace a full patient evaluation, nor is it intended to be relied upon to make a primary interpretation of endoscopic procedures, medical diagnosis, or recommendations of treatment/course of action for patients," reinforcing its role as a CADe tool for human assistance.

7. Type of Ground Truth Used

• Type of Ground Truth: The document implies that ground truth for "potential colorectal polyps" was established for the algorithm performance testing. For a device detecting polyps, the most robust ground truth would generally be histopathology (pathology results) from biopsied/resected lesions. Clinical consensus from expert endoscopists is also commonly used, especially for cases where biopsy might not be performed. The document does not explicitly state the type of ground truth used, but for polyp detection, pathology is gold standard.

8. Sample Size for Training Set

• Sample Size for Training Set: Not provided in this document. The document primarily focuses on the substantial equivalence and validation of changes rather than a full re-description of the training process for the core AI algorithm, as the algorithm itself is stated to be unchanged from K213686.

9. How Ground Truth for Training Set Was Established

• Ground Truth Establishment for Training Set: Not provided in this document. Similar to the test set, the methods for establishing ground truth for the training data (e.g., expert annotations, pathology reports, adjudicated consensus) would have been detailed in the original K213686 submission.

In summary, the provided FDA clearance letter for K251126 confirms that algorithm performance testing (for true positives, false positives, and detection time) was conducted for this submission, particularly with an "expanded dataset for the added video processing tower." However, it relies on the clinical performance established in the predicate's prior submission (K213686) because the core inference algorithms are unchanged. Therefore, many details regarding the clinical acceptance criteria, sample sizes, expert qualifications, and ground truth establishment for the clinical performance aspect are referred to the previous submission and are not present in this document.

Ask a specific question about this device