K Number
K232830
Device Name
Vibrant System
Manufacturer
Date Cleared
2023-12-08

(86 days)

Product Code
Regulation Number
876.5940
Panel
GU
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Vibrant System is an orally administered Capsule that is indicated for the treatment of adults with chronic idiopathic constipation who have not experienced relief of their bowel symptoms by using laxative therapies at the recommended dosage for at least one month.

Device Description

The Vibrant System is designed to mechanically induce peristaltic activity in the colon, thus aiding in relieving constipated patients. Constipation relief is achieved by the Capsule's stimulation in the colon, consequently inducing peristaltic activity which promotes transit and facilitates defecation. The stimulation protocol is designed to activate at specific times during the day (i.e., afternoon and evening). The Vibrant System is comprised of two components: a reusable pod and a single use capsule. The Capsule is expelled from the body during the patient's bowel movements.

AI/ML Overview

This document outlines the acceptance criteria and study proving the device meets those criteria, based on the provided text.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the primary efficacy endpoints of the clinical study, which aim to demonstrate superior performance of the active device over placebo.

Acceptance Criteria (Primary Efficacy Endpoints)Reported Device Performance (mITT Analysis Set)
CSBM1 success rate: An increase of at least one weekly Complete Spontaneous Bowel Movement (CSBM) during at least 6 of the 8 weeks of treatment should be statistically significantly higher in the active arm compared to the placebo arm.CSBM1 success rate (Active Arm): 55.81% (24/43)
CSBM1 success rate (Placebo Arm): 32.08% (17/53)
p-value: 0.0161 (Statistically Significant)
CSBM2 success rate: An increase of at least two weekly CSBM during at least 6 of the 8 weeks of treatment should be statistically significantly higher in the active arm compared to the placebo arm.CSBM2 success rate (Active Arm): 30.23% (13/43)
CSBM2 success rate (Placebo Arm): 22.64% (12/53)
p-value: 0.5099 (Not Statistically Significant)

Conclusion on Acceptance Criteria: The study successfully met the acceptance criteria for the CSBM1 success rate, demonstrating a statistically significant improvement with the active device compared to placebo. The CSBM2 success rate, while numerically higher in the active arm, did not meet the statistical significance criteria. However, the overall study was deemed successful based on the CSBM1 outcome.

2. Sample Size and Data Provenance

  • Test Set Sample Size: 100 subjects were enrolled and randomized in the study.
    • Intend-to-Treat (ITT) analysis set: 100 subjects.
    • Modified Intend-to-Treat (mITT) analysis set: 96 subjects (randomized subjects who met the inclusion criteria).
  • Data Provenance: The study was conducted in the United States (US). It was a prospective, randomized, multi-center, double-blinded, placebo-controlled study.

3. Number of Experts and Qualifications for Ground Truth Establishment (Test Set)

The document does not explicitly state the number of experts used or their qualifications for establishing the ground truth for the test set. The primary efficacy endpoints (CSBM1 and CSBM2 success rates) are based on patient-reported outcomes (Complete Spontaneous Bowel Movements), not expert interpretation of diagnostic images or data. Therefore, expert consensus in the traditional sense for diagnostic accuracy might not be directly applicable here.

4. Adjudication Method (Test Set)

The document does not describe a formal adjudication method (e.g., 2+1, 3+1) for the test set data. Given that the endpoints are based on patient-reported bowel movements, the data would likely be collected directly from subjects and analyzed statistically without a need for expert adjudication in the same way imaging studies might require.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This type of study typically involves multiple human readers interpreting diagnostic data (e.g., medical images) with and without AI assistance to measure the AI's impact on their performance. The Vibrant System is a therapeutic device that directly treats constipation, and its effectiveness is measured by direct physiological outcomes (bowel movements), not by aiding human interpretation of data.

6. Standalone Performance

Yes, a standalone study (algorithm only without human-in-the-loop performance) was done, as the Vibrant System is a device designed to deliver a therapeutic effect independently. The clinical study directly evaluated the device's efficacy in patients by comparing the active device to placebo, without human intervention in the device's mechanism of action or interpretation beyond general patient care.

7. Type of Ground Truth Used

The ground truth used in this study is based on patient-reported outcomes, specifically:

  • Complete Spontaneous Bowel Movements (CSBMs): Number of bowel movements that are spontaneous (not induced by laxatives or suppositories) and complete.
  • Changes from baseline in average straining.
  • Changes from baseline in average stool consistency.
  • Changes from baseline in average bloating.
  • Quality of life measurements.

These are direct measures of the therapeutic effect and patient experience, rather than expert consensus on a diagnostic finding or pathology.

8. Sample Size for the Training Set

The document does not provide information regarding a specific "training set" sample size for an algorithm. The clinical study described is an efficacy study to support the device's safety and effectiveness, not a study to train an AI algorithm. While the device utilizes an "adaptive delay mechanism," the details of its development or any associated training data are not described in this regulatory submission summary.

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

As no specific training set for an AI algorithm is directly mentioned or detailed in the provided document, there is no information on how ground truth for a training set was established. The clinical study's ground truth was established through direct patient outcomes measurement as described in point 7.

N/A