Search Results

The leva Pelvic Health System is intended for:

1. Strengthening of the pelvic floor muscles;
2. Rehabilitation and training of weak pelvic floor muscles for the treatment of stress, mixed and mild to moderate urgency urinary incontinence (including overactive bladder) in women;
3. Rehabilitation and training of weak pelvic for the first-line treatment of chronic fecal incontinence (>3month uncontrolled passage of feces) in women.
   This device interacts with the user via smart phone technology.

The leva Pelvic Health System ("leva PHS" or "leva System") is a prescription intra-vaginal device designed to allow the user to rehabilitate and strengthen their pelvic floor muscles ("PFM") as well as allow them to monitor their progress during pelvic floor muscle training ("PFMT"). The leva system is designed to wirelessly facilitate PFMT in women and to transmit real-time performance data through a dedicated mobile application that has been downloaded onto the patient's mobile device. The leva system is designed to be used vaginally and is intended to be used repeatedly by a single patient.

The provided text describes clinical studies for the Renovia leva Pelvic Health System, but it does not specifically mention acceptance criteria or a study designed to universally "prove the device meets acceptance criteria" for a diagnostic or AI-driven system.

Instead, the document details two clinical studies (REN-17 and REN-19) that support the expanded indications for use of the device, particularly for fecal incontinence. These studies serve to demonstrate the device's safety and effectiveness for its intended use, thereby establishing substantial equivalence to a predicate device.

Here's an analysis based on the information provided, tailored to address the points in the prompt, with a strong caveat that the traditional "acceptance criteria" and "study proving it meets acceptance criteria" framework, as typically applied to diagnostic AI, is not explicitly present here. The studies focus on clinical effectiveness and safety rather than specific technical performance metrics of an AI algorithm.

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

The document does not present explicit "acceptance criteria" in the format of a diagnostic performance target (e.g., sensitivity > X%, specificity > Y%). Instead, the studies aim to demonstrate clinical improvement and non-inferiority/superiority in patient-reported outcomes for fecal incontinence. The performance is measured by changes in clinical scores.

2. Sample size used for the test set and the data provenance

• REN-17 (Single-arm study for primary effectiveness):
  • Test set (Effectiveness Analysis): 26 participants
  • Test set (Safety Analysis): 27 participants
  • Data provenance: United States only, prospective.
• REN-19 (RCT Subset Analysis for fecal incontinence symptoms):
  • Test set (Effectiveness/Safety Analysis): 92 participants (44 in leva-02 arm, 48 in control arm).
  • Data provenance: United States only, prospective (subset of a larger RCT).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This information is not provided in the document. For this type of device (pelvic floor muscle training biofeedback), the "ground truth" is typically established by patient-reported outcomes (like St. Mark's Score, CRADI-8, CRAIQ-7), which are subjective measures of symptoms and quality of life, rather than objective assessments requiring expert interpretation of raw data. The device provides biofeedback, and the clinical studies assess the impact of that biofeedback on patient outcomes.

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

This information is not provided and is generally not applicable to studies relying primarily on validated, self-reported patient questionnaires for primary endpoints. The CRADI-8 and CRAIQ-7 are validated patient-reported symptom scales. St. Mark's Score is also a validated questionnaire completed by the patient, though occasionally a clinician might administer it.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The leva Pelvic Health System is a biofeedback device for pelvic floor muscle training, not an AI-driven diagnostic imaging or interpretation tool that assists human readers. The clinical studies compare its effectiveness in improving clinical outcomes (like fecal incontinence symptoms and quality of life) against standard care (unassisted Kegel exercises) or against baseline, but not in the context of an AI-assisted diagnostic workflow involving human readers.

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

This question is not applicable in the traditional sense for this device. The device itself is a "human-in-the-loop" system by design, providing real-time biofeedback to the user during exercises. Its "performance" is measured by its impact on clinical outcomes when used by patients, not by an algorithm's isolated diagnostic accuracy. The text states that the device transmits biofeedback to an app, and the previous 510(k) comparison indicates the "Principle of Operation" is "Provides indication of relative position of pelvic floor muscle contraction using accelerometers." This refers to its sensing capabilities. The clinical studies assess the overall effect of using this system (device + app + patient interaction) on health outcomes.

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

The ground truth for effectiveness was established using patient-reported outcomes data from validated questionnaires:

• St. Mark's Score (Vaizey) for fecal incontinence severity (REN-17).
• FIQoL (Fecal Incontinence Quality of Life) for different aspects of quality of life (REN-17).
• CRADI-8 (Colorectal-Anal Distress Inventory, Short Form) for fecal incontinence symptoms (REN-19 subset).
• CRAIQ-7 (Colorectal-Anal Impact Questionnaire Short Form) for condition-specific quality of life (REN-19 subset).

Fecal incontinence diagnosis itself was based on pre-defined screening criteria reported by participants.

8. The sample size for the training set

The document does not specify a training set sample size because the reported studies (REN-17 and REN-19) are clinical trials designed to assess the device's efficacy and safety in human subjects, not to train a machine learning model. While the device certainly has internal software and algorithms that might have been developed using some data, these clinical studies are distinct from the paradigm of "AI training sets."

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

As there is no explicit "training set" described in the context of AI model development, this question is not directly applicable. If one were to consider the broader development cycle of the device, the "ground truth" for the device's biofeedback mechanism (e.g., accurately reflecting pelvic floor muscle contraction) would have been established through engineering validation and verification testing, likely comparing accelerometer data to known movements or potentially against electromyography (EMG) or pressure-based perineometry, but this is not detailed in the provided clinical study summaries. The clinical studies use actual patient outcomes as their measure of effectiveness.

Ask a specific question about this device

The leva Pelvic Health System is intended for:

1. Strengthening of the pelvic floor muscles;

2. Rehabilitation and training of weak pelvic floor muscles for the treatment of stress, mixed and mild to moderate urgency urinary incontinence (including overactive bladder) in women.

This device interacts with the user via smart phone technology.

The leva Pelvic Health System ("leva System") is a prescription intra-vaginal device designed to allow the user (or woman) to rehabilitate and strengthen their pelvic floor muscles (PFM) as well as allow them to monitor their progress during pelvic floor muscle training (PFMT). The leva system is designed to wirelessly facilitate PFMT in women and to transmit real-time performance data through a dedicated mobile application that has been downloaded onto the patient's mobile device. The leva system is designed to be used vaginally and is intended to be used repeatedly by a single patient.

The leva PHS consists of a probe, storage case, associated batteries, and the Renovia Digital Health App (App). Thermoplastic elastomer (TPE) was used as the material overlay for the electronics and six accelerometers are contained within the probe. Additional electronics are contained in the storage case to transmit data wirelessly between the device and the App.

The provided text describes a 510(k) premarket notification for the "leva Pelvic Health System." It primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device (K192270, leva Pelvic Digital Health System) based on technological characteristics and non-clinical testing.

Crucially, this document does NOT contain information about a study proving the device meets specific performance acceptance criteria related to its clinical efficacy or accuracy using AI. It mainly discusses hardware, firmware, and software changes, and non-clinical testing (biocompatibility, software/firmware design verification, manufacturing testing). Therefore, I cannot fulfill most of the requested information about acceptance criteria for device performance, clinical study design, expert ground truth, or MRMC studies, as these types of details are not present in the provided 510(k) summary.

The device is a perineometer that provides an indication of the relative intensity of pelvic floor muscle contraction using accelerometers. Its intended use is for strengthening, rehabilitation, and training of weak pelvic floor muscles for the treatment of stress, mixed, and mild to moderate urgency urinary incontinence.

Here's what can be extracted from the provided text:

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

  • Acceptance Criteria: The document does not explicitly state quantitative acceptance criteria for device performance (e.g., accuracy, sensitivity, specificity, or improvement thresholds for a specific clinical outcome). The "acceptance" discussed is related to demonstrating substantial equivalence through non-clinical testing.
  • Reported Device Performance: The document states that "Biocompatibility testing demonstrated that the subject device, leva Pelvic Health System, is as safe and effective, and performs as well as the predicate device, leva Pelvic Digital Health System." It also mentions "Software and firmware design verification testing" and "Manufacturing testing protocol verification" were done to ensure the device continues to meet requirements for substantial equivalence. However, specific performance metrics or thresholds are not provided.

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

  • Not provided. The document focuses on non-clinical testing (biocompatibility, software verification, manufacturing testing) and does not describe a clinical test set with human subject 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):

  • Not applicable/Not provided. No clinical test set with ground truth established by experts is described in this document.

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

  • Not applicable/Not provided. No clinical test set requiring adjudication is described.

• 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:

  • No. This document does not describe an AI-assisted device or an MRMC study. The device provides "indication of relative intensity of pelvic floor muscle contraction using accelerometers" and transmits data to a mobile app for user monitoring and guidance. It does not appear to employ AI for diagnostic or assistive interpretation requiring human reader studies.

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

  • Not applicable/Not provided. The device's primary function is to measure muscle contraction and provide data to the user via an app for rehabilitation purposes, not to provide an automated diagnosis or interpretation in a "standalone" fashion as might be expected from a typical AI algorithm in medical imaging.

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

  • Not specified/Not applicable to a clinical study. The "ground truth" implicitly referred to is safety and performance equivalence to the predicate device, demonstrated through non-clinical tests (biocompatibility, software/firmware design verification, manufacturing testing).

• 8. The sample size for the training set:

  • Not applicable/Not provided. This document does not pertain to the development or validation of an AI model with a training set.

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

  • Not applicable/Not provided. No AI model training set is discussed.

Summary of available information regarding the device itself:

• Trade/Device Name: leva Pelvic Health System
• Regulation Number: 21 CFR §884.1425
• Regulation Name: Perineometer
• Regulatory Class: II
• Product Code: HIR
• Intended Use:
  1. Strengthening of the pelvic floor muscles.
  2. Rehabilitation and training of weak pelvic floor muscles for the treatment of stress, mixed, and mild to moderate urgency urinary incontinence (including overactive bladder) in women.
• Principle of Operation: Provides indication of relative intensity of pelvic floor muscle contraction using accelerometers.
• Key changes from predicate (minor modifications):
  • Hardware (adhesive, PCB/PCBA, battery vendor, labeling)
  • Embedded software (firmware: performance improvement, communications, diagnostic, bug fixes)
  • Mobile Application Software (bug fixes, content updates like educational videos)
  • Manufacturing and Risk Analysis updates
• Testing performed to support substantial equivalence (non-clinical):
  • Biocompatibility (ISO 10993-1, -5, -10)
  • Software and firmware design verification testing
  • Manufacturing testing protocol verification

Ask a specific question about this device