Search Results

The prolaio eVO2peak Module (Version 1.0) is an all-software medical device intended to be used for estimating peak oxygen consumption (eVO2peak (mL/kg/min)) in adult patients for whom such VO2 Peak cardiopulmonary functional testing is desired.

The prolaio eVO2peak Module uses as inputs: demographic data and single-lead electrocardiogram (sampled at least 125 Hz) and triaxial accelerometry data (sampled at 50 Hz) from qualified third-party FDA-cleared wearable medical sensors from patients carrying out activities of daily living.

The prolaio eVO2peak Module is intended to provide information as an adjunctive aid in the clinical evaluation of patients by qualified clinicians who have the responsibility for interpreting its significance in connection with other standard of care clinical findings.

The prolaio eVO2peak Module is not intended to be used as a diagnostic, for active patient monitoring, to be solely relied upon for determining patient status, or as an alarm device.

The prolaio eVO2peak Module is a software-only Class II SaMD Python library. It processes stored physiologic data—single-lead ECG and triaxial accelerometry. The module applies a locked deep-learning model trained against reference VO2 Peak from cardiopulmonary exercise test (CPET). The module returns mean eVO2peak and contextual information allowing clinicians to use eVO2peak in concert with other clinical signs and parameters.

Here's an analysis of the acceptance criteria and study proving the device meets those criteria, based on the provided FDA 510(k) clearance letter for the prolaio eVO2peak Module:

Acceptance Criteria and Reported Device Performance

Details of the Study Proving Acceptance Criteria

1. Sample sized used for the test set and the data provenance:

   • Sample Size: 228 patients.
   • Data Provenance: Data from multiple centers in the United States. The study was a "clinical study," suggesting it was prospective in nature, though not explicitly stated. The patients were "demographically diverse and representative of the intended population."

2. 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 clearance letter. The ground truth was established by "cardiopulmonary exercise tests (CPET)," which is a standard clinical procedure for measuring VO2 Peak, but the number and qualifications of experts interpreting or validating these CPET results are not detailed.

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

   • This information is not provided in the clearance letter. As the ground truth is CPET, a highly standardized physiological test, an adjudication method for establishing ground truth might not be applicable in the same way it would be for subjective clinical assessments.

4. 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, an MRMC comparative effectiveness study was not done. The prolaio eVO2peak Module is a standalone software device that provides an estimate, not a tool for human readers to interpret images or assist in diagnosis. Its purpose is to provide an adjunctive aid for clinicians, implying it generates information to be considered alongside other clinical findings, rather than assisting in image interpretation.

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

   • Yes, a standalone performance study was done. The reported performance metrics (Mean Error, Mean Absolute Error) are directly from the prolaio eVO2peak Module's output compared against the ground truth CPET measurements. The device is described as an "all-software medical device" and a "locked deep-learning model," indicating standalone algorithm performance.

6. The type of ground truth used:

   • CPET (Cardiopulmonary Exercise Test) measurements were used as the reference standard for VO2 Peak. This is considered outcomes data for this specific physiological parameter.

7. The sample size for the training set:

   • This information is not explicitly provided in the clearance letter. It states the deep-learning model was "trained against reference VO2 Peak from cardiopulmonary exercise test (CPET)," but does not give the size of this training dataset.

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

   • The ground truth for the training set was established using "reference VO2 Peak from cardiopulmonary exercise test (CPET)." This implies the same method as the ground truth for the test set, leveraging a standardized physiological test.

Ask a specific question about this device