(121 days)
The LifeShirt Real-Time is intended for use during daily activities of living and sleep, for the purpose of recording physiological data for later analysis by a physician. Respiration, ECG, pulse oximetry, blood pressure, temperature, and body position data may be collected. The system is intended to provide analysis of breathing patterns as an aid in classifying apneas as well as displaying heart rate changes from electrocardiographic waveforms in the wake and sleeping states as well as activities of daily living. The LifeShirt Real-Time is indicated for reuse by multiple adult patients in applications that may include pharmaceutical studies in which respiratory information is a useful indicator, or the general healthcare market where patients may be monitored at home and the data provided to their physicians as an aid to diagnosis and treatment.
The LifeShirt Real-Time consists of the following components: the LifeShirt garment, LifeShirt Recorder/Transmitter, a wireless flash card, a data Flash Card, VivoMonitor™ real-time software and VivoLogic® analysis and reporting software. A cleared pulse oximeter, blood pressure cuff, and a temperature sensor are optional accessories provided for use with the device.
This 510(k) summary focuses on modifications to an existing device, the LifeShirt, rather than a standalone study of a new medical device. As such, the information provided primarily addresses the equivalence of the modified device to its predicate, with limited detail on specific performance acceptance criteria and study data in the format requested for a new device's comprehensive performance evaluation.
Here's an analysis based on the provided text, highlighting the limitations due to the nature of this 510(k):
1. Table of acceptance criteria and the reported device performance
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Accurate data transmission and reception (for newly added wireless capabilities) | "Performance testing included verification that data recorded by the LifeShirt recorder is accurately transmitted and received by the PC computer system." (Details on specific metrics or thresholds are not provided.) |
| Electromagnetic Compatibility (EMC) | "In addition, testing was performed to demonstrate electromagnetic compatibility." (Details on specific standards or results are not provided.) |
| Safety and Effectiveness equivalence with predicate device | "Performance data demonstrates that the LifeShirt Real-Time is as safe and effective as the predicate Multiple Patient Use LifeShirt." (Specific quantitative data is not provided.) |
Explanation: The document describes a "Special 510(k)" submission, which is used for modifications to a legally marketed device that do not significantly alter its fundamental scientific technology or intended use. For such submissions, the FDA typically focuses on demonstrating that the changes do not raise new questions of safety or effectiveness and that the modified device remains substantially equivalent to its predicate. Therefore, the "acceptance criteria" here are largely implied to be maintaining the performance of the predicate device, with specific verification of the new features (wireless communication and temperature probe).
2. Sample size used for the test set and the data provenance
The document does not specify a separate "test set" sample size in the context of clinical data for performance evaluation. The "performance testing" mentioned refers to engineering verification and validation activities for the new features (wireless data transmission, EMC). There is no mention of a pre-defined subject cohort used for clinical performance testing for the modified features.
Data Provenance: Not explicitly stated for specific clinical tests, as the focus is on engineering verification of new features and equivalence to an already cleared device.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable in this Special 510(k). The document describes engineering verification testing, not a clinical study requiring expert-established ground truth for a diagnostic outcome.
4. Adjudication method for the test set
Not applicable. There is no mention of a clinical test set requiring expert adjudication for ground truth.
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
Not applicable. This device is not an AI-assisted diagnostic tool, and no MRMC study is mentioned. The device records physiological data for later analysis by a physician.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This Special 510(k) is about a hardware device with software components, not a standalone algorithm in the typical sense of a diagnostic AI. The "VivoLogic analysis and reporting software" is part of the system for "later analysis by a physician," implying a human-in-the-loop workflow. The performance testing focuses on the accuracy of data transmission and fundamental device capabilities.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not detail the type of ground truth used as it relates to clinical diagnostic accuracy, as this was not a primary focus of this Special 510(k). The "ground truth" for the performance testing mentioned (e.g., accuracy of data transmission) would be engineering standards and successful transfer of data files.
8. The sample size for the training set
Not applicable. This document does not describe a machine learning algorithm that requires a training set for its development. The "VivoLogic processing software" likely uses established algorithms for physiological data analysis, not a learning-based approach that requires a training set in the AI sense.
9. How the ground truth for the training set was established
Not applicable, as there is no mention of a training set for a machine learning algorithm.
§ 870.1425 Programmable diagnostic computer.
(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).