(162 days)
The TelePatch Cardiac Monitor PM750, is a pager-sized, handheld or patient worn device designed specifically to record and transmit ambulatory ECG signals. The device is designated as Rx only, to be worn by infants to adults of all ages. The device can be worn for days or weeks, as it is intended for use by patients who are experiencing symptoms that are transient and infrequent in nature.
TelePatch Cardiac Monitor PM750 is a small, auto triggered, device, prescribed by physicians for patients who are experiencing symptoms that may be attributable to cardiac arrhythmia. Shortness of breath and palpations are examples of these symptoms. This device may be worn for a period of days or weeks - whatever time is necessary to capture and record the ECG. The PM750 has two operating modes to allow for event analysis of the recorded ECG or in Holter mode to allow for full disclosure analysis of the recorded ECG. The device is comprised of the function contained within the CardioPAL SAVI (Model PM410) ECG loop recorder and the SAVI Wireless (Model PM500) event monitor and an off the shelf cellular phone. The device can be used with a break-away lanyard and has interaction with a PC interface cable.
The provided text describes the 510(k) summary for the TelePatch Cardiac Monitor PM750. This document focuses on demonstrating substantial equivalence to predicate devices based on various engineering and safety standards, rather than presenting a performance study with acceptance criteria for an AI algorithm.
Therefore, the requested information regarding acceptance criteria, device performance, sample sizes for test and training sets, data provenance, expert ground truth establishment, adjudication methods, MRMC studies, and standalone performance for an AI algorithm is largely Not Applicable in the context of this 510(k) summary.
The document primarily discusses compliance with electrical safety, EMC, usability, and biological evaluation standards, and compares the technical specifications and indications for use of the new device to its predicates.
Here's a breakdown of what can be extracted and what cannot:
1. A table of acceptance criteria and the reported device performance
- Not Applicable in the context of AI performance.
- The document mentions conformance to various medical device standards (e.g., AAMI/ANSI/IEC 60601-1, IEC 60601-1-2, AAMI/ANSI/IEC 60601-2-47, ISO 14971, IEC 62366, ISO 10993-5, ISO 10993-10). The "reported device performance" is that it meets the requirements of these standards and is "substantially equivalent" to the predicate devices. These are engineering and safety performance criteria, not diagnostic accuracy or AI performance metrics.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not Applicable. The document explicitly states "Discussion of Clinical Tests Performed: Not Applicable." This indicates a clinical performance study (which would typically involve test sets and data provenance for evaluating diagnostic output) was not performed or deemed necessary for this 510(k) clearance based on substantial equivalence to predicate devices.
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. As no clinical performance study was reported, there was no test set requiring expert-established ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not Applicable. No clinical performance study was reported.
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 an "Ambulatory Electrocardiographic System" and a "Radiofrequency Physiological Signal Transmitter and Receiver," not an AI diagnostic algorithm for which an MRMC study would typically be performed.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not Applicable. This document describes a physical medical device for recording and transmitting ECG signals, not a standalone AI algorithm. While it has an "Electrocardiograph, Ambulatory with Analysis Algorithm" (product code MLO), no specific performance study of this algorithm in a "standalone" fashion is detailed in this 510(k) summary. The analysis algorithm is part of the on-board analysis capability and comparisons are made at a high level ("Yes" for on-board analysis across all devices).
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
- Not Applicable. No clinical performance study was reported.
8. The sample size for the training set
- Not Applicable. This 510(k) summary does not describe the development or training of a new AI algorithm.
9. How the ground truth for the training set was established
- Not Applicable. This 510(k) summary does not describe the development or training of a new AI algorithm.
Summary based on the provided document:
The K161916 510(k) summary for the TelePatch Cardiac Monitor PM750 demonstrates substantial equivalence to predicate devices (CardioPAL SAVI PM410 and SAVI Wireless PM500) based on non-clinical testing and comparison of their technological characteristics and indications for use. The testing performed focused on compliance with various engineering, safety, and usability standards for medical electrical equipment. No clinical studies or specific performance metrics related to an AI algorithm's diagnostic accuracy or reader improvement were reported or deemed necessary for this clearance.
§ 870.2910 Radiofrequency physiological signal transmitter and receiver.
(a)
Identification. A radiofrequency physiological signal transmitter and receiver is a device used to condition a physiological signal so that it can be transmitted via radiofrequency from one location to another, e.g., a central monitoring station. The received signal is reconditioned by the device into its original format so that it can be displayed.(b)
Classification. Class II (performance standards).