(14 days)
The Tunstall icp triagemanager software application allows the caregiver to review patient information and to motivate and provide educational information to the patient.
The Tunstall icp triagemanager is not intended to provide automated treatment decisions, nor is it to be used as a substitute for a professional healthcare judgment. Clinical judgment and experience by a caregiver are required to check and interpret the patient information delivered.
The Tunstall icp triagemanager is not intended for real-time monitoring, is not an alarm system and may not be used to receive real-time or time-critical data, is not intended for patients requiring direct medical supervision or emergency intervention, and is not intended for direct diagnosis or monitoring.
The icp triagemanager is a web-based, telehealth remote patient monitoring system application used by trained healthcare personnel to access patient's vitals sign data and patient's answers to health related questions.
The icp triagemanager allows healthcare professionals to review patient's information and to provide educational or motivational information to the patients. The software also allows medical personnel to predefine upper and lower limits outside of which communication with caregivers is initiated.
The icp triagemanager is not intended for direct diagnosis or monitoring of patient's conditions, nor is it intended for providing automated treatment decisions or to be used as substitute for professional healthcare judgment. The system is not intended for real-time monitoring of time-critical data, nor is it intended for patients requiring direct medical supervision or emergency intervention.
The icp triagemanager runs on a standard "off-the-shelf" server hosted by the health care facility and allows caregivers to review patient vital signs on the secure website. The patient's physiological data are measured using standard commercially available medical devices designed for home use. These devices communicate via commercially available hub/gateways compatible with the icp triagemanager software installed on the host server. The hub/gateway systems communicate over a secure internet connection to a secure database on the host server running the icp triagemanager software.
The provided document, K122095, is a 510(k) Summary for the Tunstall icp triagemanager system. This document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study with specific acceptance criteria and detailed performance metrics of the device itself.
Therefore, the information required for a table of acceptance criteria and reported device performance (points 1-7) is not explicitly available in this summary. The 510(k) process for this device relies on demonstrating that the new device is as safe and effective as a legally marketed predicate device (K103276, Intel Health Guide Express) without necessarily reporting detailed performance studies against pre-defined acceptance criteria for the new device.
However, I can extract information related to the testing performed, ground truth, and training data based on the provided text, where available.
1. Table of Acceptance Criteria and Reported Device Performance
Not available in this 510(k) summary. The document focuses on demonstrating substantial equivalence to a predicate device.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not explicitly stated in this 510(k) summary for the icp triagemanager. The document mentions "extensive verification and validation testing" but does not detail the size or nature of the test sets used for these evaluations.
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 explicitly stated. Given the nature of the device (a remote patient monitoring software system for reviewing patient vitals and questions, not for direct diagnosis or real-time monitoring), the concept of "ground truth" established by multiple experts in a diagnostic sense might not be directly applicable as it would be for an imaging device. The system relies on data from "standard commercially available medical devices designed for home use" and "clinical judgment and experience by a caregiver" for interpretation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not explicitly stated.
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. The device is a software application for reviewing patient information, not an AI or diagnostic tool that directly assists human readers in interpreting medical images or making diagnoses. Its purpose is to facilitate remote monitoring and communication, alerting caregivers to out-of-range vital signs.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
This concept is somewhat applicable, but not in the sense of a standalone diagnostic algorithm. The device itself is a software system that presents data and triggers alerts based on user-defined thresholds. The document states it "is not intended for direct diagnosis or monitoring of patient's conditions, nor is it intended for providing automated treatment decisions or to be used as substitute for professional healthcare judgment." Therefore, its "standalone" performance would relate to its ability to accurately receive, store, display, and alert based on pre-defined vital sign parameters, which is implicitly covered by "software verification and validation tests."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
As the device's function is data presentation and alerting based on pre-set thresholds, "ground truth" would likely involve:
- Accuracy of data transmission and display: Verifying that data received from connected medical devices is accurately transmitted, stored, and displayed on the platform.
- Accuracy of alert generation: Verifying that the system correctly triggers alerts (email/pages) when vital signs exceed user-defined upper or lower limits.
- Software functionality: Verifying that all features (adding/removing patients, triaging, follow-up, user management, reporting) work as intended.
These "ground truths" would be established through software verification and validation testing, likely against specifications and known correct outputs/behaviors, rather than through clinical expert consensus on diagnostic interpretations.
8. The sample size for the training set
Not applicable. The icp triagemanager is a software application that processes and presents patient data based on pre-defined clinical rules (user-defined thresholds) and existing physiological data from external devices. It is not described as a machine learning or artificial intelligence system that requires a "training set" in the conventional sense for a diagnostic algorithm.
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 model.
§ 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).