(187 days)
+ACG is a Clinical Decision Support device that only matches data to Hospital-defined protocols to generate Alarms and Advisories. +ACG uses data from multiple sources including medical devices and healthcare information systems.
Medical Facilities use their clinical protocols, and policies to define clinically relevant alarms and advisory criteria. Talis then configures Alarms and Advisories within +ACG to be used by the Medical Facility
Talis EMR software is an Electronic Medical Record intended to support patient care documentation compliant with patient care record and billing requirements. Talis EMR leverages a non-device MDDS to acquire, transmit, store, and display electronic patient information available from multiple electronic sources including other EMRs and medical devices. Talis EMR provides no clinical recommendations, performs no assessment of patient conditions, and uses no proprietary algorithms. Display or access to patient data is not intended to influence the judgement of the healthcare professional user. Talis EMR software functions are either non-device software functions or software functions for which FDA has determined to exercise enforcement discretion.
+ACG software is an alarm notification system which may be configured to notify health care professionals when alarm or advisory conditions are identified based on patient data matching the Medical Facility defined alarm or advisory condition criteria. +ACG alarm/advisory notifications are limited to alarm or advisory conditions defined by the Medical Facility.
Medical Facilities use their clinical practices, protocols, and policies to define clinically relevant alarms and advisory criteria. Talis then configures Alarms and Advisories within +ACG to be used by the Medical Facility's clinical physicians or appropriate medical staff under the direction of physicians. +ACG is intended to support the Medical Facility's efforts to improve compliance to their patient care protocols and achievement of their quality initiatives.
+ACG software only works with Talis EMR software.
The provided text does not contain information about specific acceptance criteria and a study that proves the device meets those criteria in the traditional sense of a clinical performance study with predefined metrics (e.g., sensitivity, specificity, accuracy).
Instead, this document is a 510(k) Premarket Notification from the FDA, which focuses on establishing substantial equivalence to a predicate device based on technological characteristics and safety.
Here's an analysis of what is present in the document related to "acceptance criteria" and "proof":
The document indicates that the Talis EMR with +ACG device has undergone non-clinical testing to demonstrate compliance with various harmonized and international standards, which can be seen as the "acceptance criteria" for its safety, software lifecycle, usability, cybersecurity, and electrical safety.
Here's a breakdown based on your requested information:
1. A table of acceptance criteria and the reported device performance
The document does not present a table of quantitative acceptance criteria (e.g., "sensitivity > X%", "specificity > Y%") and reported performance metrics for the device's core function (+ACG alarm notification) as one might expect from a diagnostic or AI-driven decision support system that provides specific diagnoses or predictions.
Instead, the "acceptance criteria" are compliance with established regulatory and technical standards. The "reported device performance" is that the device has passed these tests.
| Acceptance Criteria (Standard Compliance) | Reported Device Performance |
|---|---|
| Software Lifecycle: ANSI AAMI IEC 62304:2006/A1:2016 (Medical device software – Software life cycle processes) | Has passed all safety tests for demonstrated compliance. Certified. |
| Usability Engineering: ANSI AAMI IEC 62366-1:2015+AMDI:2020 (Medical devices – Part 1 Application of usability engineering to medical devices) | Has passed all safety tests for demonstrated compliance. Certified. Human factors and usability testing completed. |
| Alarm Systems: ISO 60601-1-8 Edition 2.2 2020-07 (Medical electrical equipment – Part 1-8: General requirements for basic safety and essential performance – Collateral standard: General requirements, tests, and guidance for alarm systems in medical electrical equipment and medical electrical systems.) | Alarm and advisory signals comply with the international standard. |
| Information Security Management Systems: ISO 27001: 2017 (Information technology – Security techniques – Information security management systems – Requirements) | Cybersecurity processes and controls demonstrate compliance, certified by TUV SUD, assessed by 3rd party vulnerability and penetration testing. |
| Electrical Equipment Safety: IEC 60601-1 Edition 3.1 (Medical electrical equipment – Part 1: General requirements for basic safety and essential performance) (for Talis Hub hardware) | Tested to all applicable sections of the standard, certified by UL. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document states: "Talis EMR with +ACG, like the predicate device, did not require clinical trials." It details non-clinical tests (standards compliance, software validation, usability validation, risk management). Therefore, there is no specific "test set" sample size with patient data in the context of clinical performance evaluation mentioned. The testing focused on technical compliance, not clinical outcomes from a patient dataset.
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)
Since no clinical test set (i.e., patient data requiring independent ground truth establishment) was used, this information is not applicable and not provided. The "ground truth" for this device's function would be the accurate implementation of hospital-defined protocols and the correct generation of alarms/advisories based on inputted data, which is verified through software validation and functional testing against those pre-defined rules, rather than expert interpretation of patient cases.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable as no clinical test set requiring expert adjudication was used.
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 MRMC comparative effectiveness study was done or reported. The device is a "Clinical Decision Support device that only matches data to Hospital-defined protocols to generate Alarms and Advisories." It is explicitly stated: "It is not intended to replace clinicians' judgement, but rather to assist clinicians in making timely, informed decisions." And "+ACG Alarms are not intended to be relied upon in deciding to take immediate clinical action." This indicates it's not a diagnostic or primary monitoring tool that would typically be evaluated with MRMC studies for improved human interpretation.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
While the device's function is algorithm-only in matching data to protocols, the "performance" described is about its compliance with technical standards and its ability to generate alarms based on configured rules, rather than a standalone clinical performance evaluation against a diagnostic ground truth. The document does not describe such a standalone performance study with clinical outcomes metrics.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the functional aspect of the +ACG software, the "ground truth" would be the hospital-defined protocols and criteria for generating alarms and advisories. The device's "performance" is its ability to accurately implement these pre-defined rules. The document implies verification and validation activities were performed against these defined rules, as part of software validation.
8. The sample size for the training set
Not applicable. The +ACG software is described as a "Clinical Decision Support device that only matches data to Hospital-defined protocols." This indicates a rule-based expert system or a system configured with user-defined logic, rather than a machine learning model that requires a "training set" of data for learning patterns.
9. How the ground truth for the training set was established
Not applicable for the same reason as point 8.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).