(24 days)
The Unity Network ID is indicated for use in data collection and clinical information management through networks with independent bedside devices. The Unity Network ID is not intended for monitoring purposes, nor is the Unity Network ID intended to control any of the clinical devices (independent bedside devices/ information systems) it is connected to.
The Unity Network ID system communicates patient data from sources other than GE Medical Systems Information Technologies equipment to a clinical information system, central station, and/or GE Medical Systems Information Technologies patient monitors. The Unity Network ID acquires digital data from eight serial ports, converts the data to Unity Network protocols, and transmits the data over the monitoring network to a Unity Network device such as a patient monitor, clinical information system or central station.
The provided text describes a medical device called "Unity Network ID," which is a device for data collection and clinical information management through networks with independent bedside devices. It is not a device that involves AI (Artificial Intelligence) or machine learning algorithms for diagnostic or prognostic purposes, and therefore, many of the requested categories related to algorithm performance, training data, ground truth, and expert evaluation are not applicable.
The document discusses compliance with voluntary standards and quality assurance measures for the development of the system. The "Test Summary" indicates that the Unity Network ID was subjected to various testing phases to ensure its safety and effectiveness.
Here's an attempt to answer the questions based on the available information, noting when information is not present or not applicable to this type of device:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria Category | Specific Criteria | Reported Device Performance | Comments |
|---|---|---|---|
| System Reliability/Safety | Compliance with voluntary standards detailed in Section 9 of the submission (not explicitly detailed in provided text). | "The Unity Network ID complies with the voluntary standards as detailed in Section 9 of this submission." | The specific standards and their detailed requirements are not provided in the extracted text. |
| Design & Development Quality | - Risk Analysis conducted |
- Requirements Reviews conducted
- Design Reviews conducted
- Unit level testing (Module verification)
- Integration testing (System verification)
- Final acceptance testing (Validation)
- Performance testing conducted
- Safety testing conducted
- Environmental testing conducted | All listed quality assurance measures were "applied to the development of the system." | This indicates process adherence rather than specific quantitative performance metrics. The results of these measures "demonstrated that the Unity Network ID is as safe, as effective, and performs as well as the predicate devices." |
| Functional Equivalence | As safe, as effective, and performs as well as the predicate device (K021524 Unity Network ID). | "The results of these measurements demonstrated that the Unity Network ID is as safe, as effective, and performs as well as the predicate devices." | No specific performance metrics (e.g., data transfer rates, error rates) are provided to quantify "as well as." |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document describes testing phases (unit, integration, final acceptance, performance, safety, environmental testing) for the device's functionality and safety, not for an AI algorithm's diagnostic or predictive performance on a patient data set. Therefore, there is no mention of a "test set" in the context of patient data, sample size, or data provenance (country, retrospective/prospective) for evaluating an AI's performance. The testing would have involved the device itself and its interaction with other systems.
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)
This is not applicable as the device is a data collection and management system, not an AI diagnostic tool that requires ground truth established by medical experts on patient data.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set) for the test set
This is not applicable for the same reason as point 3.
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
An MRMC study is not applicable because the Unity Network ID is a data infrastructure device, not an AI system that assists human readers in interpreting medical cases.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This is not applicable as there is no AI algorithm being evaluated for standalone performance. The device itself is a standalone hardware/software system designed for data management.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
This is not applicable. The "ground truth" for this device would relate to its ability to correctly acquire, convert, and transmit digital data as per its specifications, rather than clinical outcomes or expert consensus on medical conditions. The "ground truth" would be defined by the expected behavior and data integrity within the network.
8. The sample size for the training set
This is not applicable. The device does not involve machine learning; therefore, there is no "training set" in the context of AI model development.
9. How the ground truth for the training set was established
This is 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).