(164 days)
The indications for use of the Hewlett-Packard CentralVue Software are:
- Condition: the clinician decides to centrally monitor up to 8 adult, pediatric, and/or neonatal patients:
and for the embedded STAR: - Condition: the clinician decides to monitor cardiac arrhythmia of adult, pediatric, and/or neonatal patients and/or ST segment of adult patients.
- Part of body or type of tissue interacted with: None, all patient connections are made by other remote devices.
- Frequency of use: As prescribed by clinician.
- Physiological purpose: To gain information for treatment, to monitor adequacy of treatment, or to rule out causes of symptoms.
- Prescription versus over-the-counter: Central-Vue Software is a prescription device.
CentralVue Software is a centralized patient monitoring application that executes on an NT Workstation and operates on data received from other networked medical devices. CentralVue Software displays physiologic waves and parameters, provides retrospective review of physiologic waves and parameters and provides the secondary annunciation of alarms for up to eight patients at a centralized location. CentralVue Software embeds STAR ST Segment and Arrhythmia analysis for up to eight patients. CentralVue Software can format data for compliant strip chart recorders such as the CentralVue Recorder.
This submission does not contain enough information to complete the requested table and answer the questions thoroughly. The provided text, K9CC4832 from May 15, 1997, describes the "CentralVue Software" and its functionalities, indications for use, and a general statement about its verification and validation. However, it lacks specific details about acceptance criteria, actual device performance metrics, study methodologies, sample sizes, ground truth establishment, or expert involvement relating to a performance study.
Here's how I can (or cannot) answer each point based on the provided text:
1. A table of acceptance criteria and the reported device performance
- Cannot create. The document mentions "STAR ST Segment and Arrhythmia monitoring software embedded in CentralVue Software was tested to assure that it performed as disclosed in an earlier submission." This implies that acceptance criteria and performance data for the STAR component exist in another document, but they are not disclosed in this text. There are no specific performance metrics (e.g., sensitivity, specificity, accuracy, detection rates for arrhythmias or ST segment changes) outlined for CentralVue Software itself or the embedded STAR component within this document.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Cannot answer. The document generally states "When the black box, gray box, white box, and STAR regression tests were completed a separate test group validated that CentralVue Software meets its performance claims and is safe and effective in its intended use." This indicates testing occurred, but no details about the sample size of patients, data sets, or their provenance (country, retrospective/prospective) are provided.
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)
- Cannot answer. There is no mention of experts or how ground truth was established for any performance testing.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Cannot answer. The document does not describe any adjudication methods used for testing or validation.
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
- Cannot answer. The document describes a "centralized patient monitoring application" with "embedded STAR ST Segment and Arrhythmia analysis." It does not describe a study involving human readers or comparing their performance with and without AI assistance. This device's function is to display data and provide analysis, not to assist humans in interpreting images in a way that would require an MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Partially addressed, but not with specific performance data. The STAR ST Segment and Arrhythmia monitoring is described as "software that run in the monitoring mode." This implies a standalone algorithmic function. However, details of its standalone performance (e.g., sensitivity, specificity for arrhythmia detection) are not provided in this document, only that it "was tested to assure that it performed as disclosed in an earlier submission."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Cannot answer. The document does not specify the type of ground truth used for any testing.
8. The sample size for the training set
- Cannot answer. The document does not mention a "training set" or "training" in the context of machine learning. The STAR ST Segment and Arrhythmia monitoring software is mentioned, but its development process (e.g., whether it uses machine learning with training data) is not elaborated upon in this text.
9. How the ground truth for the training set was established
- Cannot answer. As no training set is mentioned, the method for establishing its ground truth is also not mentioned.
§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).
(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.