Search Results
Found 1 results
510(k) Data Aggregation
(189 days)
The Sickbay Clinical Platform is software that is intended to route and store medical device data and device diagnostic information from supported devices to the Electronic Medical Record (EMR) and Clinical Information Systems.
The Sickbay Clinical Platform is a remote monitoring platform that displays physiologic data, waveforms and alarms routed through the Sickbay Clinical Platform for supported devices. The Sickbay Clinical Platform is intended to be used by healthcare professionals in a hospital setting for the following purposes:
- To remotely consult, regarding a patient's status .
- To remotely review other standard or critical near real-time patient data, . waveforms and alarms in order to utilize this information to aid in clinical decisions and deliver patient care in a timely manner.
WARNING: The Sickbay Clinical Platform is intended to supplement and not to re-place any part of the hospital's device monitoring. Do not rely on the Sickbay Clinical Platform product as the sole source of alarms.
Note: Sickbay Clinical Platform product includes 3 Apps: Patient Monitoring App; Patient Alarm Data Monitor & Alarm Analytics Dashboard App.
Medical Informatics Corp (MIC) has developed a software platform and analytics engine, Sickbay™, which gathers physiological data streams coming from patient monitoring devices and other clinical data sources. Medical Informatics Corp's software platform, Sickbay, captures patient data and enables near real-time display and analytics for clinicians to use in clinical decision support.
The Medical Informatics Corp's Sickbay™ Clinical Platform is a software device intended to route, store, and display medical device data, waveforms, and alarms from supported devices to an Electronic Medical Record (EMR) and Clinical Information Systems. It also acts as a remote monitoring platform for healthcare professionals in a hospital setting for patient status consultation and review of real-time patient data to aid in clinical decisions.
Here's an analysis of its acceptance criteria and the supporting study, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
Performance Test | Applicable Standard | Acceptance Criteria | Reported Device Performance |
---|---|---|---|
Usability | IEC 62366 | Compliance with standard | Complies |
Software Life-Cycle | IEC 62304, AAMI TIR 45 | Compliance with standards | Complies |
Human Factors | AAMI/ANSI HE75 | Compliance with standard | Complies |
Health Informatics | IEEE 11073-10406 | Compliance with standard | Complies |
Risk Management | ISO 14971 | Compliance with standard | Complies |
Alarm systems in Medical Electrical Equipment and Medical Electrical system | IEC 60601-1-8 | Compliance with standard | Complies |
Basic Safety and Essential Performance of Electrocardiographic Monitoring Equipment | IEC 60601-2-27 | Compliance with standard | Complies |
The document states that "This testing showed the Sickbay to meet applicable ISO, IEC and FDA safety and performance standards. And guidances." This indicates that the reported device performance met the specified acceptance criteria for each test.
2. Sample Size Used for the Test Set and Data Provenance
The provided document does not specify any specific sample size for a test set or the data provenance (e.g., country of origin, retrospective/prospective) for these performance tests. The listed tests are primarily "non-clinical bench testing" and relate to software development, usability, risk management, and compliance with general medical device standards, rather than direct performance evaluation on patient data.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not mention the use of experts to establish a "ground truth" for any specific test set. The tests performed are compliance-based (e.g., software development, usability guidelines, risk management standards), which do not typically require expert-established ground truth in the same way clinical performance studies do.
4. Adjudication Method for the Test Set
As no specific test set requiring ground truth or adjudication is described, there is no mention of an adjudication method (e.g., 2+1, 3+1, none) in the provided text.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. The document states: "PERFORMANCE TESTING - ANIMAL/CLINICAL: There has been no animal/clinical testing submitted with this Notification." The device is intended to display data for human review, but its performance was not evaluated through a study comparing human readers with and without AI assistance.
6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance)
The document primarily describes a software platform that processes, stores, and displays data. While it includes "Alarm Analytics Dashboard App," the core functionality is data management and display. The listed performance tests are primarily related to general software, usability, and safety standards for medical devices. There is no mention of a standalone performance study specifically evaluating the algorithm's diagnostic or analytical performance without human intervention in a clinical context (e.g., for detecting specific conditions). The device's function is to aid in clinical decisions, not to make them independently.
7. Type of Ground Truth Used
Given the "non-clinical bench testing" nature of the studies, the "ground truth" used is adherence to established technical standards, regulations, and specifications (e.g., IEC, ISO, IEEE for software, safety, usability, and health informatics). There is no use of expert consensus, pathology, or outcomes data as ground truth for these specific compliance tests.
8. Sample Size for the Training Set
The document does not provide any information on a training set or its sample size. This is consistent with the nature of the device being a data management and display platform, rather than a diagnostic AI that requires supervised learning with labeled training data.
9. How the Ground Truth for the Training Set Was Established
As no training set is mentioned or implied for the performance evaluation, there is no information on how its ground truth would have been established.
Ask a specific question about this device
Page 1 of 1