(27 days)
The Infinity CentralStation (ICS) is intended for use by trained healthcare professionals for the purpose of centralized monitoring of adult, pediatric and neonatal patient data within the hospital or clinical environment. Centralized monitoring involves the display and management of data from networked patient monitors including the annunciation of visual and audible physiologic parameter alarms at a central monitoring workstation. Infinity CentralStation with REST ECG is intended for the production and interpretation of diagnostic electrocardiograms for adult and pediatric patients when connected to a monitor with diagnostic 12-Lead ECG monitoring enabled.
The Infinity M300 is intended for use with the ICS to monitor ECG and pulse oximetry on ambulatory and non-ambulatory adult and pediatric patients using wireless communication over the Infinity patient monitoring network.
The Infinity M300 with TruST is intended for 12-Lead ECG monitoring with a reduced set of electrodes. Reconstructed leads are intended for real-time assessment of ST segment changes.
The Infinity CentralStation® (ICS) is an information technology workstation that gathers and displays data for simultaneous central monitoring and critical care management of up to 32 patient monitors connected to the Infinity Network using an optional dual-screen configuration. The ICS system consists of a central processing unit (CPU), one or two displays, a keyboard and a mouse. If an optional second monitoring unit is configured, an additional 32 patients can be monitored, for a total of 64 patients. The ICS acquires and displays waveforms, parameters and alarms from Infinity bedside monitors and Infinity M300.
The Infinity M300® is a patient-worn transceiver that uses the ICS as the primary patient monitoring display and primary alarm source. The M300 provides continuous ambulatory monitoring for the following parameters:
- ECG including heart rate, arrhythmia, and ST segment analysis
- Pulse oximetry including SpO2, pulse plethysmogram waveform, and pulse rate
The M300 has a color display for displaying parameter information, waveforms, and alarms. It also has a rechargeable battery that can be charged using the bedside charger or the central charger. The M300 is restricted to be used on one patient at a time. The M300 also includes the following accessories:
- M300 bedside charger
- M300 central charger
- M300 programming kit
This document is a 510(k) summary for the Draeger Infinity CentralStation with Infinity M300, a physiological patient monitoring system. It primarily focuses on demonstrating substantial equivalence to a predicate device and outlines the device's intended use and technical specifications. It does not contain information about specific acceptance criteria, study findings, model performance metrics, sample sizes, ground truth establishment, or expert involvement as typically required for evaluating the performance of an AI/ML powered device.
Therefore, I cannot fulfill your request for the detailed table and study information as it is not present in the provided text. The document is concerned with regulatory clearance based on substantial equivalence and safety/effectiveness testing against established standards, not a specific performance study for an AI algorithm.
Here's what I can extract from the provided text, highlighting the absence of the requested AI/ML specific information:
1. A table of acceptance criteria and the reported device performance
- Information not provided. The document states: "The modified Infinity CentralStation with Infinity M300 has been tested in accordance with applicable standards and internal design control procedures and was determined to be as safe and effective for its intended use as the predicate devices." This is a general statement of compliance, not a report of specific performance metrics against acceptance criteria. The relevant standards listed are for electromagnetic compatibility (IEC 60601-1-2: 2007).
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Information not provided. No details on a test set sample size or data provenance are mentioned.
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)
- Information not provided. The device is a physiological monitor, not an interpretive AI system that would typically require expert-established ground truth in this context.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Information not provided. Not applicable given the nature of the device and information provided.
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
- Information not provided. This device is a monitoring system, not an AI-assisted diagnostic tool for human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Information not provided. The device performs physiological monitoring, including arrhythmia detection and ST segment analysis, which are algorithmic functions, but the document does not detail specific "standalone performance studies" in the context of an AI/ML algorithm being evaluated. Its performance is evaluated for safety and effectiveness against predicate devices and standards.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Information not provided. For physiological monitoring, ground truth would typically come from standardized simulated signals, known clinical cases validated by other medical equipment, or direct physiological measurements, but the document does not elaborate on how "ground truth" was established for its internal performance evaluations.
8. The sample size for the training set
- Information not provided. There is no mention of a "training set" as this document does not describe an AI/ML model development or validation.
9. How the ground truth for the training set was established
- Information not provided. Not applicable.
In summary, this document is a regulatory submission for a medical device that monitors physiological parameters. It does not provide the kind of detailed performance and validation data typically associated with studies proving an AI/ML device meets specific acceptance criteria.
§ 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.