Search Results

The monitors are intended to be used for monitoring, storing, recording, and reviewing of, and to generate alarms for, multiple physiological parameters of adults and pediatrics. The monitors are intended for use by trained healthcare professionals in hospital environments. The monitored physiological parameters include: ECG, respiration (RESP), temperature (TEMP), oxygen saturation of arterial blood (SpO2), pulse rate (PR), non-invasive blood pressure (NIBP), invasive blood pressure (IBP), carbon dioxide (CO2), cardiac output (C.O.), and Anaesthesia gas(AG). The arrhythmia detection and ST Segment analysis are intended for adult patients. The monitors are not intended for MRI environments.

The iM series Patient Monitor including iM50, iM60, iM70 and iM80 can perform long-time continuous monitoring of multiple physiological parameters. Also, it is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormalities so that doctors and nurses can respond to the patient's situation as appropriate.

Based on the provided text, the device in question is a Patient Monitor (Model: iM50, iM60, iM70, iM80), which monitors various physiological parameters. The document focuses on demonstrating substantial equivalence to a predicate device, rather than providing detailed acceptance criteria and a standalone study for a novel AI device. Therefore, much of the requested information regarding AI-specific evaluation (e.g., sample size for AI test sets, expert adjudication, MRMC studies, AI effect size, ground truth establishment for training) is not applicable or not present in this 510(k) summary.

However, I can extract information related to the device's self-contained performance testing and regulatory acceptance criteria.

Acceptance Criteria and Device Performance for Patient Monitor (iM Series)

The document primarily relies on bench testing and software verification and validation to demonstrate that the iM series Patient Monitor meets its accuracy specifications and relevant consensus standards, thereby establishing substantial equivalence to a predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present explicit "acceptance criteria" in a quantitative table for this specific device in the manner typically seen for novel AI models. Instead, it compares the technical specifications of the subject device to a predicate device and states that "the results of the bench testing show that the subject device meets its accuracy specification and meet relevant consensus standards."

The comparison table (pages 5 & 6) implicitly indicates that "acceptance" for the subject device's performance corresponds to ranges/specifications that are identical or comparable to the cleared predicate device.

Notes on the 'AG Module': The document explicitly states for the AG (Anesthesia Gas) module that its "indication is not present in the primary predicate, but is present in Edan Patient Monitor V series K160981." This implies that while it differs from the immediate primary predicate, it is substantially equivalent to a different, already cleared, predicate device from the same manufacturer.

2. Sample size used for the test set and the data provenance

• Sample Size: The document does not specify a distinct "test set" sample size in terms of patient data or number of tests. The performance data section refers to "functional and system level testing" and "bench testing." This implies testing against specifications and standards rather than a clinical dataset of a specific size.
• Data Provenance: Not specified. Given it's a bench test, it would typically be conducted in a laboratory setting. There's no mention of country of origin for test data, nor whether it's retrospective or prospective patient data, as clinical data was deemed "Not applicable."

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable. This is a physiological monitor, not an AI diagnostic device requiring expert consensus for ground truth on images or signals. The "ground truth" for the device's performance would be derived from calibrated measurement references and established engineering principles in bench testing.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Not applicable. As above, this is not an AI diagnostic device relying on human expert review for ground truth.

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

Not applicable. This device is a physiological monitor, not an AI-assisted diagnostic tool that requires human readers for interpretation.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The device's performance in terms of its physiological measurements and alarm detection is inherently "standalone" in that it performs these functions without direct human intervention in the measurement process itself, generating outputs for healthcare professionals. The bench testing performed would be considered evaluating this standalone performance against technical specifications and standards.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

For the non-clinical performance (bench testing), the "ground truth" is based on:

• Calibration standards: Using known, precise inputs (e.g., electrical signals simulating ECG, precise pressures for NIBP, known gas concentrations for CO2/AG) to verify the accuracy of the device's measurements.
• Consensus Standards: Adherence to recognized international standards for medical electrical equipment (e.g., IEC 60601 series, ISO 80601 series). These standards define acceptable performance limits and test methodologies.

8. The sample size for the training set

Not applicable. This document does not describe an AI/ML device that requires a "training set" in the conventional sense. The device's algorithms are likely based on established physiological signal processing, not deep learning models trained on large datasets.

9. How the ground truth for the training set was established

Not applicable, as there is no "training set" for an AI/ML model described.

Ask a specific question about this device