Search Results

The device is intended to be used for measuring, storing, and to generate prompts for, multiple physiological parameters of adults and pediatrics (including neonates). The device is intended for use by trained healthcare professionals in hospital environments. Parameters include: NIBP, SpO2, PR (pulse rate), TEMP. The F3000 Quick Temp module is not intended for neonates. The device is not intended for MRI environments.

The iM3s series vital signs monitors including iM3s\iM3As\iM3Bs\ iHM3s are intended to be used for measuring, storing, reviewing of, and generating prompts for multiple physiological parameters of adults and pediatrics.

The provided documentation describes the FDA 510(k) clearance for the Edan Instruments Vital Signs monitor, Model: iM3s, iM3As, iM3Bs, iHM3s. However, the document primarily focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance testing and software verification/validation, rather than detailing a clinical study with specific acceptance criteria for AI/algorithm performance.

Therefore, many of the requested details regarding acceptance criteria, sample size, expert involvement, and ground truth establishment for a study proving device performance in an AI/algorithm context are not applicable or not provided in this specific FDA clearance document. The device is a vital signs monitor, not explicitly described as incorporating AI for diagnosis or interpretation that would necessitate an MRMC study or detailed ground truth establishment in the context of AI performance.

The document states "Clinical data: Not applicable," further confirming the absence of a clinical study for this clearance.

Here's a breakdown based on the information available in the document:

1. A table of acceptance criteria and the reported device performance:

The document refers to compliance with consensus standards for device performance, where the "acceptance criteria" are implied by adherence to these standards and the "reported device performance" is that the device "meets its accuracy specification and meet relevant consensus standards." Specific numerical acceptance criteria are mentioned for the measurement accuracy of SpO2, PR, and NIBP, and various temperature modules.

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

• The document explicitly states "Clinical data: Not applicable." The "test set" for performance was conducted through "Non-clinical data" including "Electrical safety and electromagnetic compatibility (EMC)" and "Performance testing-Bench."
• No specific sample sizes (e.g., number of patients/measurements) for "bench" testing are provided.
• Data provenance (e.g., country of origin, retrospective/prospective) is not applicable given no clinical study.

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

• Not applicable as no clinical ground truth or expert-adjudicated test set was used. Device performance was assessed against established engineering and safety standards.

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

• Not applicable as no clinical test set requiring adjudication was used.

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:

• No MRMC study was performed as this device is a vital signs monitor, not an AI-assisted diagnostic device requiring human reader improvement assessment. Clinical data was deemed "Not applicable."

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

• The performance assessment focused on the device's ability to accurately measure vital signs according to specifications and consensus standards (e.g., IEC 80601-2-30 for NIBP, ISO 80601-2-56 for temperature, ISO 80601-2-61 for pulse oximetry). This is essentially a "standalone" performance evaluation of the measurement algorithms within the device against physical standards, but not in the context of an AI-driven diagnostic algorithm.

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

• For the non-clinical performance testing, the "ground truth" would be the reference measurements from calibrated and traceable sources, as specified by the relevant international standards (e.g., simulated physiological signals/conditions, calibrated temperature sources, etc.).

8. The sample size for the training set:

• Not applicable. This document describes the clearance of a vital signs monitor, not an AI/machine learning algorithm requiring a separate training set.

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

• Not applicable, as no AI training set is described.

Ask a specific question about this device