(56 days)
The monitor monitors parameters such as ECG (3-lead or 5-lead selectable), Respiration (RESP), Functional arterial oxygen saturation (SpO2), Invasive or non-invasive blood pressure (dual-IBP, NIBP), Temperature (dual-TEMP), Expired CO2.
The monitor is intended to be used only under regular supervision of clinical personnel. It is applicable to adult, pediatric, and neonatal usage in a hospital environment and during patient transport inside a healthcare facility.
The monitor is equipped with alarms that indicate system faults (such as loose or defective electrodes), physiologic parameters that have exceeded the limits set by the operator, or both.
iM8 Series Patient Monitor 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 abnormity so that doctors and nurses can deal with them in time. The patient monitor supports software upgrade online and networking and build-in battery power is available for all the models.
iM8 Series Patient Monitor can monitor physiological parameters including SpO2, NIBP, ECG, RESP, TEMP, CO2, IBP. The above is the maximum configuration, the user may select different monitoring parameters in according with the requirement.
iM8 Series patient monitor includes three models iM8, iM8B, from the view of the below table, screen size is the primary difference for three models.
This document is a 510(k) summary for a traditional patient monitor, not an AI/ML device. Therefore, the detailed information typically required for an AI/ML study, such as acceptance criteria, sample sizes for training/test sets, expert qualifications, and specific AI/ML performance metrics, is not present. This submission focuses on demonstrating substantial equivalence to predicate devices through functional and safety testing, not on new algorithm performance.
Here's an analysis of the provided text based on the questions, acknowledging the limitations for an AI/ML context:
1. A table of acceptance criteria and the reported device performance
Based on the provided text, there are no specific quantitative "acceptance criteria" or "reported device performance" metrics explicitly stated in a table format as one would expect for an AI/ML device's efficacy study. The document focuses on establishing substantial equivalence to predicate devices for several physiological parameters.
The closest we get to "performance" is the statement: "have the same or similar performance specifications" in the comparison with predicate devices. This implies that the device is expected to perform at least comparably to the legally marketed predicate devices without detailing specific numerical targets.
The device description mentions it "can perform long-time continuous monitoring of multiple physiological parameters" and "is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormity." These are functional descriptions rather than quantifiable performance metrics with acceptance criteria.
Note: For a traditional medical device like a patient monitor, "acceptance criteria" would typically refer to accuracy, precision, and range specifications for each physiological parameter (e.g., NIBP accuracy within ±X mmHg, SpO2 accuracy within ±Y%) as measured against a gold standard. These details are not elaborated in this 510(k) summary; instead, they are covered by demonstrating equivalence to predicate devices which have already met such benchmarks.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The provided text does not specify any sample size for testing. It mentions "Verification and validation testing was done on the Patient Monitor" and lists types of tests like "Software testing," "Hardware testing," "Safety testing," "Environment test," and "Risk analysis." However, it does not detail the methodology, subject count, or data provenance (country, retrospective/prospective) for these tests.
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)
This information is not provided in the document. As this is a traditional patient monitor, the "ground truth" for physiological measurements would typically be established through direct comparison with reference instruments or clinical standards, rather than expert consensus on interpreted data as might be the case for an AI/ML diagnostic device.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided. Given it's a traditional device focusing on measurement accuracy and functional safety, an adjudication method like 2+1 or 3+1 (common for expert review in AI/ML studies) would generally not be applicable.
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, an MRMC comparative effectiveness study was not done. This type of study is specifically relevant for AI-assisted diagnostic or interpretive devices where human performance with and without AI is compared. The Edan Instruments patient monitor is a traditional monitoring device, not an AI/ML system, and therefore, this type of study is not applicable and not mentioned.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device itself is a "standalone" patient monitor in the sense that its measurements and alarms are generated by the device's inherent algorithms and sensors. However, this is not "standalone (algorithm only without human-in-the-loop performance)" in the context of an AI/ML diagnostic or interpretive algorithm. The monitor is designed to be used "under regular supervision of clinical personnel," meaning a human is always in the loop to respond to the monitor's output. The document does not describe performance of the algorithms in isolation from the full device system.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not explicitly state the type of ground truth used. However, for a device measuring physiological parameters like ECG, SpO2, NIBP, TEMP, and CO2, the ground truth would typically be established using:
- Reference instruments/gold standard devices: For parameters like blood pressure, temperature, and SpO2, highly accurate and calibrated reference devices would be used for comparison.
- Physiological simulators or controlled environments: To test accuracy across various conditions.
- Clinical observations/direct physiological measurements: For ECG and respiration, direct physiological signals from subjects or phantoms would be compared to the device's interpretation.
8. The sample size for the training set
This information is not provided and is not applicable in the context of this traditional patient monitor 510(k) submission. "Training sets" are specific to AI/ML development, which this device does not appear to utilize in the sense of a learning algorithm.
9. How the ground truth for the training set was established
This information is not provided and is not applicable for the reasons stated above (traditional device, no mention of AI/ML training).
§ 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.