(312 days)
The monitor is intended to be used for monitoring, storing, and reviewing of, and to generate alarms for, multiple physiological parameters of adults, pediatrics and neonates. The monitor is intended for use by trained healthcare professionals in hospital environments.
Monitored parameters include: NIBP, SpO2, PR (pulse rate), Quick TEMP/Infrared TEMP.
The monitor is not intended for MRI environments. TEMP module is not intended for neonates.
The iM3 has three work modes, Monitor, Spot and Round, to measure physiological parameters, including non-invasive blood pressure (NIBP), oxygen saturation of the blood (SpO2), pulse rate (PR), and Quick TEMP/Infrared TEMP (TEMP).
• For the Monitor mode, the user can do continuous measurement, monitoring, alarming and manager patient data.
• For the Spot mode, also call spot check mode, the user can measure parameters quickly without creating a patient within the instrument workflow.
• The Round mode is designed to support hospital staff when doing ward rounds. The Round mode is similar as Spot mode. The difference between Round mode and Spot mode is that for one ward round, the iM3 can additionally store one ward round record automatically (the latest measurement) or manually (user can choose the measure results).
iM3 capabilities include storing, displaying measuring data. When necessary, alarms will be produced so that doctors and nurses can manage patient care appropriately.
The iM3can connect with EDAN's MFM-CMS Central Monitoring System to display the iM3 data on a remote work station. The MFM-CMS system received FDA 510(k) clearance on June 21, 2013(K120727)
The provided text is a 510(k) summary for the Edan Instruments iM3 Vital Signs Monitor, seeking FDA clearance based on substantial equivalence to predicate devices. This type of submission focuses on demonstrating that a new device is as safe and effective as a legally marketed predicate device.
The document does not describe a study that proves the device meets specific acceptance criteria in the context of an AI/ML algorithm being developed or tested against a ground truth for diagnostic or prognostic performance. Instead, it discusses the performance as it relates to comparison with a predicate device and compliance with established medical device standards.
Therefore, many of the requested details related to AI/ML validation studies (like sample size for test sets, data provenance, expert adjudication, MRMC studies, standalone performance, ground truth establishment for training/test sets) are not applicable to this document as it describes a traditional vital signs monitor seeking 510(k) clearance, not an AI/ML diagnostic or prognostic device.
However, based on the provided text, I can infer and extract information relevant to the device's functional performance criteria and what was demonstrated:
Acceptance Criteria and Reported Device Performance (Inferred from comparison to predicate and standard compliance):
The "acceptance criteria" here are implicitly defined by the performance specifications of the predicate devices and relevant IEC/ISO standards for vital signs monitors. The reported device performance is presented as being "similar" to the predicate and compliant with these standards.
1. Table of Acceptance Criteria and Reported Device Performance
| Parameter / Criterion | Acceptance Criteria (from predicate/standards) | Reported iM3 Device Performance |
|---|---|---|
| NIBP (EDAN Module) | ||
| Principle of Operation | Oscillation | Oscillation |
| Measurement Range (Adult) | Systolic 40 to 270 mmHg, Diastolic 10 to 215 mmHg, Mean 20 to 235 mmHg | Systolic 40 to 270 mmHg, Diastolic 10 to 215 mmHg, Mean 20 to 235 mmHg |
| Measurement Range (Ped.) | Systolic 40 to 200 mmHg, Diastolic 10 to 150 mmHg, Mean 20 to 165 mmHg | Systolic 40 to 230 mmHg, Diastolic 10 to 180 mmHg, Mean 20 to 195 mmHg (Note: iM3 measurements are wider, but still within acceptable ranges as per relevant standards) |
| Measurement Range (Neonate) | Systolic 40 to 135 mmHg, Diastolic 10 to 100 mmHg, Mean 20 to 110 mmHg | Systolic 40 to 135 mmHg, Diastolic 10 to 100 mmHg, Mean 20 to 110 mmHg |
| Accuracy | Maximum average error: ±5 mmHg, Maximum standard deviation: 8 mmHg | Maximum average error: ±5 mmHg, Maximum standard deviation: 8 mmHg |
| SpO2 (EDAN Module) | ||
| Measurement Range (SpO2) | 0-100% | 0-100% |
| Saturation Accuracy | Adult/pediatric, non-motion: 70 to 100% ±2 %. Neonate: 70 to 100% ±3% (0-69% unspecified for both) | Adult/pediatric, non-motion: 70 to 100% ±2 %. Neonate: 70 to 100% ±3% (0-69% unspecified for both) |
| Measurement Range (PR) | 25 to 300 bpm | 25 to 300 bpm |
| Pulse Rate Accuracy | Adult and Neonate: 25 to 300 bpm ±2bpm (non-motion conditions) | Adult and Neonate: 25 to 300 bpm ±2bpm (non-motion conditions) |
| TEMP (EDAN Quick Temp) | ||
| Measurement Range (Monitor) | 25 °C ~45 °C | 25 °C ~45 °C |
| Accuracy (Monitor mode) | ±0.1 °C (25 °C ~ 45 °C) | ±0.1 °C (25 °C ~ 45 °C) |
| Clinical Bias | (-0.2 to -0.4 )°C | (-0.2 to -0.4 )°C |
| Limits of Agreement | 0.49 | 0.49 |
| Electrical Safety | Compliance with: ANSI/AAMI ES60601-1:2005/(R)2012 and A1:2012, IEC 60601-1-8: 2006, IEC 60601-2-49: 2011, IEC 80601-2-30:2009, ISO 80601-2-56: 2009 and ISO 80601-2-61:2011 standards. | The system complies with specified standards. Coexistence testing was also performed and adheres to FDA guidance on Radio Frequency Wireless Technology in Medical Devices. |
| EMC | Compliance with IEC 60601-1-2: 2014 standard. | The system complies with specified standard. |
| Software | Compliance with FDA's "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." | Software verification and validation testing were conducted, and documentation was provided as recommended by FDA guidance. |
2. Sample size used for the test set and the data provenance:
- This document does not specify a "test set" in the context of an AI/ML model, but rather refers to performance validation against established standards.
- The comparison data presented in the tables are physical performance specifications of the device modules, not patient data from a clinical trial in the AI/ML sense. Actual human testing for NIBP, SpO2, and TEMP accuracy would have been done to meet the standards (e.g., ISO 81060-2:2013 for NIBP, ISO 80601-2-61: 2011 for SpO2, ISO 80601-2-56 for TEMP), but the specifics (sample sizes, provenance) are not detailed in this summary. These physical performance tests are typically done in controlled lab settings or with human subjects as required by the specific standard.
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):
- Not applicable as this is not an AI/ML diagnostic device requiring expert consensus on image interpretation or similar. The "ground truth" for vital signs monitoring validation is typically measured physiological parameters from reference devices.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not 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:
- Not applicable.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable. The device directly measures physiological parameters. Its performance is inherent to its sensors and processing, and the accuracy claims are against reference measurements, not an independent algorithm being evaluated.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- The ground truth for the performance claims would be highly accurate reference measurements from precisely calibrated medical devices or established physiological measurement techniques (e.g., intra-arterial blood pressure for NIBP, co-oximetry for SpO2, highly accurate thermometers for TEMP). The document states compliance with relevant ISO/IEC standards which dictate the methods for determining accuracy, including the reference methods.
8. The sample size for the training set:
- Not applicable. This is a vital signs monitor, not a machine learning algorithm that requires a "training set" for its core function.
9. How the ground truth for the training set was established:
- Not applicable.
§ 870.2700 Oximeter.
(a)
Identification. An oximeter is a device used to transmit radiation at a known wavelength(s) through blood and to measure the blood oxygen saturation based on the amount of reflected or scattered radiation. It may be used alone or in conjunction with a fiberoptic oximeter catheter.(b)
Classification. Class II (performance standards).