(377 days)
The CMS8000 Patient Monitor is intended to be used for monitoring, displaying, reviewing, storing and alarming of multiple physiological parameters including ECG, Heart Rate (HR), Respiration Rate (RESP), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure (IBP), carbon dioxide (CO2), and Temperature (TEMP) of adult, pediatric and neonatal patient. The Pulse Oxygen Saturation (SpO2) and Pulse Rate (PR) are intended use for adult and pediatric patient. The monitor is to be used in healthcare facilities by clinical physicians or appropriate medical staff under the direction of physicians. It is not intended for helicopter transport or hospital ambulance.
The proposed device, CMS8000 Patient Monitor is intended to be used for monitoring, displaying, reviewing, storing and alarming of multiple physiological parameters. It has the physical and technical alarming function with audio and visual alarming, The device can driven by AC or DC power supply.
The provided 510(k) summary for the Contec Medical Systems CMS8000 Patient Monitor discusses performance testing but does not explicitly provide a table of acceptance criteria and reported device performance in the format requested. It also does not include information on sample sizes for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, or training set details as typically expected for advanced AI/ML device submissions.
However, based on the provided text, here's what can be extracted and inferred:
1. Table of Acceptance Criteria and Reported Device Performance
The document mentions that performance testing was conducted to "validate and verify that the proposed device, the Patient Monitors met all design specifications." It specifically states clinical tests were performed for SpO2 and NIBP according to ISO 9919 and AAMI SP10 standards. These standards themselves contain acceptance criteria relevant to the performance of pulse oximeters and automated sphygmomanometers. While the document doesn't report the specific acceptance criteria or the numerical results to populate the table directly, it implicitly states that the device met these standards.
Inferred Table Structure (Based on common practice for similar devices and standards):
| Performance Metric | Acceptance Criteria (Implied by Standards) | Reported Device Performance |
|---|---|---|
| SpO2 Accuracy (for different ranges) | Defined by ISO 9919 (e.g., RMS difference between device and reference within a certain limit across various SpO2 levels) | Met ISO 9919:2005 standard |
| NIBP Accuracy (systolic, diastolic, mean) | Defined by AAMI SP10 (e.g., mean difference and standard deviation between device and reference measurements within certain limits) | Met AAMI SP10:2002 standard |
| ECG Performance | Defined by AAMI / ANSI EC13:2002/(R) 2007 (e.g., accuracy of heart rate detection, alarm performance) | Met AAMI / ANSI EC13:2002/(R) 2007 standard |
| Respiration Rate (RESP) Accuracy | Not explicitly stated but would be part of general design specifications | Met all design specifications (implied) |
| Invasive Blood Pressure (IBP) Accuracy | Defined by IEC 60601-2-34:2000 | Met IEC 60601-2-34:2000 standard |
| CO2 Measurement Accuracy | Defined by ISO 21647:2004 | Met ISO 21647:2004 standard |
| Temperature (TEMP) Accuracy | Not explicitly stated but would be part of general design specifications | Met all design specifications (implied) |
2. Sample size used for the test set and the data provenance
The document states: "Performance testing including clinical and bench testing was conducted to validate and verify that the proposed device, the Patient Monitors met all design specifications."
- Sample Size for Test Set: Not specified in the provided text. The standards (ISO 9919, AAMI SP10) would dictate minimum sample sizes for their respective clinical validation components, but these numbers are not present here.
- Data Provenance: The document does not explicitly state the country of origin of the data or whether it was retrospective or prospective. It only generically mentions "clinical test" for SpO2 and NIBP functions.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided in the given text. While clinical tests were conducted, details about who established the ground truth (e.g., reference measurements by qualified clinicians) are absent.
4. Adjudication method for the test set
This information is not provided in the given text.
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 is not mentioned in the provided text. The device is a patient monitor, not an AI-assisted diagnostic imaging tool where MRMC studies are typically relevant. This submission predates the widespread regulatory focus on AI/ML in medical devices.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This concept is not applicable in the context of this traditional patient monitor device. The device inherently provides parameters for human interpretation and action. Its performance is measured directly against reference standards, not as an "algorithm only" component separate from human interaction in the way AI/ML algorithms often are.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Based on the mentioned standards for validation:
- For SpO2 (ISO 9919): Ground truth is typically established using a reference oximeter in controlled desaturation studies or by comparing to arterial blood gas measurements (co-oximetry values).
- For NIBP (AAMI SP10): Ground truth is typically established by simultaneous auscultatory measurements performed by trained observers using a mercury sphygmomanometer or another validated reference method.
- For other physiological parameters (ECG, IBP, CO2, RESP, TEMP): Ground truth would be established by comparison to reference measurement devices or validated clinical methods.
The document does not explicitly state these methods but references to the standards imply adherence to their ground truth methodologies.
8. The sample size for the training set
This information is not applicable/provided. The CMS8000 Patient Monitor, as described (submitted in 2011), is a traditional physiological monitor, not an AI/ML device that requires a "training set" in the modern sense. Its algorithms are based on established physiological principles and signal processing, not statistical learning from large datasets.
9. How the ground truth for the training set was established
This information is not applicable/provided for the same reason as point 8.
§ 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.