(87 days)
The Marquette Eagle 4000 Patient Monitor is designed to monitor and display patient data. Its design allows the operator to adjust parameter alarm settings that would audibly and visually notify the operator when a violation occurs. The option is provided for printing of information by a paper recorder. Use of the Marquette Eagle 4000 Patient Monitor is intended for patient populations including: adult, pediatric, and/ or neonatal. Use of the Marquette Eagle 4000 Patient Monitor is not recommended for use in patient's home or residence, during patient transport, or when it has not been ordered by a physician or other qualified medical personnel. Use of the Marquette Eagle 4000 Patient Monitor is intended for operating room (OR), post anesthesia recovery, critical care, surgical intensive care, respiratory intensive care, coronary care, medical intensive care, pediatric intensive care, or neonatal intensive care. These departments are typically located in hospitals or may be located in outpatient clinics or free standing surgical centers. It is intended for use by physicians, physician assistants, registered nurses, certified registered nurse anesthetists, or other hospital personnel trained in the use of the equipment.
The Marquette Eagle 4000 Patient Monitor is a patient monitoring system that is designed to be used to monitor a patient's basic physiological parameters including: electrocardiography (ECG), invasive blood pressure, non-invasive blood pressure, oxygen saturation, temperature, respiration, apnea detection, pulse rate, cardiac output, and full arrhythmia analysis. The device now includes Marquette's 12 lead ECG Analysis program (commonly referred to as 12 SL).
The provided text is a 510(k) summary for the Marquette Eagle 4000 Patient Monitor, dated February 2, 1997. This document focuses on demonstrating substantial equivalence to predicate devices for regulatory clearance, rather than conducting a detailed performance study with specific acceptance criteria and detailed quantitative results as might be found in a modern clinical trial or a more recent AI/ML device submission.
Therefore, much of the requested information cannot be extracted directly from this document because it predates the rigorous, quantitative evaluation standards common for AI/ML medical devices today. The summary primarily relies on a general statement of "verification and validation testing" and "accuracy requirements as specified in the contents of the premarket notification submission" without detailing the specifics of these tests or their results.
Here's a breakdown of what can and cannot be answered based on the provided text:
1. A table of acceptance criteria and the reported device performance
- Acceptance Criteria: Not explicitly stated in a quantifiable way in this summary. The summary broadly states that "Test results indicate that the Eagle 4000 Patient Monitor provides an equivalent level or better in performance, when compared to the legally marketed predicate devices when tested to the accuracy requirements as specified in the contents of the premarket notification submission." The "accuracy requirements" themselves are not provided.
- Reported Device Performance: No specific quantitative performance metrics (e.g., sensitivity, specificity, accuracy, error rates) are reported in this summary.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size: Not specified.
- Data Provenance: Not specified.
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/Not specified. The document does not describe the establishment of ground truth by independent experts in a test set, as would be common for AI/ML devices. The "verification and validation testing" likely refers to internal engineering and clinical validation testing against established standards or predicate device performance.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable/Not specified. There is no mention of an adjudication process for a test set.
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. This type of study (MRMC for AI assistance) is not mentioned and is highly unlikely given the device type (patient monitor) and the era (1997). The device provides physiological parameter monitoring and 12-lead ECG analysis, but there's no indication of it being an AI-assisted diagnostic tool that would improve human reader performance in the modern sense.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, implicitly. The performance evaluation would inherently be of the device's algorithms and hardware alone, as it's a patient monitor providing data and analysis. The "verification and validation testing" would assess the accuracy of its measurements and analyses (e.g., ECG, blood pressure, arrhythmia detection) as a standalone system. However, specific results are not provided.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not explicitly defined in the summary. For a patient monitor, ground truth would typically involve:
- Reference Devices: Comparing measurements against highly accurate, calibrated reference instrumentation (e.g., for blood pressure, temperature, oxygen saturation).
- Validated ECG Databases: For the "12 SL" ECG analysis program, ground truth might involve comparisons against widely accepted ECG databases with expert-adjudicated diagnoses, though this is not stated.
- Clinical Observation: For arrhythmia detection, comparison against expert interpretation of concurrent ECG recordings.
- The summary only broadly refers to "accuracy requirements as specified in the contents of the premarket notification submission."
8. The sample size for the training set
- Not applicable/Not specified. The document does not mention "training sets" as it would for a machine learning device. The ECG analysis program would have been developed using a dataset, but it's not characterized as a "training set" in the context of modern ML.
9. How the ground truth for the training set was established
- Not applicable/Not specified. As no "training set" is described, its ground truth establishment is not discussed.
In summary, the provided 510(k) summary from 1997 is a regulatory declaration of substantial equivalence for a patient monitor and does not contain the detailed performance study information, acceptance criteria, or ground truth methodologies that are now standard for AI/ML device submissions. The document's purpose is to demonstrate that the Eagle 4000 is as safe and effective as its predicate devices based on general verification and validation testing, without providing the quantitative specifics you've requested.
N/A