(319 days)
The Commander Flex is for use by patients to collect and transmit general health questions and patient vital sign data (such as weight, blood pressure, glucose, pulse oximetry) between the patient, typically at home, and a health care professional at a remote site.
Commander Flex devices are home health monitoring tools typically used by patients with diseases such as congestive heart failure (CHF), diabetes, chronic obstructive pulmonary disease (COPD) asthma and coronary artery disease (CAD). Patients use Commander Flex to collect and send important health information to their health care team to allow a doctor and other health care team members to act before symptoms worsen. Commander Flex devices have a built-in non-invasive blood pressure measurement system that measures systolic and diastolic blood pressure and displays the readings on the Commander Flex panel. In addition to making blood pressure and heart rate measurements, Commander Flex devices store and transmit data from peripheral devices to remote locations. Commander Flex connects to a user's home phone line or cellular network. It has inputs for peripheral devices such as weight scales, glucose meters, pulse oximeters, thermometers and blood pressure cuff. The display asks health-related questions to obtain objective biometric data such as: weight, blood pressure, glucose, and pulse oximetry. Patients may also answer a series of questions about their current symptoms. The patient can respond Yes or No or select from a list. Commander Flex devices collect data from peripherals and transmit the data using a cellular connection or toll-free telephone number and modelar design of the Commander Flex device allows for selection of the appropriate health monitoring devices for cost-effective patient care. Commander Flex products are for home use. This 510(k) clearance achieves OTC designation for Commander Flex devices. The peripheral devices are used as supplied by the manufacturer. The Commander Flex devices make no interpretation, evaluation, medical judgements or recommendations for treatment. Commander Flex is not used as an emergency response device. Clinical judgment and experience are required to interpret the information transmitted. Commander Flex devices are not intended as a substitute for medical care.
The provided text is a 510(k) summary for the Medtronic Commander Flex device, primarily focusing on its substantial equivalence to previously cleared predicate devices for the purpose of obtaining an Over-The-Counter (OTC) designation. The document does not describe an AI/ML-based device or its performance against acceptance criteria in the context of an AI/ML study.
Therefore, many of the requested elements for describing the acceptance criteria and the study proving the device meets them (such as a table of AI performance metrics, sample sizes for test/training sets, expert adjudication methods, MRMC studies, standalone AI performance, and ground truth establishment for AI) are not applicable to this document as it pertains to a blood pressure measurement system and remote patient monitoring device, not an AI/ML diagnostic tool.
However, based on the provided text, I can infer and extract information relevant to the device's general performance and the studies conducted to demonstrate its capabilities, particularly for the blood pressure measurement component.
Here's an attempt to answer the questions based on the non-AI device described:
1. A table of acceptance criteria and the reported device performance
The document states that the Commander Flex blood pressure algorithm performance meets ANSI/AAMI SP10 and ISO 81060-2 requirements for sphygmomanometers. These standards define the acceptance criteria for blood pressure device accuracy. While the specific numerical acceptance criteria (e.g., mean difference and standard deviation between device and reference measurements) are not explicitly listed in the text, the successful meeting of these recognized standards implies the device's performance reached the established benchmarks.
| Acceptance Criteria (Standard Reference) | Reported Device Performance |
|---|---|
| ANSI/AAMI SP10 standards for sphygmomanometers | Met |
| ISO 81060-2 requirements for sphygmomanometers | Met |
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 for Test Set: 99 human subjects.
- Data Provenance: Not explicitly stated, but clinical testing was performed. Given Medtronic's location (Minneapolis, Minnesota per the document) and FDA submission, it's highly likely the study was conducted in the US. The study appears to be prospective as it involved measuring accuracy with simultaneous measurements.
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)
For blood pressure measurement accuracy studies, the "ground truth" is typically established by trained observers using an auscultatory method (stethoscope).
- Number of Experts/Observers: Not explicitly stated, but it refers to "a trained observer." This might imply multiple trained observers, but the exact count isn't given.
- Qualifications of Experts: Described as "trained observer." Specific qualifications (e.g., years of experience, medical degree, certification) are not detailed in this summary.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The method described is simultaneous blood pressure measurements by the Commander device and a trained observer using the stethoscope auscultatory method. This is a direct comparison, not typically requiring adjudication in the sense of reconciling multiple independent readings like in an imaging study. The "ground truth" is typically the auscultatory reading.
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. This document describes a non-AI/ML device (a blood pressure monitor and remote patient monitoring system). It is not an MRMC study and does not involve human readers interpreting images with or without AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This device does not contain a discrete "algorithm" in the AI/ML sense that provides a diagnostic output that would be evaluated in a standalone manner like an AI model. However, the blood pressure measurement component does involve an internal algorithm. The clinical data on page 8, "Clinical testing of the Commander Flex blood pressure 2.0 algorithm..." describes an evaluation of this inherent blood pressure measurement algorithm's accuracy compared to a reference standard (auscultation). In that sense, it's an evaluation of the device's automated function, akin to a "standalone" performance for its specific blood pressure task.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The ground truth for the blood pressure measurement study was established by simultaneous measurements by a trained observer using the stethoscope auscultatory method. This is considered a gold standard for non-invasive blood pressure measurement studies.
8. The sample size for the training set
Not Applicable. This document does not describe an AI/ML device that would require a separate training set. The device is a traditional medical device (blood pressure monitor and remote patient monitoring system) that has undergone verification and validation testing, not AI model training.
9. How the ground truth for the training set was established
Not Applicable. As there is no AI/ML training set, there is no ground truth establishment for it mentioned.
§ 870.1130 Noninvasive blood pressure measurement system.
(a)
Identification. A noninvasive blood pressure measurement system is a device that provides a signal from which systolic, diastolic, mean, or any combination of the three pressures can be derived through the use of tranducers placed on the surface of the body.(b)
Classification. Class II (performance standards).