(122 days)
The Leaf Patient Monitoring System monitors the orientation and activity of patients susceptible to pressure ulcers. It allows healthcare providers to implement individualized turn management plans and continuously monitor each patient. The Leaf Patient Monitoring System provides alerts when patient orientation or activity deviates from parameters set by healthcare providers. The device is intended for use in medical, nursing and long-term care facilities, including independent living, assisted-living and rehabilitation facilities.
The Leaf Patient Monitoring System is a medical device designed for use in hospitals, nursing homes, or other patient care facilities to monitor and report body orientation and activity, as well as to provide visual alerts for orientations and activity levels that fall outside of thresholds set by healthcare providers. The use of the Leaf Patient Monitoring System provides for continuous monitoring of patient position and allows caregivers to easily identify patients that are in need of caregiver-assisted turns according to the institution's guidelines or protocols. The use of the Leaf Patient Monitoring System can increase compliance with the care facility's prescribed patient tuning schedule and thereby may aid in the prevention of pressure ulcers.
The Leaf Patient Monitoring System is comprised of Patient Sensors, Leaf Antennas, and USB RF Transceivers, Turn Management Software, and a User Interface that can be viewed on a monitoring station. Each Leaf Patient Sensor is associated with a single patient, such that the patient's orientation, movements, and other care parameters can be monitored.
The provided text is a 510(k) premarket notification for the Leaf Patient Monitoring System. It focuses on demonstrating substantial equivalence to a predicate device (Centauri Medical, Inc. DynaSense System) rather than providing detailed acceptance criteria and a study proving the device meets those criteria, particularly in the context of an AI/algorithm-driven device with performance metrics like sensitivity, specificity, etc.
Based on the provided document, here's an attempt to answer the questions, highlighting where information is not present as per the request:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state quantitative acceptance criteria (e.g., minimum accuracy, sensitivity, specificity) for the Leaf Patient Monitoring System's performance in terms of monitoring patient orientation and activity, nor does it present specific reported performance metrics against such criteria. The focus is on demonstrating that the device "meets the established specifications necessary for consistent performance during its intended use" and "performs as intended."
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
The document mentions "System performance testing" as part of nonclinical bench testing but does not specify a sample size, test set, or data provenance (country of origin, retrospective/prospective). It does not describe a clinical study with patients to validate performance.
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 as the document does not describe a clinical performance study involving expert-adjudicated ground truth.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
This information is not provided.
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
An MRMC comparative effectiveness study was not mentioned or described. This device appears to be a monitoring system for patient orientation and activity, not an AI-assisted diagnostic imaging device that would typically involve human "readers." The system is designed to provide alerts and help caregivers with turn management, aiming to increase compliance with care facility protocols for pressure ulcer prevention.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document describes "System performance testing" as part of nonclinical bench testing, implying standalone testing. However, the details of what this entailed (e.g., specific metrics for the algorithm's performance in detecting orientation changes) are not detailed. The device itself is described as a system that continuously monitors and communicates data wirelessly to a monitoring station that displays information via a user interface and provides alerts. Its purpose is to aid human caregivers rather than replace their decision-making entirely.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The document does not specify the type of ground truth used for its "System performance testing." Given it's a patient monitoring system for orientation and activity, ground truth would likely involve direct observation or independent measurement of patient position/movement, but this is not stated.
8. The sample size for the training set
The document does not mention a training set or its sample size. This suggests that while the device contains software, a deep learning or similar AI model requiring a large training set may not be the core technology being described for performance evaluation in this submission. The "Software verification" mentioned is more likely related to traditional software engineering validation.
9. How the ground truth for the training set was established
As no training set is mentioned, this information is not provided.
Summary of what the document focuses on:
The document primarily focuses on demonstrating substantial equivalence to a predicate device (Centauri Medical, Inc. DynaSense System) based on:
- Identical intended use and indications for use.
- Similar technological characteristics, with minor modifications (updated aesthetics, minor display changes, related software updates, and a non-adhesive frame around the sensor adhesive).
- Labeling changes, specifically the removal of a contraindication for pacemaker/ICD patients with the addition of an appropriate warning statement, which was analyzed not to raise new issues of safety or effectiveness.
- Nonclinical Testing Summary: This included "System performance testing," "Software verification," and "Electrical Safety and EMC." The collective results are stated to "demonstrate that the materials chosen, the manufacturing processes, and design... meet the established specifications necessary for consistent performance" and "do not raise new questions of safety or effectiveness."
Essentially, the submission leverages the predicate device's prior clearance to establish safety and effectiveness, affirming that the new device is functionally the same or improved without introducing new risks that would necessitate extensive new clinical performance studies with detailed acceptance criteria and ground truth validation for novel AI algorithms.
§ 880.2400 Bed-patient monitor.
(a)
Identification. A bed-patient monitor is a battery-powered device placed under a mattress and used to indicate by an alarm or other signal when a patient attempts to leave the bed.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 880.9.