(227 days)
The Current Wearable Health Monitoring System is intended for reusable bedside, mobile and central multi-parameter, physiologic patient monitoring of adult patients in professional healthcare facilities, such as hospitals or skilled nursing facilities, or their own home. It is intended for monitoring of patients by trained healthcare professionals.
The Current Wearable Health Monitoring System is intended to provide visual and audible physiologic multi-parameter alarms. The Current Wearable Health Monitoring System is intended for temperature monitoring temperature at the upper arm is clinically indicated.
The Current Wearable Health Monitoring System is intended for continuous monitoring of the following parameters in adults:
- · Pulse rate
- · Oxygen saturation
- · Temperature
- · Movement
The Current Wearable Health Monitoring System is intermittent or spot-check monitoring, in adults, of:
- · Respiration rate
- · Non-invasive blood pressure
- · Lung function & spirometry
- · Weight
The Current Wearable Health Monitoring System is not intended for use in high-acuity environments, such as ICU or operating rooms.
The Current Wearable Health Monitoring System is not intended for use on acutely ill cardiac patients with the potential to develop life threatening arrhythmias e.g. very fast atrial fibrillation. For these patients, they should be monitored using a device with continuous ECG. The Current Wearable Health Monitoring System is not a substitute for an ECG monitor.
The Current Wearable Health Monitoring System is not intended for SpO2 monitoring in conditions of high motion or low perfusion.
The Current Wearable Health Monitoring System is a remote patient monitoring system that consists of a single monitoring device (the wearable) worn on the upper arm by adult patients (aged 18 years old and over), a software platform (containing an alarming system) and a user interface to allow presentation of vital signs data both on mobile devices and a central station. The Current Wearable Health Monitoring System is also integrated with specific devices for monitoring of blood pressure, spirometry, lung function, and weight.
The Wearable is intended to continuously monitors physiological vital sign data from the person being monitored and securely transmit the encrypted data via the secure server. The wearable is intended for use in professional healthcare facilities, such as hospitals or skilled nursing facilities, or the home by trained healthcare professionals.
The healthcare professional can securely access the patient physiological signs remotely via a mobile application or a web-interface which is also intended to provide visual and audible physiologic multi-parameter alarms.
It is intended to continuously monitor pulse rate (PR), oxygen saturation (SpO2), temperature (TEMP) and movement (MOVEMENT). Current is intended for intermittent or spot-checking monitoring of respiration rate (RESP), blood pressure (BP), spirometry and lung function, and weight (WEIGHT).
In the home environment, the patient will have responsibility for applying the device to their arm, charging the device, and plugging in the Homehub to mains power. The data will still be made directly available to healthcare professionals. These healthcare professionals will be at a remote location e.g., an office or within the hospital or could be with the patient in their own home.
The provided text describes a 510(k) submission for the Current Health Monitoring System Gen 2. The submission claims substantial equivalence to a predicate device (Current Health Monitoring System Gen 1) based on non-clinical performance data. Therefore, the "acceptance criteria" and "study that proves the device meets the acceptance criteria" refer to the non-clinical tests performed to demonstrate equivalent performance to the predicate device.
Here's a breakdown of the information requested based solely on the provided text, noting that the document itself is a summary and does not contain the detailed results of the studies. It only states that the tests "were all passed".
Since the document focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance and a comparison of technological characteristics, it does not include information typically found in studies designed to prove improvement over human readers, or detailed standalone algorithmic performance metrics. The "ground truth" here is the performance of the predicate device and established standards.
1. A table of acceptance criteria and the reported device performance
The document does not provide a table with specific quantitative acceptance criteria or detailed numerical reported device performance for the Gen 2 device. It states that the Gen 2 device was tested for various parameters and "all tests were passed," implying that the Gen 2 device met the performance of the predicate device and relevant standards. The "acceptance criteria" implicitly are the performance specifications and accuracy established for the predicate device (Gen 1) and by the cited standards (e.g., ISO, IEC, FDA guidance documents).
Here's a conceptual table based on the types of tests performed and the implied "acceptance criteria" which would be meeting the predicate's performance and/or standard requirements:
| Acceptance Criterion (Implicit) | Reported Device Performance (Summary Statement) |
|---|---|
| Compliance with IEC 60601-1 (Electrical Safety) | All tests were passed |
| Compliance with IEC 60601-1-2 (Electromagnetic Compatibility, EMC) | All tests were passed |
| Accuracy of pulse rate monitoring (ISO 80601-2-61, FDA Guidance) | All tests were passed |
| Accuracy of SpO2 monitoring (ISO 80601-2-61, FDA Guidance) | All tests were passed |
| Accuracy of respiration rate measurement | All tests were passed |
| Accuracy of temperature measurement (ISO 80601-2-56) | All tests were passed |
| Compliance with ASTM D7386 (Device Ship/Transport Testing) | All tests were passed |
| Biocompatibility (ISO 10993-1) | All tests were passed |
| Software/Firmware verification and validation (including integration/interoperability) | All tests were passed |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not specify the sample sizes used for any of the non-clinical tests (e.g., how many measurements were taken for pulse rate accuracy, or how many devices were tested for electrical safety).
The document is a summary of the 510(k) submission, and these details are typically found in the full submission. It also does not specify the country of origin of the data or whether the data was retrospective or prospective. Given that no animal or clinical studies were included, the "data" refers to engineering and lab-based test data.
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 type of information is not applicable in the context of this 510(k) submission as described. The "ground truth" for these non-clinical tests is established by:
- Engineering standards (e.g., IEC 60601-1, ISO 80601-2-61).
- Reference devices or methods (e.g., end-tidal CO2 for respiration rate).
- The performance of the predicate device.
There is no mention of human expert readers or their qualifications being involved in establishing ground truth for the device's technical performance parameters like pulse rate, SpO2, or temperature accuracy in the provided text.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This is not applicable as the described tests are non-clinical engineering and performance validations against established standards and predicate device performance, not human reader studies requiring adjudication.
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, a multi-reader, multi-case (MRMC) comparative effectiveness study was not done (or at least, not mentioned) as "Substantial equivalence is based on an assessment of non-clinical performance data and no animal or clinical performance data is included." This device is a physiological monitor, not an AI diagnostic tool intended to assist human readers in interpreting images or complex data, so this type of study would not be expected.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The entire set of "Summary of Non-Clinical Tests (Performance data)" can be considered standalone algorithm/device performance testing. The provided text states:
- "Validation of the accuracy of pulse rate monitoring..."
- "Validation of the accuracy of SpO2 monitoring..."
- "Ensure accuracy of the Current Health Gen 2 measurement of respiration rate..."
- "The Current Health Gen 2 was tested to confirm the Temperature Measurement Accuracy..."
These tests evaluate the device's ability to accurately measure physiological parameters independently.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The types of ground truth used for the non-clinical performance tests are:
- Established engineering standards and guidance documents: ISO 80601-2-61 (Pulse Oximeters), IEC 60601-1 (Electrical Safety), IEC 60601-1-2 (EMC), ISO 80601-2-56 (Temperature), ASTM D7386 (Ship/Transport), ISO 10993-1 (Biocompatibility), FDA Guidance for Pulse Oximeters.
- Reference measurement methods: For respiration rate, it was "measured via end-tidal CO2".
- Performance of the predicate device: The Gen 2 was demonstrated to have "equivalent performance" to the Gen 1.
8. The sample size for the training set
The document does not mention a "training set" in the context of machine learning. The device being submitted is a physiological monitor, not explicitly described as containing a machine learning algorithm that requires a separate "training set" and "test set" in the AI/ML sense. The "test set" here refers to the data collected during the non-clinical performance tests.
9. How the ground truth for the training set was established
As there is no mention of a "training set" for a machine learning model, this question is not applicable based on the provided text. The device is a monitor, and its "performance" is about its accuracy in measuring vital signs, not about learning from data to make predictions or classifications.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).