Search Results

The MotionWatch and PRO-Diary are compact, lightweight, body-worn activity monitoring devices that may be used to document physical movement associated with applications in physiological monitoring. The devices are intended to monitor limb or body movements during daily living and sleep. The MotionWatch and PRO-Diary can be used to assess activity in any instance where quantifiable analysis of physical motion is desired.

Additionally, the PRO-Diary has a built-in score pad that allows the wearer to subjectively assign and enter responses to pre-programmed questions. The score pad can be used as a substitute or in addition to the traditional written patient diary in conjunction with activity monitoring.

MotionWatch and PRO-Diary are compact, ambulatory, battery-operated activity recorders with physical characteristics similar to a small wristwatch.

The MotionWatch and PRO-Diary are intended for the acquisition and analysis of the physical activity of the body during daily living and sleep. The MotionWatch and PRO-Diary use state of the art miniature accelerometer technology to measure movements of the limb or torso and store these data within the devices differ in that the MotionWatch incorporates an ambient light sensor whereby the PRO-Diary incorporates a display and score-pad to allow subjective inputs.

The MotionWatch and PRO-Diary require operational software to allow configuration. data download, storage and off-line analysis of activity data by a health, care provider. The software can be run on an IBM-Compatible PC and the device is connected directly by means of a standard Universal Serial Bus connection for configuration and download.

The MotionWatch and PRO-Diary utilize a motion sensor known as an "accelerometer" to measure the occurrence and degree of motion. The sensor is a solid state device with a digital output directly proportional to physical acceleration in 1, 2 or 3 axes of orientation. The acceleration data are processed into "counts" before being stored in the non-volatile memory of the device.

Here's the breakdown of the acceptance criteria and the study details for the MotionWatch and PRO-Diary devices, based on the provided text:

Acceptance Criteria and Device Performance

The provided document details non-clinical performance testing for both the MotionWatch and PRO-Diary. The acceptance criteria and reported device performance are presented below. It's important to note that these are engineering performance specifications rather than clinical study endpoints.

MotionWatch Non-Clinical Performance Testing:

PRO-Diary Non-Clinical Performance Testing:

Study Details:

2. Sample Size Used for the Test Set and Data Provenance:

• Sample Size: The document repeatedly refers to "a sample of devices" or "a sample device" for testing. However, no specific number for the sample size (i.e., how many individual devices were tested) is provided for any of the performance tests.
• Data Provenance: Not explicitly stated. Given the submitter's address (CamNtech, UK, Ltd. ... Cambridge, United Kingdom), the testing was likely conducted in the United Kingdom. The study appears to be a prospective series of engineering validation tests rather than a retrospective analysis of existing data.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:

• Not applicable. The "ground truth" in this context refers to the verifiable physical conditions (e.g., applied acceleration, light levels) used to test the device's accuracy. These are objective measurements rather than subjective expert interpretations. In the case of the PRO-Diary's subjective input test, the written log serves as the ground truth, which is a direct record.
• No human experts were used to establish the "ground truth" for the device's physical performance characteristics.

4. Adjudication Method for the Test Set:

• Not applicable. This was not a clinical study involving subjective measures or ambiguous data interpretation requiring adjudication. The pass/fail criteria are objective and directly measured against known physical inputs or comparisons to a reference (e.g., calibrated light meter, written log).

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, What was the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance:

• No such study was conducted or reported. The devices (MotionWatch and PRO-Diary) are activity recorders. They collect raw physical movement data and, in the case of the PRO-Diary, subjective inputs. They do not employ AI or machine learning for interpretation, nor do they involve "human readers" interpreting data in a diagnostic or assessment capacity where AI assistance would be relevant for improvement. The document describes basic device performance validation.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done:

• Yes, in essence. The entire performance testing described is "standalone" in the sense that it evaluates the device's inherent ability to measure and record physical parameters and, for the PRO-Diary, to record subjective input accurately. There is no "human-in-the-loop" performance being measured in these engineering validation tests, other than a human observing a display's legibility or comparing a written log (for the PRO-Diary's subjective input feature).

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.):

The ground truth used for these performance tests includes:

• Simulated reference acceleration: For accuracy and frequency response of acceleration measurements.
• Absence of physical stimulus: For zero count output.
• Calibrated light meter: For light sensor accuracy.
• Total darkness (covered sensor): For zero lux output.
• Controlled power on/off events: For recovery after reset.
• Written log: For the accuracy of subjective input recording and display on the PRO-Diary.

8. The Sample Size for the Training Set:

• Not applicable. These devices are not AI/ML-based systems that require a training set. They are hardware devices with embedded software for data acquisition and storage, validated through direct physical performance testing against known inputs.

9. How the Ground Truth for the Training Set Was Established:

• Not applicable. As there is no training set for an AI/ML algorithm, no ground truth needed to be established for one.

Ask a specific question about this device