(338 days)
DARI Health is a computer and video system used to quantify and graphically display human movement patterns and techniques for uses such as assessment and training of limb or body motion in pre/post rehabilitation evaluation, physical therapy, and the like.
DARI Health is a "markerless," three-dimensional human motion capture and analytical software system that uses off-the-shelf video cameras, off-the-shelf computer hardware, off-theshelf motion analysis software, and proprietary DARI Health Software (consisting of DARI Connect, DARI Capture plug-in, DARI Insight Engine, and DARI Rerort Engine) or DARA quantify, and document full-body human kinematics and kinetics during patient movement. Motions are recorded in real-time, using a digital "skeleton" to identify joint center and segment data for the cervical spine, upper extremity, trunk, and lower extremity of the paint. The captured video can be viewed after recording has ended or at some later point. During movement, the DARI Health interfaces with the capture software (off-the-shelf, Captury Live) tracks all segments and joint centers as they move in all planes of more the with resulting output is sent to The DARI Insight Engine processing software-either housed it ally on the computer used for capture or in a security-compliant, cloud-based server-where thered drant can be used to calculate all kinetic data produced during the revor d more one more one Such data is then displayed in different report formats-from large, raw datasets to simple, grahital reports that track key biomechanical metrics. Healthcare providers can access patient biomechanical data remotely through a secure webportal or locally on the computer database application to monitor patient progress and view prior or current motion analyses. There is no direct contact with the patient by the DARI Health system, and no energy is delivered to the subject at any point during the usage of the system.
The DARI Health device is a "markerless," three-dimensional human motion capture and analytical software system that uses off-the-shelf video cameras, computer hardware, motion analysis software, and proprietary DARI Health Software to quantify and document full-body human kinematics and kinetics during patient movement.
Here's an analysis of the acceptance criteria and the study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
Based on the provided text, the acceptance criteria are not explicitly stated in a defined "acceptance criteria" section with specific numerical thresholds. Instead, the document discusses the device's performance in relation to predicate devices and industry standards. Therefore, I will derive the implicit acceptance criteria from the performance claims made in the "Summary of Performance Data" section and present the reported device performance.
| Acceptance Criterion (Implicitly Derived) | Reported Device Performance |
|---|---|
| Kinematic Accuracy: No statistically significant differences in clinically relevant joint angles compared to a predicate marker-based system (Vicon/Peak Motus). | Met: When compared to a predicate marker-based Vicon (Peak Motus) system, the DARI Health system showed no statistically significant differences in the clinically relevant joint angles being measured for investigation (p = 0.33). |
| Kinetic Accuracy: No statistically significant differences in peak force, mean force, or now force compared to industry-standard force plate output. | Met: The DARI Health system was tested against standard force plate output, and its force calculation methodology demonstrated no statistically significant differences in peak force, mean force, or now force as compared to simultaneous measurements derived from a force plate (p > 0.05). Additionally, comparison of force-time curves showed a strong correlation between modalities (r = 0.995, r^2 = 0.989, SEM = 11.1 N). |
| Repeatability (Segment Length & Joint Center Calculation): Ability to identify joint centers and segment lengths within a specified tolerance, exceeding predicate and industry standards. | Met: Repeatability of segment length and joint center calculation over successive scans of 9,120 bone segments demonstrated the ability to identify the joint centers and segment lengths within 0.811mm with 99% confidence, exhibiting only 1.02% total skeletal change between sessions with 0.002 mm of variance. This exceeds predicate repeatability associated with marker analysis and inter-test repeatability of goniometers claimed by predicate JRS v2.0. |
| Software Functionality: Software functions as intended, and all results are as expected. | Met: Software validation and testing were completed for the device and functioned as intended, and all results were those expected. |
| Safety: Compliance with relevant safety standards (IEC 60601-1 and IEC 60601-1-2). | Met: The DARI Health complies with IEC 60601-1 and IEC 60601-1-2. The system requires no contact with the patient and poses no electrical, chemical, mechanical, thermal, or radiation safety concerns. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Kinematic Accuracy Study: Not explicitly stated as a number of subjects or sessions. It refers to "clinically relevant joint angles being measured for investigation" in a comparison to a predicate system.
- Sample Size for Kinetic Accuracy Study: Not explicitly stated as a number of subjects or sessions. It refers to a comparison to "simultaneous measurements derived from a force plate."
- Sample Size for Repeatability Study: "Successive scans of 9,120 bone segments" were analyzed. This implies a significant amount of data, likely from multiple subjects and/or multiple scan sessions.
- Data Provenance: The studies are described as "independent, peer-reviewed studies" and "DARI Health internal studies." The country of origin of the data is not specified, but the submission is to the U.S. FDA. The retrospective or prospective nature of these studies is not explicitly mentioned.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document does not mention the use of experts to establish ground truth for the test set. Instead, the ground truth was established by:
- Predicate marker-based Vicon (Peak Motus) system: For kinematic accuracy.
- Industry-standard force plate output: For kinetic accuracy.
- Successive scans and internal measurements: For repeatability.
Therefore, there were no human experts establishing the ground truth as described in the prompt's question for this type of objective measurement device.
4. Adjudication Method for the Test Set
Not applicable. As the ground truth was established by objective measurement systems (Vicon, force plate, internal measurements), there was no human adjudication process involved for the test set.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
No, an MRMC comparative effectiveness study was not conducted. The studies described are focused on the technical accuracy and repeatability of the device's measurements compared to established objective methods, not on how human readers (clinicians) improve with AI assistance. The DARI Health system is a measurement and analysis tool, not one that directly assists a human reader in making a diagnostic interpretation in the same way an AI for medical imaging might.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
Yes, the performance studies described are essentially standalone (algorithm only) performance assessments. The DARI Health system's ability to accurately capture, quantify, and analyze human movement (kinematics and kinetics) and its repeatability are evaluated as a standalone system against objective measurement standards. It does not involve human-in-the-loop performance in the context of these validation studies.
7. The Type of Ground Truth Used
- Kinematic Accuracy: Reference data from a predicate marker-based Vicon (Peak Motus) system. This is an instrument-based ground truth.
- Kinetic Accuracy: Reference data from industry-standard force plate output. This is also an instrument-based ground truth.
- Repeatability: Internal measurements of successive scans of bone segments, indicating the device's consistency over time.
8. The Sample Size for the Training Set
The document does not provide any information regarding the sample size used for the training set. The descriptions focus on performance validation rather than the details of algorithm development or training.
9. How the Ground Truth for the Training Set was Established
The document does not provide any information on how the ground truth for the training set (if any specific training set was used for machine learning models, which is implied by a "markerless" system) was established. The "Summary of Performance Data" focuses solely on the validation/test datasets against established objective measures.
§ 890.5360 Measuring exercise equipment.
(a)
Identification. Measuring exercise equipment consist of manual devices intended for medical purposes, such as to redevelop muscles or restore motion to joints or for use as an adjunct treatment for obesity. These devices also include instrumentation, such as the pulse rate monitor, that provide information used for physical evaluation and physical planning purposes., Examples include a therapeutic exercise bicycle with measuring instrumentation, a manually propelled treadmill with measuring instrumentation, and a rowing machine with measuring instrumentation.(b)
Classification. Class II (special controls). The device, when it is a measuring exerciser or an interactive rehabilitation exercise device for prescription use only, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 890.9.