(368 days)
The EYE-SYNC® is intended for recording, viewing, and analyzing eye movements in support of identifying visual tracking impairment in human subjects.
The EYE-SYNC® is intended to record, measure, and analyze eye movements as an aid in the diagnosis of concussion, also known as mild traumatic brain injury (mTBI), within three days of sport-related head injury in patients 17-24 years of age in conjunction with a standard neurological assessment, for use by medical professionals qualified to interpret the results of a concussion assessment examination.
A negative EYE-SYNC® classification corresponds to eye movements that are consistent with a lack of concussion.
A positive EYE-SYNC® classification corresponds to eye movements that may be present in patients with concussion.
The SyncThink EYE-SYNC device is a portable, fully enclosed eye tracking environment with three primary components:
-
- Eye Tracker (head-mounted device) with eye tracking sensor
-
- Eye tracking display
-
- Android Tablet
The eye tracker is a modified Samsung GearVR provided by SensoMotoric Instruments (SMI). It is mounted to the subject's face and held either by hands placed on the side or using a strap. The eye tracking sensor includes two high-speed infrared cameras (for each eye) connected to a visual display for battery, computation, and display. Camera lighting is provided by 12 high-quality Light-emitting Diodes (LEDs) centered at 850 nanometers. Eye gaze tracking is performed using a proprietary implementation of the pupil- corneal reaction method. The eye tracker display is a nonnetworked mobile device that fits within the eye tracking sensor and connects over USB. The display receives eye tracking sensor information for post-processing, manages sensor calibration, provides binocular visual display to the subject, and interfaces with the Android tablet over Bluetooth. Eye gaze tracking and visual display is combined to provide several assessment paradigms to characterize subject eye tracking performance:
- Smooth Pursuit
- · Saccades
- · Vestibular-Ocular Reflex (VOR)
- · VOR Cancellation (VORx)
An EYE-SYNC software app on the display device manages these functions.
The Android tablet is a standard off-the-shelf 9.7" mobile tablet from Samsung with Verizon 4G cellular connectivity. A second EYE-SYNC software app designed to provides an integrative platform for data collected on the HMD eye tracker:
- · Patient, administrator, and records management
- · Eye tracker assessment Bluetooth control
- · Assessment Vestibular/Ocular-Motor Screening (VOMS) self-report tools
- · Eye tracker assessment real-time Bluetooth monitoring
- Eye tracker data log Bluetooth transfer
- Eye tracker assessment analysis using visual synchronization metrics
- · Analysis report generation with visualizations
- · Background diagnostics to verify device health
- · Cloud connectivity for data synchronization
Internal batteries from the eye tracking display and Android tablet provide power for remote use, away from power source. Each device has an EYE-SYNC software app installed to provide the described functionality. EYE-SYNC is provided as a complete system and both apps are managed a single software project with identical version numbers. EYE-SYNC is provided in a standalone carry-case with user manual, strap, cleaning, and charging accessories.
The provided text describes the regulatory clearance of the EYE-SYNC device. Here's a breakdown of the acceptance criteria and study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion | Reported Device Performance | Comments |
|---|---|---|
| Sensitivity (Detection of Concussion) | 82% (95% CI: 74%, 89%) | Meets the performance demonstrated by the predicate device (80.4%). |
| Specificity (Non-detection of Concussion) | 93% (95% CI: 91%, 94%) | Significantly higher than the predicate device (66.1%), indicating better ability to correctly identify non-concussed individuals. |
| Negative Predictive Value (NPV) | 98% (95% CI: 97%, 99%) | Higher than the predicate device (94.5%), indicating excellent ability to rule out concussion when the test is negative. |
| Positive Predictive Value (PPV) | 56% (95% CI: 48%, 64%) | Higher than the predicate device (31.6%), indicating improved ability to identify concussion when the test is positive, though still with a notable rate of false positives. (Note: PPV and NPV calculated based on observed study prevalence of 10% concussion). |
| Test-Retest Reliability (for specific metrics) | SD tangential error: ICC = 0.86 (0.82, 0.90) | |
| SD radial error: ICC = 0.78 (0.71, 0.84) | ||
| Mean phase error: ICC = 0.83 (0.77, 0.87) | High ICC values indicate strong reliability of the measurements. | |
| Electrical Safety | Complied with IEC 60601-1:2012 Ed. 3.0 and IEC 60601-2-57:2011 Ed1.0. | |
| Electromagnetic Compatibility (EMC) | Complied with IEC 60601-1-2:2014 Ed 4.0. | |
| Software Verification and Validation | Conducted according to FDA Guidance, considered "moderate" level of concern. | |
| Cybersecurity | Assessed and documented according to FDA Guidance. | |
| Light Safety (Photobiological Safety) | Conformed to EN62471. | |
| Biocompatibility | Cytotoxicity, Sensitization, and Irritation tests conducted and passed. | (Specific results not given, but stated to be conducted in accordance with ISO 10993-1). |
2. Sample Size and Data Provenance
- Test Set Sample Size: 1,069 subjects
- Data Provenance: The study was a retrospective analysis of subjects ages 17-24 years actively engaged in competitive athletics. The location/country of origin is not explicitly stated, but the context of FDA clearance for a US market implies the data is relevant to a US population or sufficiently representative thereof. The study involved patient evaluations conducted by healthcare practitioners blinded to EYE-SYNC device output "+3 days from injury," suggesting it was collected progressively for the purpose of the study.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Not explicitly stated as a specific number of individual experts.
- Qualifications of Experts: The ground truth for concussion was established using the SCAT-5 clinical reference standard definition of concussion, with evaluations conducted by "a healthcare practitioner blinded to EYE-SYNC device output." While specific qualifications like "radiologist with 10 years of experience" are not provided, "healthcare practitioner" implies a medical professional (e.g., physician, athletic trainer, nurse practitioner) trained in concussion assessment.
4. Adjudication Method for the Test Set
- The text states that the SCAT-5 clinical reference standard definition of concussion was used, with evaluations conducted by a single healthcare practitioner who was blinded to the EYE-SYNC device output. There is no mention of multiple readers or an explicit adjudication method (e.g., 2+1, 3+1). The "ground truth" seems to have been based on this single blinded practitioner's assessment using the SCAT-5.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No MRMC comparative effectiveness study was done to evaluate how much human readers improve with AI vs. without AI assistance. The study focuses on the standalone algorithm's performance in aid of diagnosis. The device's use is explicitly "in conjunction with a standard neurological assessment," implying it's an aid to a human clinician, but the study itself does not measure the human-in-the-loop performance change.
6. Standalone (Algorithm Only) Performance
- Yes, a standalone performance evaluation was clearly done. The reported sensitivity, specificity, PPV, and NPV are for the EYE-SYNC device's classification algorithm. The healthcare practitioner who established the ground truth was "blinded to EYE-SYNC device output," which supports this being a standalone performance assessment of the algorithm against clinical ground truth.
7. Type of Ground Truth Used
- The ground truth used was expert consensus / clinical reference standard: The SCAT-5 clinical reference standard definition of concussion, as determined by a blinded healthcare practitioner. This is a widely accepted clinical tool for concussion assessment.
8. Sample Size for the Training Set
- The text does not explicitly state the sample size for the training set. The provided data focuses solely on the "validation data analysis" performed on 1,069 subjects, which represents the test set.
9. How Ground Truth for Training Set Was Established
- Since the training set size is not provided, the method for establishing its ground truth is also not explicitly described in this document. It is typically assumed that training data ground truth would be established through similar expert labeling or clinical diagnosis processes, but no details are given here.
§ 882.1455 Traumatic brain injury eye movement assessment aid.
(a)
Identification. A traumatic brain injury eye movement assessment aid is a prescription device that uses a patient's tracked eye movements to provide an interpretation of the functional condition of the patient's brain. This device is an assessment aid that is not intended for standalone detection or diagnostic purposes.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Clinical performance data under anticipated conditions of use must evaluate tracked eye movement in supporting the indications for use and include the following:
(i) Evaluation of sensitivity, specificity, positive predictive value, and negative predictive value using a reference method of diagnosis;
(ii) Evaluation of device test-retest reliability; and
(iii) A description of the development of the reference method of diagnosis, which may include a normative database, to include the following:
(A) A discussion of how the clinical work-up was completed to establish the reference method of diagnosis, including the establishment of inclusion and exclusion criteria; and
(B) If using a normative database, a description of how the “normal” population was established, and the statistical methods and model assumptions used.
(2) Software verification, validation, and hazard analysis must be performed. Software documentation must include a description of the algorithms used to generate device output.
(3) Performance testing must demonstrate the electrical safety and electromagnetic compatibility (EMC) of the device.
(4) The patient-contacting components of the device must be demonstrated to be biocompatible.
(5) A light hazard assessment must be performed for all eye-tracking and visual display light sources.
(6) Labeling must include:
(i) A summary of clinical performance testing conducted with the device, including sensitivity, specificity, positive predictive value, negative predictive value, and test-retest reliability;
(ii) A description of any normative database that includes the following:
(A) The clinical definition used to establish a “normal” population and the specific selection criteria;
(B) The format for reporting normal values;
(C) Examples of screen displays and reports generated to provide the user results and normative data;
(D) Statistical methods and model assumptions; and
(E) Any adjustments for age and gender.
(iii) A warning that the device should only be used by trained healthcare professionals;
(iv) A warning that the device does not identify the presence or absence of traumatic brain injury or other clinical diagnoses;
(v) A warning that the device is not a standalone diagnostic; and
(vi) Any instructions to convey to patients regarding the administration of the test and collection of test data.