A Computer Vision-Based Application for the Assessment of Head Posture: A Validation and Reliability Study

Abstract

As its name implies, the forward head position (FHP) is when the head is further forward of the trunk than normal. This can cause neck and shoulder tension, as well as headaches. The craniovertebral angle (CVA) measured with 2D systems such as Kinovea software is often used to assess the FHP. Computer vision applications have proven to be reliable in different areas of daily life. The aim of this study is to analyze the test-retest and inter-rater reliability and the concurrent validity of a smartphone application based on computer vision for the measurement of the CVA. Methods: The CVAs of fourteen healthy volunteers, fourteen neck pain patients, and fourteen tension-type headache patients were assessed. The assessment was carried out twice, with a week of rest between sessions. Each examiner took a lateral photo in a standing position with the smartphone app based on computer vision. The test-retest reliability was calculated with the assessment of the CVA measured by the smartphone application, and the inter-rater reliability was also calculated. A third examiner assessed the CVA using 2D Kinovea software to calculate its concurrent validity. Results: The CVA in healthy volunteers was 54.65 (7.00); in patients with neck pain, 57.67 (5.72); and in patients with tension-type headaches, 54.63 (6.48). The test-retest reliability was excellent, showing an Intraclass Correlation Coefficient (ICC) of 0.92 (0.86–0.95) for the whole sample. The inter-rater reliability was excellent, with an ICC of 0.91 (0.84–0.95) for the whole sample. The standard error of the measurement with the app was stated as 1.83°, and the minimum detectable change was stated as 5.07°. The concurrent validity was high: r = 0.94, p < 0.001. Conclusion: The computer-based smartphone app showed excellent test-retest and inter-rater reliability and strong concurrent validity compared to Kinovea software for the measurement of CVA.

A Beta Version of an Application Based on Computer Vision for the Assessment of Knee Valgus Angle: A Validity and Reliability Study

“…Once the markers were placed, each examiner run the application with MATLAB and asked to the application to look for the photos and to evaluate the knee valgus angle of each participant (Figure 1). This beta application has shown strong current validity and excellent reliability in measuring the craniovertebral angle [17].…”

“…The integration of computer vision in healthcare and sports medicine has the potential to revolutionize how patients and athletes are assessed and treated [16]. Previous studies analyzed recent technological advances, such as computer vision or deep learning, to analyze and extract data from digital images to track static and dynamic patterns [17,18]. This technology has demonstrated the ability to make reliable and valid records in humans and animals.…”