Head Pitch Angular Velocity Discriminates (Sub-)Acute Neck Pain Patients and Controls Assessed with the DidRen Laser Test

Abstract

Understanding neck pain is an important societal issue. Kinematic data from sensors may help to gain insight into the pathophysiological mechanisms associated with neck pain through a quantitative sensorimotor assessment of one patient. The objective of this study was to evaluate the potential usefulness of artificial intelligence with several machine learning (ML) algorithms in assessing neck sensorimotor performance. Angular velocity and acceleration measured by an inertial sensor placed on the forehead during the DidRen laser test in thirty-eight acute and subacute non-specific neck pain (ANSP) patients were compared to forty-two healthy control participants (HCP). Seven supervised ML algorithms were chosen for the predictions. The most informative kinematic features were computed using Sequential Feature Selection methods. The best performing algorithm is the Linear Support Vector Machine with an accuracy of 82% and Area Under Curve of 84%. The best discriminative kinematic feature between ANSP patients and HCP is the first quartile of head pitch angular velocity. This study has shown that supervised ML algorithms could be used to classify ANSP patients and identify discriminatory kinematic features potentially useful for clinicians in the assessment and monitoring of the neck sensorimotor performance in ANSP patients.

Evaluating Cervical Spine Mobility and Fitt's Law Compliance: The DidRen Laser Test Adapted for Virtual Reality with Age and Sex Effects

“…The laser beam must hit three red visual targets (Figure 1). LEDs directly above the red targets validate each hit in addition to producing a sound [19][20][21][22][23].…”

“…These tests are generally straightforward to implement and affordable to clinicians, both regarding time and budget. The use of sensors, even low-cost ones, to these tests adds complexity but also offers relevant clinical indicators and a means to monitor patient progress and guide rehabilitation efforts [19, 21, 22].…”

“…The laser beam must hit three red visual targets (Figure 1). LEDs directly above the red targets validate each hit in addition to producing a sound [19–23]. The DidRen laser test consists of a simple, standardized, and repetitive sensorimotor task performed in the real world, involving axial head rotations from “target to target” in the same 5-cycles sequence (center–right–center–left–center).…”

Machine Learning Identifies Chronic Low Back Pain Patients from an Instrumented Trunk Bending and Return Test

“…A recent study using a particular supervised ML algorithm (Support Vector Machine, SVM) to analyze IMU data has already shown that a kinematic test of the lumbar spine is able to discriminate NLBP subjects from LBP patients and classify them according to their risk of chronicity, i.e., between high risk and medium to low risk, with an accuracy of >75% [12]. Moreover, it has been shown in [24] that SVM can detect neck pain from rotational head movements with an accuracy of 82%. These last two studies show that a diagnostic analysis using ML algorithms supplied with kinematic parameters is a promising way to investigate these spinal conditions further.…”

Wearable Sensors Applied in Movement Analysis

“…Wearable sensors may also provide clinicians with additional quantitative information when assessing musculoskeletal conditions, such as neck pain and low-back pain. Regarding neck pain, the authors of [ 9 ] used a single IMU placed on a participant’s forehead while performing a test to assess sensorimotor performance of the neck through repeated head rotations. A Linear Support Vector Machine can discriminate acute and subacute non-specific neck pain patients from healthy control participants with 82% accuracy by analyzing time series of angular speed and acceleration.…”