Detection and Assessment of Point-to-Point Movements During Functional Activities Using Deep Learning and Kinematic Analyses of the Stroke-Affected Wrist

• Published in: IEEE journal of biomedical and health informatics Vol. 28; no. 2; pp. 1022 - 1030
• Main Authors: Oubre, Brandon, Lee, Sunghoon Ivan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Activities of Daily Living; Biological system modeling; Biomechanical Phenomena; Deep Learning; Ecological effects; Feature extraction; Human activity recognition; Humans; Impairment; Inertial sensing devices; Kinematics; Limbs; Monitoring; Motion detection; Motion perception; Motor task performance; Paresis; Recovery of Function; remote monitoring; Stroke; Stroke - diagnosis; Stroke Rehabilitation; Task analysis; Upper Extremity; wearable sensing; Wrist
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2023.3337156

Stoke is a leading cause of long-term disability, including upper-limb hemiparesis. Frequent, unobtrusive assessment of naturalistic motor performance could enable clinicians to better assess rehabilitation effectiveness and monitor patients' recovery trajectories. We therefore propose and validate a two-phase data analytic pipeline to estimate upper-limb impairment based on the naturalistic performance of activities of daily living (ADLs). Eighteen stroke survivors were equipped with an inertial sensor on the stroke-affected wrist and performed up to four ADLs in a naturalistic manner. Continuous inertial time series were segmented into sliding windows, and a machine-learned model identified windows containing instances of point-to-point (P2P) movements. Using kinematic features extracted from the detected windows, a subsequent model was used to estimate upper-limb motor impairment, as measured by the Fugl-Meyer Assessment (FMA). Both models were evaluated using leave-one-subject-out cross-validation. The P2P movement detection model had an area under the precision-recall curve of 0.72. FMA estimates had a normalized root mean square error of 18.8% with <inline-formula><tex-math notation="LaTeX">R^{2}=0.72</tex-math></inline-formula>. These promising results support the potential to develop seamless, ecologically valid measures of real-world motor performance.