Instrumented timed up and go test and machine learning-based levodopa response evaluation: a pilot study

• Published in: Journal of neuroengineering and rehabilitation Vol. 21; no. 1; pp. 163 - 15
• Main Authors: He, Jing, Wu, Lingyu, Du, Wei, Zhang, Fei, Lin, Shinuan, Ling, Yun, Ren, Kang, Chen, Zhonglue, Chen, Haibo, Su, Wen
• Format: Journal Article
• Language: English
• Published: London BioMed Central 18.09.2024; BioMed Central Ltd; BMC
• Subjects: Aged; Antiparkinson Agents - administration & dosage; Antiparkinson Agents - therapeutic use; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Care and treatment; Comparative analysis; Diagnosis; Dopa; Dosage and administration; Female; Health aspects; Humans; Levodopa - administration & dosage; Levodopa challenge test; Levodopa response; Machine Learning; Male; Methods; Middle Aged; Movement disorders; Neurology; Neurosciences; Parkinson Disease - diagnosis; Parkinson Disease - drug therapy; Parkinson’s disease; Pilot Projects; Rehabilitation Medicine; Sensors; Wearable sensors; China; Levodopa challenge test; Parkinson’s disease; Wearable sensors; Levodopa response; Machine learning
• ISSN: 1743-0003; 1743-0003
• DOI: 10.1186/s12984-024-01452-4

Background The acute levodopa challenge test (ALCT) is a universal method for evaluating levodopa response (LR). Assessment of Movement Disorder Society’s Unified Parkinson’s Disease Rating Scale part III (MDS-UPDRS III) is a key step in ALCT, which is some extent subjective and inconvenience. Methods This study developed a machine learning method based on instrumented Timed Up and Go (iTUG) test to evaluate the patients’ response to levodopa and compared it with classic ALCT. Forty-two patients with parkinsonism were recruited and administered with levodopa. MDS-UPDRS III and the iTUG were conducted in both OFF-and ON-medication state. Kinematic parameters, signal time and frequency domain features were extracted from sensor data. Two XGBoost models, levodopa response regression (LRR) model and motor symptom evaluation (MSE) model, were trained to predict the levodopa response (LR) of the patients using leave-one-subject-out cross-validation. Results The LR predicted by the LRR model agreed with that calculated by the classic ALCT (ICC = 0.95). When the LRR model was used to detect patients with a positive LR, the positive predictive value was 0.94. Conclusions Machine learning based on wearable sensor data and the iTUG test may be effective and comprehensive for evaluating LR and predicting the benefit of dopaminergic therapy.