Predicting MDS-UPDRS-III score changes using mobile device biomarkers

Abstract Digital biomarkers derived from mobile sensors could enable more frequent and objective monitoring of motor disorder symptoms. In this study, we examined the sensitivity of five tablet-based tests in predicting changes in the MDS-UPDRS-III scores following controlled Levodopa administration, utilizing regression models trained on data from 28 patients. Our experiments revealed that the best-performing single-test models exhibited an inverse prediction in 5 patients. A combined model incorporating two tests reduced misclassification to three patients. Further stratification of patients into symptom-specific groups, based on the presence of medication-induced tremor changes, and training two subgroup-specific models led to only one subject being misclassified. These results underscore the potential of mobile device biomarkers for prediction of symptom changes in Parkinson’s disease patients and the need for individualization.