Treatment Detection and Movement Disorder Society-Unified Parkinson's Disease Rating Scale, Part III Estimation Using...

Area of Science:

• Neuroscience
• Biomarker Discovery
• Computational Biology

Background:

• Parkinson's disease (PD) drug development requires objective biomarkers to monitor treatment efficacy.
• Current methods for assessing PD symptom severity and drug response can be subjective and time-consuming.
• Developing easy-to-implement biomarkers is essential for accelerating antiparkinsonian drug discovery.

Purpose of the Study:

• To develop and validate composite biomarkers for detecting levodopa/carbidopa effects in PD patients.
• To create biomarkers capable of estimating Parkinson's disease symptom severity.
• To utilize machine learning to identify optimal finger tapping task features for predicting treatment response and disease progression.

Main Methods:

• Trained machine learning algorithms (classification and regression) on data from 20 PD patients in a placebo-controlled, crossover study.
• Collected data included alternate index and middle finger tapping (IMFT), alternative index finger tapping (IFT), thumb-index finger tapping (TIFT), and Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) III scores.
• Evaluated the performance of composite biomarkers derived from tapping tasks and MDS-UPDRS III scores for treatment effect classification and symptom severity estimation.

Main Results:

• The alternative index finger tapping (IFT) composite biomarker demonstrated superior classification performance (83.50% accuracy, 93.95% precision) compared to the MDS-UPDRS III composite biomarker (75.75% accuracy, 73.93% precision).
• The IFT composite biomarker also achieved the best performance in estimating MDS-UPDRS III total score (mean absolute error: 7.87, Pearson's correlation: 0.69).
• The IFT composite biomarker outperformed combined tapping tasks and MDS-UPDRS III composite biomarkers in detecting antiparkinsonian treatment effects.

Conclusions:

• The alternative index finger tapping (IFT) composite biomarker is a validated, objective, and easy-to-implement tool for monitoring antiparkinsonian treatment effects.
• This biomarker shows significant potential for enhancing the efficiency and reliability of clinical trials for Parkinson's disease.
• The findings support the adoption of the IFT composite biomarker in clinical trials for detecting treatment effects in Parkinson's disease patients.