Improving Medication Regimen Recommendation for Parkinson's Disease Using Sensor Technology

Abstract

Parkinson's disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson's patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician's initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson's medication changes-clinically assessed by the MDS-Unified Parkinson's Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients' cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose-with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.

Keywords: PKG; Parkinson’s disease; clustering; decision support tool; levodopa; machine learning; regimen; remote assessment; wearable sensors.

Figure A1

WCSS as a function of the number of clusters when clustering patients based on their best symptom control medication regimens between the two visits according to PKG’s summary dyskinesia and bradykinesia scores. The number of clusters is set to four, as a number towards the bottom of the “elbow” is considered best, but further increasing the number of clusters has been shown to reduce the model’s robustness.

Figure 1

Sample PKG sensor time-series data [23], displaying an individual’s change in dyskinesia and bradykinesia scores in response to medication with the median, 25th, and 75th percentile, compared to a non-PD control group averaged over six days. (A) The dyskinesia time-series, (B) the bradykinesia time-series, and (C) the patient’s self-reported acknowledgment of medication administration.

Figure 2

The study design is divided into two parts as labeled by the blocks “Clustering” and “Prediction”. In the clustering block, (A) we begin with a diverse cohort of PD patients; (B) each patient is assessed by MDS-UPDRS-III scores and PKG summary dyskinesia and bradykinesia scores; the physician icon is greyed out as in the future for some remote contexts this may be accomplished using only the PKG time-series data, but we currently collect both for validation purposes; (C) we identify similar medication regimen clusters through k-means clustering. These clusters are used in the prediction block; (D) we optimize medication regimens and perform statistical analysis on demographic similarities for each group—to create a decision support tool to provide enhanced initial regimen estimates; (E) machine learning methods, specifically random forest, are applied to predict an unknown patient’s optimized regimen cluster based on physician assessment and/or wearable sensor measurements depending on the context; (F) the new patient’s data will be incorporated to improve the accuracy of the decision support tool.

Figure 3

(a,b) demonstrates the clusters for the motor function changes between visit 1 to visit 2 based on the MDS-UPDRS-III scores and the PKG’s summary dyskinesia and bradykinesia scores, respectively. (c,d) highlight the subjects’ best symptom control recorded using MDS-UPDRS-III scores and PKG’s summary dyskinesia and bradykinesia scores, respectively. The large shapes denote each cluster’s centroid, and the exterior marker of each point corresponds to the cluster centroid shape. The capital letters (A–D) are used to refer to each cluster. Each point’s interior maker in (a,b) represents the state of MDS-UPDRS-III and PKG change for each patient, where a black interior-point denotes the patient stayed the same between visits, a green point denotes that the patient’s visit 2 scores were better than their visit 1 scores. A red point denotes that the patient’s visit 2 scores were worse than their visit 1 scores. Note that due to the three-dimensional projection of the plot, the distance between points may appear skewed. See Supplemental Information for a 3-D animation showcasing the clusters’ position in space.