Using Smartphones and Machine Learning to Quantify Parkinson Disease Severity

Abstract

IMPORTANCE Current Parkinson disease (PD) measures are subjective, rater-dependent, and assessed in clinic. Smartphones can measure PD features, yet no smartphone-derived rating score exists to assess motor symptom severity in real-world settings.OBJECTIVES To develop an objective measure of PD severity and test construct validity by evaluating the ability of the measure to capture intraday symptom fluctuations, correlate with current standard PD outcome measures, and respond to dopaminergic therapy. DESIGN, SETTING, AND PARTICIPANTSThis observational study assessed individuals with PD who remotely completed 5 tasks (voice, finger tapping, gait, balance, and reaction time) on the smartphone application. We used a novel machine-learning-based approach to generate a mobile Parkinson disease score (mPDS) that objectively weighs features derived from each smartphone activity (eg, stride length from the gait activity) and is scaled from 0 to 100 (where higher scores indicate greater severity). Individuals with and without PD additionally completed standard in-person assessments of PD with smartphone assessments during a period of 6 months. MAIN OUTCOMES AND MEASURESAbility of the mPDS to detect intraday symptom fluctuations, the correlation between the mPDS and standard measures, and the ability of the mPDS to respond to dopaminergic medication. RESULTSThe mPDS was derived from 6148 smartphone activity assessments from 129 individuals (mean [SD] age, 58.7 [8.6] years; 56 [43.4%] women). Gait features contributed most to the total mPDS (33.4%). In addition, 23 individuals with PD (mean [SD] age, 64.6 [11.5] years; 11 [48%] women) and 17 without PD (mean [SD] age 54.2 [16.5] years; 12 [71%] women) completed in-clinic assessments. The mPDS detected symptom fluctuations with a mean (SD) intraday change of 13.9 (10.3) points on a scale of 0 to 100. The measure correlated well with the Movement Disorder Society Unified Parkinson Disease's Rating Scale total (r = 0.81; P < .001) and part III only (r = 0.88; P < .001), the Timed Up and Go assessment (r = 0.72; P = .002), and the Hoehn and Yahr stage (r = 0.91; P < .001). The mPDS improved by a mean (SD) of 16.3 (5.6) points in response to dopaminergic therapy. CONCLUSIONS AND RELEVANCEUsing a novel machine-learning approach, we created and demonstrated construct validity of an objective PD severity score derived from smartphone assessments. This score complements standard PD measures by providing frequent, objective, real-world assessments that could enhance clinical care and evaluation of novel therapeutics.

A roadmap for implementation of patient‐centered digital outcome measures in Parkinson's disease obtained using mobile health technologies

“…This is where mobile technologies have the potential to excel, perhaps justifying imperfect correlations with clinical scales simply because the objective measurements outperform the more subjective clinical assessments, which are prone to substantial inter‐ and intrarater variability. In other words, large differences or large detection gaps between digital outcomes and existing scales are in fact desirable because both capture different and perhaps even complementary domains (eg, as the “Mobile Parkinson Disease Score” obtained with smartphones and data analyzed with machine learning) . To be validated, nevertheless, mobile health technologies will require such aspects as accuracy (laboratory validity), reliability (test‐retest within and between sensors), sensitivity, and minimal clinically significant difference for any endpoint of interest when tested against direct patient input or any robust measure of clinical meaningfulness (eg, a pull test to compare a new digital biomarker for balance).…”

The Parkinson's disease e‐diary: Developing a clinical and research tool for the digital age

“…Active data collection should be tailored for motor and nonmotor symptoms. Examples for motor symptoms include spiral drawing, finger tapping, and voice characteristics and for nonmotor symptoms, assessments of visual performance and short‐term memory . Passive measures should be obtained in an unsupervised and unobtrusive fashion, recorded preferentially during patients' daily regular activities.…”

An update on adaptive deep brain stimulation in Parkinson's disease

“…These systems include, for example, wearables and mobile applications and distinguish themselves from systems discussed above by adding assessments of cognition, speech, subjective disease burden, and active motor tasks. This potential was recently underlined by development of a smartphone application to capture symptom fluctuation during the day …”