Smartphone App Measures Parkinson's Severity

This should be so easy to modify this for stroke but our fucking failures of stroke associations will DO NOTHING. Your doctor will DO NOTHING . Your stroke hospital will DO NOTHING.  You're screwed. 
https://www.medpagetoday.com/neurology/parkinsonsdisease/71995

• by

Judy George, Contributing Writer, MedPage Today March 26, 2018

A smartphone application can provide objective measures of Parkinson's disease (PD) severity to help manage symptoms more effectively, reported researchers from Johns Hopkins University and the University of Rochester.

With the HopkinsPD app, Parkinson's disease patients can report objective, real-time movements and responses to medication to complement standard measures. "Patients can use their mobile phones to complete a few simple tasks which the proposed method turns into an objective score," explained Suchi Saria, PhD, of Johns Hopkins' Department of Computer Science. "This score, when plotted over time, provides a lens into the patient's Parkinson symptom profile and how it's varying over time."

In an observational study published online in JAMA Neurology, Saria and colleagues assessed individuals with PD who remotely completed five tasks -- voice, finger tapping, gait, balance, and reaction time -- on the app. A novel machine-learning approach was used that objectively weighed features derived from each smartphone activity -- stride length from the gait activity, for example -- and generated a mobile Parkinson disease score (mPDS) with a scale from 0 to 100.

The mobile score captured intraday symptom fluctuations, correlated strongly with current standard rating scales, and detected responses to dopaminergic therapy.

"Patients with Parkinson's disease show large fluctuations in disease severity from hour to hour," Saria noted. "But right now, we don't have ways to measure daily symptom fluctuations." Currently, many patients keep a motor diary and record when they experience good symptom control or complications like dyskinesia; these diaries are used to adjust medication doses.

"If we could measure daily symptom fluctuations and long-term trends in symptom severity objectively, it would be possible to titrate medications more precisely based on an individual's symptom profile," she said. "If the patient is not being responsive, we could add or change the mode of delivery or add medications to improve efficacy of levodopa."

The researchers derived the mPDS from 6,148 smartphone activity assessments collected from 129 individuals. Gait contributed 33% to the total score, balance 23%, finger-tapping 23%, voice 17%, and reaction time 3%.

The analysis showed that the mPDS correlated well with the Movement Disorder Society Unified Parkinson Disease's Rating Scale total (correlation coefficient r=0.81; P*lt;0.001) and part III only (r=0.88; P<0.001), the Timed Up and Go assessment (r=0.72; P=0.002), and the Hoehn and Yahr stage (r=0.91; P<0.001). The measure detected symptom fluctuations with a mean intraday change of 13.9 points, and improved by 16.3 points when patients received dopaminergic therapy.
The mPDS needs to be validated further in a larger sample, the researchers noted. And while this approach was applied to a smartphone application, it could be extended to wearable sensors or other devices, Saria said.

The study was funded in part by the Michael J. Fox Foundation and the National Institute of Neurological Disorders and Stroke.

The authors reported having no conflicts of interest.

last updated 03.26.2018

• Primary Source

JAMA Neurology

Source Reference: Zhan A, et al "Using smartphones and machine learning to quantify Parkinson disease severity: The mobile Parkinson disease score" JAMA Neurology 2018; DOI:10.1001/jamaneurol.2018.0809.