New smartphone app, office-based screening tool allow easy assessment of Parkinson’s disease
Two groups of investigators recently developed a smartphone application (app) and a simple office-based tool that allow remote evaluation of symptom severity and dementia risk, respectively, in patients with Parkinson’s Disease (PD).
The Android smartphone app, HopkinsPD, assesses PD symptoms based on five simple tasks involving voice sensing, finger tapping, gait measurement, balance, and reaction time. [JAMA Neurol 2018, doi: 10.1001/jamaneurol.2018.0809]
“Current PD measures are subjective and rater-dependent, and require in-clinic assessments,” pointed out investigators from the US and UK. “Many motor symptoms of PD are well-suited to objective measurement by smartphones. Smartphone assessment has been evaluated in PD, but most studies focused on a specific feature rather than overall symptom burden.”
Besides the app, the investigators also created a mobile PD score (mPDS) via machine learning, which serves as an objective measure of PD severity. The score was validated in 129 patients with PD, showing that PD symptom severity assessed by the app aligned closely with that assessed by neurologists.
“mPDS is a novel measure that provides rapid, remote and objective assessment of PD symptom severity on widely available smartphones,” the investigators noted. “Unlike current standard measures, which can take years and significant resources to develop, mPDS was generated quickly from a relatively small number of participants using automated techniques that can account for noise in data collected from multiple smartphone sensors and self-reported medication administration.”
“Combining smartphone data with the machine-learning methods outlined here may also provide opportunities for developing objective severity measures in other neurological conditions,” they added.
Meanwhile, another group of investigators from Canada, Japan and Sweden developed and validated the Montreal Parkinson Risk of Dementia Scale (MoPaRDS) to screen for dementia risk in patients with PD. [JAMA Neurol 2018, doi: 10.1001/jamaneurol.2018.0254]
MoPaRDS is an office-based screening tool consisting of eight simple clinical items, namely 1) <70 years of age; 2) male sex; 3) falls and/or freezing; 4) bilateral disease onset; 5) history of rapid eye movement sleep behaviour disorder; 6) orthostatic hypotension; 7) mild cognitive impairment; and 8) visual hallucinations.
Despite its simplicity, the scale demonstrated predictive validity equal to or greater than previously described algorithms using biomarkers assessments. The annual rate of conversion to dementia was 14.9 percent in the high-risk group (score >5), 5.8 percent in the intermediate-risk group (score 4–5), and 0.6 percent in the low-risk group (score 0–3). A cutoff score of ≥4 yielded a sensitivity of 77.1 percent, specificity of 87.2 percent, positive predictive value of 43.9 percent, and negativity predictive value of 96.7 percent.
“The main advantage of the MoPaRDS is its practicality for clinical use. Featuring demographic data as well as motor and nonmotor signs, the items of the scale are already often screened for in a routine office visit of a PD patient, with no need for biological samples, neuroimaging or genetic testing,” the investigators wrote.