Neurologists monitor Parkinson’s Disease patient tremors with an in-office task-based Unified Parkinson’s Disease Rating Scale (UPDRS) to manage and treat the progressive disease. Unfortunately, as is the case with blood pressure measurements and other variable biometrics, anecdotal onsite exams can provide an incomplete assessment. We’ve looked at sensor arrays and a tablet-based drawing app, each designed to help with early Parkinson’s Disease detection.

When the American Heart Association updated the best practices for blood pressure measurement earlier this year, the suggested regimen included HPBM (home blood pressure monitoring) using oscillometric wearables. Researchers at Florida Atlantic University‘s (FAU) College of Engineering and Computer Science, the Icahn School of Medicine at Mount Sinai, and the University of Rochester Medical Center reported success using wearable sensors with machine learning algorithms to continuously monitor Parkinson’s Disease patients as they move about freely in their daily life. In a study published in Sensors, the researchers reported their findings tracking the full spectrum of tremors to estimate a total Parkinson tremor rating.

The research team, led by FAU, used one gyroscope sensor on the wrist and on the ankle. According to their report, the algorithm performed higher than other UPDRS and task-independent tremor estimation methods. The study indicates the FAU sensor and algorithm-based approach has significant potential for patient tremor monitoring and subsequent symptom management and treatment.