STOP: Sentient Tracking of Parkinson’s
Effective monitoring of patients is technically challenging with wearables due to: 1) battery life is limited to a few hours when sampling and processing data continuously; 2) it is not feasible to process large amounts of sensor data on a wearable (e.g., a smartwatch). Instead of wearables, we leverage widely available technology such as smartphones, and Internet-of-Things (IoT) sensors, and augment their sensing capabilities with user-centric machine learning to create an infrastructure that links medication alerts to movement phenomena in real-time, to improve medication dosing for Parkinson’s patients and to unobtrusively monitor the progression of Parkinson’s Disease (PD).
STOP makes possible PD real-time symptom tracking, empowers DBS (Deep Brain Stimulation) patients with intelligent micro-adjustments of neurostimulators’ electrical stimulation, and provides medication dosing awareness and reminders for improving medication compliance. STOP provides valuable PD information for clinicians (e.g., a personal understanding of medication dosing lasting effects, the impact of PD symptoms in daily tasks, potential changes in mobility and social behaviour), thus potentially improving the efficiency of PD health services. STOP can minimize travel: clinically relevant data can be gathered and delivered remotely to clinicians and health researchers, allowing them to intervene, study and better understand PD; monitor PD unobtrusively over clinically relevant time periods: sensor data is gathered autonomously over long periods of time to better understand the manifestation of PD symptoms during day-to-day activities and inform future interventions and guidelines; provide clinically predictive modelling of medication need: intelligent personal modelling of users will allow for tailored PD support, particularly when PD symptoms are troublesome and require medication and DBS intervention.
Following AWARE’s plugin-based architecture, STOP will be a scalable, battery-conscious, cost-effective PD monitoring solution that uses commercially available smartphones and IoT sensors to collect and judiciously send data to a cloud infrastructure to improve PD patients’ quality of life. STOP will transform the care of PD by enabling an ecosystem of support involving patients, families, caregivers, clinicians and health researchers, working together. By monitoring the progression of PD, clinicians can better understand the effects of the medication, users’ lifestyle and individual Parkinson’s progression. Effective monitoring, analysis of movements and predictive modelling can be used by clinicians to send real-time medication alerts, improve medication adherence, and monitor PD patients’ quality of life from afar, also applicable for other neurological disorders, such as dementia, Alzheimer’s and Huntington’s.
STOP is a toolkit for PD observation available both for Android and iOS. It allows to colleсt symptoms snapshots and medication regimen adherance continuosly.
The application components have been evaluated in three trial studies; one trial was month-long in-the-wild and performed in Finland and in the UK.
Assesses level of tremor by collecting sensors data. Allows to edit ball speed, UI size, game time for experimental reusability.
Touch screen tasks
Measures effect of dexterity and dyskinesia via Archimedian spiral and square-shape drawing excercises.
Wearable device used for uderstanding muscle rigidity by colecting motion and EMG samples.
Self-reporting of medication plan and general symptoms (UPDRS). Requested to be filled only on first application run.
Retrospective log of every medication intake time. Supports manual input and natural voice recognition, e.g. "two hours ago".
Query about general health stated for the previous day. Shows up once per day between 10:00 and 11:00 AM.
STOP is designed to be accessbile for patients: notification reminders, big-shaped buttons, voice input, feedback acceptance.
- Elina Kuosmanen, Valerii Kan, Aku Visuri, Assam Boudjelthia, Lokmane Krizou, and Denzil Ferreira. 2019. Measuring Parkinson's Disease Motor Symptoms with Smartphone-based Drawing Tasks. In Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2019 International Symposium on Wearable Computers (UbiComp '19). ACM. (Accepted)
- Elina Kuosmanen, Valerii Kan, Julio Vega, Aku Visuri, Yuuki Nishiyama, Anind K. Dey, Simon Harper, and Denzil Ferreira. 2019. Challenges of Parkinson’s Disease: User Experiences with STOP. In Proceedings of the 21th International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI '19). ACM. (Accepted)
- Elina Kuosmanen, Valerii Kan, Aku Visuri, Julio Vega, Yuuki Nishiyama, Anind K. Dey, Simon Harper, and Denzil Ferreira. 2018. Mobile-based Monitoring of Parkinson’s Disease. In Proceedings of the 17th International Conference on Mobile and Ubiquitous Multimedia (MUM 2018). ACM, 441–448.
- Valerii Kan, Dorina Rajanen, Kennedy Opoku Asare, and Denzil Ferreira. 2018. STOP: A Smartphone-based Game for Parkinson’s Disease Medication Adherence. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers (UbiComp '18). ACM, 373–376.
- Valerii Kan. 2018. STOP: A Smartphone-Based Game for Parkinson’s Disease Medication Adherence. Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu.