Parkinson's disease (PD) is a chronic neurological disease that negatively influences patients' quality of life (QoL). Reduced social interactions are a result of both PD symptoms and impairment in QoL, which is known as social withdrawal. Smartphones are suitable for monitoring social behaviour under the notion of digital phenotyping, as people spend significant time socialising on them. We implement year-long longitudinal research using smartphones to study social withdrawal in PD. In addition to an entire year of 24/7 continuous monitoring on smartphones, weekly social ratings and QoL are provided as self-report ground truth. Twenty-three features are extracted from more than 10 million raw data entries collected from eight participants. These features are then used to build models to reflect participants' self-report ratings. We consider the interactions that happen on smartphones, such as calls, messages and social media, and use smartphone sensors to infer face-to-face interactions. By applying multiple linear regression and Naive Bayes, our model is significantly better than just assigning mean and random guesses. The results suggest that our approach provides a more granular method for tracking social behaviour in people with PD via smartphones, and it could benefit wider communities where the social impact on patients needs attention.

We report the process used to create artefacts for self-reporting Parkinson's Disease symptoms. Our premise was that a technology-based approach would provide participants with an effective, flexible, and resilient technique. After testing four prototypes using Bluetooth, NFC, and a microcontroller we accomplished almost full compliance and high acceptance using a paper diary to track day-to-day fluctuations over 49 days. This diary is tailored to each patient's condition, does not require any handwriting, allows for implicit reminders, provides recording flexibility, and its answers can be encoded automatically. We share five design implications for future Parkinson's self-reporting artefacts: reduce participant completion demand, design to offset the effect of tremor on input, enable implicit reminders, design for positive and negative consequences of increased awareness of symptoms, and consider the effects of handwritten notes in compliance, encoding burden, and data quality.