I investigate personalized methodologies to monitor chronic conditions that affect daily human behavior using smartphone and wearable data. I have experience applying machine learning classification algorithms, time series, and N-of-1 methods, as well as building open-source software to support our work. I collaborate with patients, clinicians, and researchers from multiple disciplines and try to prioritize user-centered approaches. In the long term, my goal is to explore how we can enable patients to inform, amend, and evaluate their health tracking algorithms to improve disease self-management.

I am a Postdoctoral Research Associate at the Mobile Sensing + Health Institute mentored by Carissa Low. I am also the designer and lead developer of the Reproducible Analysis Pipeline for Data Streams (RAPIDS), an open source pipeline to standardize the data processing, analysis, and evaluation of mobile sensing projects. Here are links to presentations about my work, papers I have published, and software that I developed.

These are some projects I am helping with:

• ROSA | Remote Oncology Symptom Assessment Using Smartphones and Fitbits
• RHYTHMS | Symptom Burden Self-Reported by Perioperative Patients Undergoing Pancreatic Surgery
• UPLIFT | Using Personalized Lifestyle Interventions for Fatigue Treatment in Cancer Survivors
• RAPIDS | Reproducible Analysis Pipeline for Data Streams
• PDCareBox | Aggregator of new techniques for dealing with Parkinson’s in daily life
• CAREY | A platform to support remote caregiving using mobile sensors

These are the places I worked at before:

• University of Bristol | Detecting Mental Health Behaviours Using Mobile Interactions (DeMMI)
• University of Manchester (PhD) | Unobtrusive and Personalised Monitoring of Parkinson’s Using Smartphones
• University of Oulu | On depression prediction and on a mobile app for monitoring Parkinson’s hand motor symptoms
• Microsoft Research | I was an intern on Project Emma, and a contributor on a follow-up study with Columbia University