Predicting Symptom Trajectories of Schizophrenia using Mobile Sensing

Wang, Rui; Wang, Weichen; Aung, Min S. H.; Ben‐Zeev, Dror; Brian, Rachel; Campbell, Andrew T.; Choudhury, Tanzeem; Hauser, Marta; Kane, John M.; Scherer, Emily A.; Walsh, Megan

doi:10.1145/3130976

Cited by 88 publications

(101 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Work to date in this area has focused on several issues including monitoring people already diagnosed with mental health issues such as schizophrenia [7,10,86,87] and depression [17,18], and monitoring general populations for signs of depression [69] or examining mood [55]. Other work has looked at specific populations and contexts, for example looking at stress in the workplace [29].…”

Section: Digital Phenotyping and Smartphone Datamentioning

confidence: 99%

Student Perspectives on Digital Phenotyping

Rooksby

Morrison²,

Murray-Rust

2019

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

There is a mental health crisis facing universities internationally. A growing body of interdisciplinary research has successfully demonstrated that using sensor and interaction data from students' smartphones can give insight into stress, depression, mood, suicide risk and more. The approach, which is sometimes termed Digital Phenotyping, has potential to transform how mental health and wellbeing can be monitored and understood. The approach could also transform how interventions are designed, delivered and evaluated. To date, little work has addressed the human and ethical side of digital phenotyping, including how students feel about being monitored. In this paper we report findings from in-depth focus groups, prototyping and interviews with students. We find they are positive about mental health technology, but also that there are multi-layered issues to address if digital phenotyping is to become acceptable. Using an acceptability framework, we set out the key design challenges that need to be addressed. CCS CONCEPTS • Human-centered computing → Empirical studies in ubiquitous and mobile computing;

show abstract

Section: Digital Phenotyping and Smartphone Datamentioning

confidence: 99%

Student Perspectives on Digital Phenotyping

Rooksby

Morrison²,

Murray-Rust

2019

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Ben et al 2 first explored the feasibility and acceptability of behavioral sensing in outpatients and inpatients with schizophrenia. The CrossCheck study used passive mobile sensing data, including physical activity, sociability, mobility, phone usage, sleep, and characteristics of ambient environments to predict the aggregated self-reported ecological momentary assessment (EMA) scores for 10 different symptom items 11 and the total scores of monthly 7-item Brief Psychiatric Rating Scale (BPRS) administered by clinicians 12 .…”

mentioning

confidence: 99%

Using behavioral rhythms and multi-task learning to predict fine-grained symptoms of schizophrenia

Tseng

Sano

Ben‐Zeev

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

Schizophrenia is a severe and complex psychiatric disorder with heterogeneous and dynamic multi-dimensional symptoms. Behavioral rhythms, such as sleep rhythm, are usually disrupted in people with schizophrenia. As such, behavioral rhythm sensing with smartphones and machine learning can help better understand and predict their symptoms. Our goal is to predict fine-grained symptom changes with interpretable models. We computed rhythm-based features from 61 participants with 6,132 days of data and used multi-task learning to predict their ecological momentary assessment scores for 10 different symptom items. By taking into account both the similarities and differences between different participants and symptoms, our multi-task learning models perform statistically significantly better than the models trained with single-task learning for predicting patients’ individual symptom trajectories, such as feeling depressed, social, and calm and hearing voices. We also found different subtypes for each of the symptoms by applying unsupervised clustering to the feature weights in the models. Taken together, compared to the features used in the previous studies, our rhythm features not only improved models’ prediction accuracy but also provided better interpretability for how patients’ behavioral rhythms and the rhythms of their environments influence their symptom conditions. This will enable both the patients and clinicians to monitor how these factors affect a patient’s condition and how to mitigate the influence of these factors. As such, we envision that our solution allows early detection and early intervention before a patient’s condition starts deteriorating without requiring extra effort from patients and clinicians.

show abstract

“…A small but growing body of literature suggests that individual mobility behaviours are consequential for people's mental health and general well‐being (e.g. depression symptoms, schizophrenia symptoms, and mood; Saeb, Lattie, Kording, & Mohr, 2017; Sandstrom, Lathia, Mascolo, & Rentfrow, 2017; Wang et al, 2017). However, past studies were mostly focused on a narrow set of mobility behaviours and/or isolated indicators of subjective well‐being (e.g.…”

Section: Understanding and Assessing Everyday Mobility Behaviormentioning

confidence: 99%

Investigating the Relationships between Mobility Behaviours and Indicators of Subjective Well–Being Using Smartphone–Based Experience Sampling and GPS Tracking

et al. 2020

Self Cite

View full text Add to dashboard Cite

People interact with their physical environments every day by visiting different places and moving between them. Such mobility behaviours likely influence and are influenced by people's subjective well‐being. However, past research examining the links between mobility behaviours and well‐being has been inconclusive. Here, we provide a comprehensive investigation of these relationships by examining individual differences in two types of mobility behaviours (movement patterns and places visited) and their relationship to six indicators of subjective well‐being (depression, loneliness, anxiety, stress, affect, and energy) at two different temporal levels of analysis (two‐week tendencies and daily level). Using data from a large smartphone‐based longitudinal study (N = 1765), we show that (i) movement patterns assessed via GPS data (distance travelled, entropy, and irregularity) and (ii) places visited assessed via experience sampling reports (home, work, and social places) are associated with subjective well‐being at the between and within person levels. Our findings suggest that distance travelled is related to anxiety, affect, and stress, irregularity is related to depression and loneliness, and spending time in social places is negatively associated with loneliness. We discuss the implications of our work and highlight directions for future research on the generalizability to other populations as well as the characteristics of places. © 2020 European Association of Personality Psychology

show abstract

Predicting Symptom Trajectories of Schizophrenia using Mobile Sensing

Cited by 88 publications

References 55 publications

Student Perspectives on Digital Phenotyping

Student Perspectives on Digital Phenotyping

Using behavioral rhythms and multi-task learning to predict fine-grained symptoms of schizophrenia

Investigating the Relationships between Mobility Behaviours and Indicators of Subjective Well–Being Using Smartphone–Based Experience Sampling and GPS Tracking

Contact Info

Product

Resources

About