Predicting Symptom Trajectories of Schizophrenia using Mobile Sensing

Citations Over TimeTop 10% of 2017 papers

Abstract

Continuously monitoring schizophrenia patients’ psychiatric symptoms is crucial for in-time intervention and treatment adjustment. The Brief Psychiatric Rating Scale (BPRS) is a survey administered by clinicians to evaluate symptom severity in schizophrenia. The CrossCheck symptom prediction system is capable of tracking schizophrenia symptoms based on BPRS using passive sensing from mobile phones. We present results from an ongoing randomized control trial, where passive sensing data, self-reports, and clinician administered 7-item BPRS surveys are collected from 36 outpatients with schizophrenia recently discharged from hospital over a period ranging from 2-12 months. We show that our system can predict a symptom scale score based on a 7-item BPRS within ±1.45 error on average using automatically tracked behavioral features from phones (e.g., mobility, conversation, activity, smartphone usage, the ambient acoustic environment) and user supplied self-reports. Importantly, we show our system is also capable of predicting an individual BPRS score within ±1.59 error purely based on passive sensing from phones without any self-reported information from outpatients. Finally, we discuss how well our predictive system reflects symptoms experienced by patients by reviewing a number of case studies.

Related Papers

• → Clinical implications of Brief Psychiatric Rating Scale scores(2005)886 cited
• → The Brief Psychiatric Rating Scale(1994)61 cited
• The brief psychiatric rating scale: effect of scaling system on clinical response assessment.(1994)
• → Use of the Brief Psychiatric Rating Scale to Facilitate Differential Diagnosis at Acute Inpatient Admission(2001)8 cited
• → Itemized clinician ratings versus global ratings of symptom severity in patients with schizophrenia(2002)3 cited