A review of physiological and behavioral monitoring with digital sensors for neuropsychiatric illnesses

Abstract

Physiological, behavioral, and psychological changes associated with neuropsychiatric illness are reflected in several related signals, including actigraphy, location, word sentiment, voice tone, social activity, heart rate, and responses to standardized questionnaires. These signals can be passively monitored using sensors in smartphones, wearable accelerometers, Holter monitors, and multimodal sensing approaches that fuse multiple data types. Connection of these devices to the internet has made large scale studies feasible and is enabling a revolution in neuropsychiatric monitoring. Currently, evaluation and diagnosis of neuropsychiatric disorders relies on clinical visits, which are infrequent and out of the context of a patient's home environment. Moreover, the demand for clinical care far exceeds the supply of providers. The growing prevalence of context-aware and physiologically relevant digital sensors in consumer technology could help address these challenges, enable objective indexing of patient severity, and inform rapid adjustment of treatment in real-time. Here we review recent studies utilizing such sensors in the context of neuropsychiatric illnesses including stress and depression, bipolar disorder, schizophrenia, post traumatic stress disorder, Alzheimer's disease, and Parkinson's disease.

Figures

Figure 1

Geolocation data measured via smartphone can track time spent at modal locations. The x- and y-axes are distance from the most commonly visited location. The z-axis is the percentage of total time spent in a given location, with darker orange encoding a higher percentage and a lighter yellow encoding a lower percentage. The dark orange peak at the origin where the individual spends the most time is assumed to be home, and the second-largest peak (z-axis value) where the individual spends the next most time is assumed to be work, or vice-versa if the individual spends more time at work than home.

Figure 2

Social network activity measured via smartphone can identify mood and illness. The y-axis encodes unique pairings of sender and recipient IDs. The x-axis encodes time. The radius of each colored dot is proportional to the number of calls and text messages in one day. Interactions from a sender-recipient pairing have the same color over time, i.e. all red dots with the same height on the y-axis represent interactions between the same two unique individuals. Qualitatively, (a) healthy controls demonstrate more regular amounts of interaction over time with their social contacts compared to (b) subjects with bipolar disorder who alternate bouts of high and low levels of interaction.

Figure 3

Screenshots of the AMoSS app for the Android operating system: (a) PHQ-9 questionnaire, (b) Simple mood assessment tool, and (c) “MoodZoom” survey to assess emotional status and mood.

Figure 4

A “double-plot” of wearable accelerometry or actigraphy data demonstrates night-to-night patterns. The x-axis is the date, and the y-axis is time of day. Each day is repeated adjacent to and below the previous day. This aligns the nights of data and can be particularly useful in depicting circadian rhythm sleep disorders. (a) Actigraphy levels in a healthy control. (b) Actigraphy levels in a patient with borderline personality disorder.