Combining Continuous Smartphone Native Sensors Data Capture and Unsupervised Data Mining Techniques for Behavioral Changes Detection: A Case Series of the Evidence-Based Behavior (eB2) Study

Abstract

BackgroundThe emergence of smartphones, wearable sensor technologies, and smart homes allows the nonintrusive collection of activity data. Thus, health-related events, such as activities of daily living (ADLs; eg, mobility patterns, feeding, sleeping, ...) can be captured without patients’ active participation. We designed a system to detect changes in the mobility patterns based on the smartphone’s native sensors and advanced machine learning and signal processing techniques.ObjectiveThe principal objective of this work is to assess the feasibility of detecting mobility pattern changes in a sample of outpatients with depression using the smartphone’s sensors. The proposed method processed the data acquired by the smartphone using an unsupervised detection technique.MethodsIn this study, 38 outpatients from the Hospital Fundación Jiménez Díaz Psychiatry Department (Madrid, Spain) participated. The Evidence-Based Behavior (eB2) app was downloaded by patients on the day of recruitment and configured with the assistance of a physician. The app captured the following data: inertial sensors, physical activity, phone calls and message logs, app usage, nearby Bluetooth and Wi-Fi connections, and location. We applied a change-point detection technique to location data on a sample of 9 outpatients recruited between April 6, 2017 and December 14, 2017. The change-point detection was based only on location information, but the eB2 platform allowed for an easy integration of additional data. The app remained running in the background on patients’ smartphone during the study participation.ResultsThe principal outcome measure was the identification of mobility pattern changes based on an unsupervised detection technique applied to the smartphone’s native sensors data. Here, results from 5 patients’ records are presented as a case series. The eB2 system detected specific mobility pattern changes according to the patients’ activity, which may be used as indicators of behavioral and clinical state changes.ConclusionsThe proposed technique could automatically detect changes in the mobility patterns of outpatients who took part in this study. Assuming these mobility pattern changes correlated with behavioral changes, we have developed a technique that may identify possible relapses or clinical changes. Nevertheless, it is important to point out that the detected changes are not always related to relapses and that some clinical changes cannot be detected by the proposed method.

A digital companion for ecological momentary assessment and prevention of suicide: A case series on the use of the emma app

“…Currently emma allows the active collection of the subjective state self-assessed by the user. However, we would like to complete it with a seamless [51,92] in situ collection of objective data, particularly on connectedness indicators that have been evaluated only in few studies related to suicide [19]. Therefore, we plan to implement digital phenotyping/footprinting [15,93,94] in the app to collect all metadata on phone use (number, duration, direction of calls and sms) and activity on social media because they appear to be a very promising field of exploration and intervention in suicidology (Notredame in press).…”

Study protocol of a randomised clinical trial testing whether metacognitive training can improve insight and clinical outcomes in schizophrenia

“…Functioning Functioning will be recorded through the Global Assessment of Functioning (GAF) [42], the World Health Organization Disability Schedule (WHO-DAS) [43] and the Satisfaction Life Domains Scale (SLDS) [44]. In addition, as a relatively novel methodology in patients with psychotic disorders, ecological momentary assessment (EMA) [27] will be piloted in a subsample of those participants who agree to set up two web-based applications in their smartphones, namely Memind (www.memind.net) and eB2 [28]. Memind is an 'active' platform which has two different interfaces or views, namely staff and patient view.…”

“…As secondary aims, we will investigate the effect of MCT-related insight changes on clinical outcomes, including symptomatic severity, hospitalizations, suicidal behaviour and psychosocial functioning. In addition, we will pilot the use of ecological momentary assessment (EMA) via two web-based applicationswww.MEmind.net [27] and the Evidence-Based Behaviour platform eB2 app [28] -to measure functioning in a subsample of participants.…”

Using Machine Learning and Smartphone and Smartwatch Data to Detect Emotional States and Transitions: Exploratory Study

“…Research has been conducted in the quest for gold standard digital biomarkers that can be collected through consumer-grade smartphones and wearable sensors (eg, accelerometer, audio, location, phone log, sound features, etc) to detect mental health disorders in the early stages [ 4 , 5 ]. It is evident that mobility patterns, location variations, and phone usage patterns captured by smartphones can aid in identifying patients with mental health illnesses and disorders [ 1 , 2 , 6 - 9 ]. Early detection of depressive symptoms by applying deep neural networks and ML techniques to self-reported contextual data through smartphones obtained promising results [ 8 ].…”