Back

Mobile Monitoring of Mood (MoMo-Mood) Pilot: A Longitudinal, Multi-Sensor Digital Phenotyping Study of Patients with Major Depressive Disorder and Healthy Controls

Triana, A. M.; Martikkala, A.; Baryshnikov, I.; Heikkila, R.; Alakörkkö, T.; Darst, R. K.; Ekelund, J.; Isometsä, E.; Aledavood, T.

2020-11-04 health informatics
10.1101/2020.11.02.20222919 medRxiv
Show abstract

Mental disorders are a major global cause of morbidity and mortality. The surge in adoption of smartphones and other wearable devices has made it possible to use the data generated by them for clinical purposes. In particular, in psychiatry, detailed and high-resolution information on patients state, mood, and behavior can significantly improve the assessment, diagnosis and the treatment of patients. However, there is long path to turn the raw data created by these sensors, to information and insights that can be applied in clinical practice. Here, we introduce the MoMo-Mood Pilot: a study created to investigate the feasibility of using smartphones and wearables as data collection tools from subjects suffering from major depressive disorder. We collect data from 14 patients and 22 controls in two phases (active and passive). We demonstrate the feasibility of monitoring patients with several devices over short periods and passively monitoring them over long periods of time with minimal disruption in their daily activities. We identify and describe a series of challenges in this process. The MoMo-Mood pilot study is an encouraging step in the process of determining the effectiveness of using wearables for quantifying the behavior and the state of psychiatric patients with high temporal resolution, which can lead to their potential adoption in clinical practice.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.