Transforming Psychiatry into Data-Driven Medicine with Digital Measurement Tools

Abstract

Psychiatry has been limited by historically rooted practices centered primarily on subjective observation. Fields such as oncology have progressed toward data-driven clinical decision-making that combines subjective clinical assessment of symptoms and preferences with biological measures such as genetics, biomarkers, imaging, and integrative physiology to derive quantitative risk scores and decision support. In contrast, psychiatry has just begun to scratch the surface of measurement-based care with validated clinical questionnaires. An opportunity exists to improve modern psychiatric care with novel data streams from digital sensors combined with clinical observation and subjective self-report. The prospect of integrating this complex information with modern computational and analytical methods could advance the field, both in research and clinical practice. Here we discuss this possibility and propose some key priorities to enable these innovations toward improving clinical outcomes in the future.

Continuous digital collection of patient-reported outcomes during inpatient treatment for affective disorders – implementation and feasibility

“…The copyright holder for this preprint this version posted September 1, 2020. ; https://doi.org/10.1101/2020.08.27.20183400 doi: medRxiv preprint data throughout the course of treatment. Moreover, the digital implementation of PROs will allow for more precise and immediate data storage and analysis (Hsin et al, 2018). In the future, such an infrastructure of digital data collection could be used to communicate treatment outcomes and visual representations thereof directly to patients.…”

“…However, previous work relies on extremely homogeneous study populations that are carefully selected according to strict inclusion and exclusion criteria. Any machine learning models trained on such data are of little value when findings are to be generalised to the clinical reality that are highly diverse inpatient populations (Hsin, Fromer, & Califf, 2018;Humphreys & All rights reserved. No reuse allowed without permission.…”

The Digital Phenotyping Project: A Psychoanalytical and Network Theory Perspective

“…The RDoC project seems to announce an approach to diagnosis in which a person's self-reflexive relation to his own suffering is left out. Indeed, there seems to be a rupture with any form of subjectivism behind this project (Kozak and Cuthbert, 2016;Hsin et al, 2018). For Frances, however, human understanding of psychopathology and its treatment methods has not really improved (Frances, 2014).…”

Applying speech technologies to assess verbal memory in patients with serious mental illness

“…Furthermore, only a few test versions exist, which are typically administered in controlled settings (i.e., in the laboratory or clinic) in a cross-sectional manner thus precluding a finegrained examination on a daily basis of the relationship to clinical state and treatment. In toto this limits scientific progress in terms of applications within psychiatry and its role as a future biomarker or digital phenotype for personalized medicine purposes 4,5 . To address this, we exploited the fact that verbal recall is expressed via speech and that this data stream is potentially suited to processing with modern speech technologies.…”