Digital Phenotyping Using Multimodal Data
- PDF / 2,031,975 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 91 Downloads / 258 Views
PSYCHOSIS (A AHMED, SECTION EDITOR)
Digital Phenotyping Using Multimodal Data Alex S. Cohen 1,2 & Christopher R. Cox 1 & Michael D. Masucci 1,2 & Thanh P. Le 1,2 & Tovah Cowan 1,2 & Lyndon M. Coghill 2 & Terje B. Holmlund 3,4 & Brita Elvevåg 3,4 Accepted: 31 August 2020 # Springer Nature Switzerland AG 2020
Abstract Purpose of Review Digital phenotyping involves the quantification of in situ phenotypes using personal digital devices and holds the potential to dramatically reshape how serious mental illnesses (SMI) assessment is conducted. Despite promise, few, if any, digital phenotyping efforts for SMI have garnered the support necessary for clinical implementation. Recent Findings In this paper, we highlight how digital phenotyping efforts can be improved by integrating data from multiple channels (i.e., “multimodal” data integration). We begin by arguing that “multimodal” integration is critical for digital phenotyping of many, possibly most, SMI symptoms. Next, we consider computational approaches that can accommodate multimodal data. Summary We conclude by considering next steps for multimodal data for research and clinical applications. We punctuate this paper with examples of multimodal digital phenotyping using natural language processing (NLP) to measure speech disorganization in psychosis. Keywords Digital phenotyping . Multimodal . Machine learning . Serious mental illness . Ambulatory
Introduction: Digital Phenotyping Serious mental illnesses (SMI) are among the top causes of distress, disability, and burden known to humankind [1]. Accurate diagnosis, assessment, and monitoring are critical for optimizing treatment, minimizing side effects, and reducing expensive and invasive emergency interventions [2, 3]. Traditional clinical assessment demands expense of money, time, space, and other resources that collectively far exceed what individuals, organizations, and tax-payers are able or willing to shoulder [4]. Digital phenotyping involves the quantification of in situ phenotypes using personal digital This article is part of the Topical Collection on Psychosis * Alex S. Cohen [email protected] 1
Department of Psychology, Louisiana State University, 236 Audubon Hall, Baton Rouge, LA 70803, USA
2
Center for Computation and Technology, Louisiana State University, 1079 Digital Media Center, Baton Rouge, LA 70803, USA
3
Department of Clinical Medicine, UiT The Arctic University of Norway, Tromsø, Norway
4
The Norwegian Centre for eHealth Research, University Hospital of North Norway, Tromsø, Norway
devices and holds the potential to dramatically reshape how SMI assessment is conducted [5–8]. From a pragmatic perspective, digital phenotyping allows for automation and dissemination in ways traditional measures cannot. This can potentially improve the efficiency and ecological validity of data collection, for example, by using machine learning from data collected using inexpensive mobile recording devices and social medial platforms as individuals navigate their daily routines. The use of “big data,” coll
Data Loading...
