Nicholas C Jacobson1, Damien Lekkas2, Raphael Huang3, Natalie Thomas3. 1. Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, United States; Department of Biomedical Data Science, Geisel School of Medicine, Dartmouth College, United States; Department of Psychiatry, Geisel School of Medicine, Dartmouth College, United States; Quantitative Biomedical Sciences Program, Dartmouth College, United States. Electronic address: Nicholas.C.Jacobson@dartmouth.edu. 2. Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, United States; Quantitative Biomedical Sciences Program, Dartmouth College, United States. 3. Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, United States.
Abstract
BACKGROUND: Recent studies have demonstrated that passive smartphone and wearable sensor data collected throughout daily life can predict anxiety symptoms cross-sectionally. However, to date, no research has demonstrated the capacity for these digital biomarkers to predict long-term prognosis. METHODS: We utilized deep learning models based on wearable sensor technology to predict long-term (17-18-year) deterioration in generalized anxiety disorder and panic disorder symptoms from actigraphy data on daytime movement and nighttime sleeping patterns. As part of Midlife in the United States (MIDUS), a national longitudinal study of health and well-being, subjects (N = 265) (i) completed a phone-based interview that assessed generalized anxiety disorder and panic disorder symptoms at enrollment, (ii) participated in a one-week actigraphy study 9-14 years later, and (iii) completed a long-term follow-up, phone-based interview to quantify generalized anxiety disorder and panic disorder symptoms 17-18 years from initial enrollment. A deep auto-encoder paired with a multi-layered ensemble deep learning model was leveraged to predict whether participants experienced increased anxiety disorder symptoms across this 17-18 year period. RESULTS: Out-of-sample cross-validated results suggested that wearable movement data could significantly predict which individuals would experience symptom deterioration (AUC = 0.696, CI [0.598, 0.793], 84.6% sensitivity, 52.7% specificity, balanced accuracy = 68.7%). CONCLUSIONS: Passive wearable actigraphy data could be utilized to predict long-term deterioration of anxiety disorder symptoms. Future studies should examine whether these methods could be implemented to prevent deterioration of anxiety disorder symptoms.
BACKGROUND: Recent studies have demonstrated that passive smartphone and wearable sensor data collected throughout daily life can predict anxiety symptoms cross-sectionally. However, to date, no research has demonstrated the capacity for these digital biomarkers to predict long-term prognosis. METHODS: We utilized deep learning models based on wearable sensor technology to predict long-term (17-18-year) deterioration in generalized anxiety disorder and panic disorder symptoms from actigraphy data on daytime movement and nighttime sleeping patterns. As part of Midlife in the United States (MIDUS), a national longitudinal study of health and well-being, subjects (N = 265) (i) completed a phone-based interview that assessed generalized anxiety disorder and panic disorder symptoms at enrollment, (ii) participated in a one-week actigraphy study 9-14 years later, and (iii) completed a long-term follow-up, phone-based interview to quantify generalized anxiety disorder and panic disorder symptoms 17-18 years from initial enrollment. A deep auto-encoder paired with a multi-layered ensemble deep learning model was leveraged to predict whether participants experienced increased anxiety disorder symptoms across this 17-18 year period. RESULTS: Out-of-sample cross-validated results suggested that wearable movement data could significantly predict which individuals would experience symptom deterioration (AUC = 0.696, CI [0.598, 0.793], 84.6% sensitivity, 52.7% specificity, balanced accuracy = 68.7%). CONCLUSIONS: Passive wearable actigraphy data could be utilized to predict long-term deterioration of anxiety disorder symptoms. Future studies should examine whether these methods could be implemented to prevent deterioration of anxiety disorder symptoms.
Authors: J M Christiana; S E Gilman; M Guardino; K Mickelson; P L Morselli; M Olfson; R C Kessler Journal: Psychol Med Date: 2000-05 Impact factor: 7.723
Authors: L N Robins; J Wing; H U Wittchen; J E Helzer; T F Babor; J Burke; A Farmer; A Jablenski; R Pickens; D A Regier Journal: Arch Gen Psychiatry Date: 1988-12
Authors: Ronald C Kessler; Maria Petukhova; Nancy A Sampson; Alan M Zaslavsky; Hans-Ullrich Wittchen Journal: Int J Methods Psychiatr Res Date: 2012-08-01 Impact factor: 4.035
Authors: R de Graaf; R V Bijl; J Spijker; A T F Beekman; W A M Vollebergh Journal: Soc Psychiatry Psychiatr Epidemiol Date: 2003-01 Impact factor: 4.328
Authors: Garrett I Ash; Matthew Stults-Kolehmainen; Michael A Busa; Allison E Gaffey; Konstantinos Angeloudis; Borja Muniz-Pardos; Robert Gregory; Robert A Huggins; Nancy S Redeker; Stuart A Weinzimer; Lauren A Grieco; Kate Lyden; Esmeralda Megally; Ioannis Vogiatzis; LaurieAnn Scher; Xinxin Zhu; Julien S Baker; Cynthia Brandt; Michael S Businelle; Lisa M Fucito; Stephanie Griggs; Robert Jarrin; Bobak J Mortazavi; Temiloluwa Prioleau; Walter Roberts; Elias K Spanakis; Laura M Nally; Andre Debruyne; Norbert Bachl; Fabio Pigozzi; Farzin Halabchi; Dimakatso A Ramagole; Dina C Janse van Rensburg; Bernd Wolfarth; Chiara Fossati; Sandra Rozenstoka; Kumpei Tanisawa; Mats Börjesson; José Antonio Casajus; Alex Gonzalez-Aguero; Irina Zelenkova; Jeroen Swart; Gamze Gursoy; William Meyerson; Jason Liu; Dov Greenbaum; Yannis P Pitsiladis; Mark B Gerstein Journal: Sports Med Date: 2021-09-01 Impact factor: 11.928