Youngseo Son1, Sean A P Clouston2,3, Roman Kotov4, Johannes C Eichstaedt5, Evelyn J Bromet4, Benjamin J Luft6, H Andrew Schwartz1. 1. Department of Computer Science, Stony Brook University, New York, USA. 2. Program in Public Health, Stony Brook University, New York, USA. 3. Department of Family, Population and Preventive Medicine, Stony Brook University, New York, USA. 4. Department of Psychiatry, Stony Brook University, New York, USA. 5. Department of Psychology & Institute for Human-Centered A.I., Stanford University, Stanford, California, USA. 6. Department of Medicine, Stony Brook University, New York, USA.
Abstract
BACKGROUND: Oral histories from 9/11 responders to the World Trade Center (WTC) attacks provide rich narratives about distress and resilience. Artificial Intelligence (AI) models promise to detect psychopathology in natural language, but they have been evaluated primarily in non-clinical settings using social media. This study sought to test the ability of AI-based language assessments to predict PTSD symptom trajectories among responders. METHODS: Participants were 124 responders whose health was monitored at the Stony Brook WTC Health and Wellness Program who completed oral history interviews about their initial WTC experiences. PTSD symptom severity was measured longitudinally using the PTSD Checklist (PCL) for up to 7 years post-interview. AI-based indicators were computed for depression, anxiety, neuroticism, and extraversion along with dictionary-based measures of linguistic and interpersonal style. Linear regression and multilevel models estimated associations of AI indicators with concurrent and subsequent PTSD symptom severity (significance adjusted by false discovery rate). RESULTS: Cross-sectionally, greater depressive language (β = 0.32; p = 0.049) and first-person singular usage (β = 0.31; p = 0.049) were associated with increased symptom severity. Longitudinally, anxious language predicted future worsening in PCL scores (β = 0.30; p = 0.049), whereas first-person plural usage (β = -0.36; p = 0.014) and longer words usage (β = -0.35; p = 0.014) predicted improvement. CONCLUSIONS: This is the first study to demonstrate the value of AI in understanding PTSD in a vulnerable population. Future studies should extend this application to other trauma exposures and to other demographic groups, especially under-represented minorities.
BACKGROUND: Oral histories from 9/11 responders to the World Trade Center (WTC) attacks provide rich narratives about distress and resilience. Artificial Intelligence (AI) models promise to detect psychopathology in natural language, but they have been evaluated primarily in non-clinical settings using social media. This study sought to test the ability of AI-based language assessments to predict PTSD symptom trajectories among responders. METHODS: Participants were 124 responders whose health was monitored at the Stony Brook WTC Health and Wellness Program who completed oral history interviews about their initial WTC experiences. PTSD symptom severity was measured longitudinally using the PTSD Checklist (PCL) for up to 7 years post-interview. AI-based indicators were computed for depression, anxiety, neuroticism, and extraversion along with dictionary-based measures of linguistic and interpersonal style. Linear regression and multilevel models estimated associations of AI indicators with concurrent and subsequent PTSD symptom severity (significance adjusted by false discovery rate). RESULTS: Cross-sectionally, greater depressive language (β = 0.32; p = 0.049) and first-person singular usage (β = 0.31; p = 0.049) were associated with increased symptom severity. Longitudinally, anxious language predicted future worsening in PCL scores (β = 0.30; p = 0.049), whereas first-person plural usage (β = -0.36; p = 0.014) and longer words usage (β = -0.35; p = 0.014) predicted improvement. CONCLUSIONS: This is the first study to demonstrate the value of AI in understanding PTSD in a vulnerable population. Future studies should extend this application to other trauma exposures and to other demographic groups, especially under-represented minorities.
Entities:
Keywords:
9/11; World Trade Center; depression; disaster responders; language-based assessments; oral history interviews; posttraumatic stress disorder; risk factors; trajectories
Authors: Angela L Carey; Melanie S Brucks; Albrecht C P Küfner; Nicholas S Holtzman; Fenne Große Deters; Mitja D Back; M Brent Donnellan; James W Pennebaker; Matthias R Mehl Journal: J Pers Soc Psychol Date: 2015-03-30
Authors: Catrin E Lewis; Daniel Farewell; Vicky Groves; Neil J Kitchiner; Neil P Roberts; Tracey Vick; Jonathan I Bisson Journal: Depress Anxiety Date: 2017-05-29 Impact factor: 6.505
Authors: H Andrew Schwartz; Johannes C Eichstaedt; Margaret L Kern; Lukasz Dziurzynski; Stephanie M Ramones; Megha Agrawal; Achal Shah; Michal Kosinski; David Stillwell; Martin E P Seligman; Lyle H Ungar Journal: PLoS One Date: 2013-09-25 Impact factor: 3.240
Authors: Joshua R Oltmanns; H Andrew Schwartz; Camilo Ruggero; Youngseo Son; Jiaju Miao; Monika Waszczuk; Sean A P Clouston; Evelyn J Bromet; Benjamin J Luft; Roman Kotov Journal: J Psychiatr Res Date: 2021-09-06 Impact factor: 4.791
Authors: Giancarlo Pasquini; Giselle Ferguson; Isabella Bouklas; Huy Vu; Mohammadzaman Zamani; Ruixue Zhaoyang; Karra D Harrington; Nelson A Roque; Jacqueline Mogle; H Andrew Schwartz; Stacey B Scott Journal: PLoS One Date: 2022-02-23 Impact factor: 3.752
Authors: Jeff Sawalha; Muhammad Yousefnezhad; Zehra Shah; Matthew R G Brown; Andrew J Greenshaw; Russell Greiner Journal: Front Psychiatry Date: 2022-02-01 Impact factor: 4.157