World Trade Center responders in their own words: predicting PTSD symptom trajectories with AI-based language analyses of interviews
Authors:
Open Access
- 22 June 2021
- journal article
- research article
- Published by Cambridge University Press (CUP) in Psychological Medicine
- Vol. 53 (3) , 918-926
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.Keywords
All Related Versions
This publication has 54 references indexed in Scilit:
- Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary ApproachPLOS ONE, 2013
- Exposure, probable PTSD and lower respiratory illness among World Trade Center rescue, recovery and clean-up workersPsychological Medicine, 2011
- Rumination in PTSD as well as in Traumatized and Non-Traumatized Depressed Patients: A Cross-Sectional Clinical StudyBehavioural and Cognitive Psychotherapy, 2011
- Long‐term course of probable PTSD after the 9/11 attacks: A study in urban primary careJournal of Traumatic Stress, 2010
- Telling losses: Personality correlates and functions of bereavement narrativesJournal of Research in Personality, 2008
- Pronouns in Marital InteractionPsychological Science, 2005
- Rumination and overgeneral memory in depression: Effects of self-focus and analytic thinking.Journal of Abnormal Psychology, 2001
- Predicting anxiety and depression from personality: Is there a synergistic effect of neuroticism and extraversion?Journal of Abnormal Psychology, 2000
- Posttraumatic stress disorder after treatment for breast cancer: Prevalence of diagnosis and use of the PTSD Checklist--Civilian Version (PCL--C) as a screening instrument.Journal of Consulting and Clinical Psychology, 1998
- Psychometric properties of the PTSD checklist (PCL)Behaviour Research and Therapy, 1996