TY - JOUR
T1 - Unravelling psychiatric heterogeneity and predicting suicide attempts in women with trauma-related dissociation using artificial intelligence
AU - Srinivansan, Suhas
AU - Harnett, Nathaniel G.
AU - Zhang, Liang
AU - Dahlgren, M. Kathryn
AU - Jang, Junbong
AU - Lu, Senbao
AU - Nephew, Benjamin C.
AU - Palermo, Cori A.
AU - Pan, Xi
AU - Eltabakh, Mohamed Y.
AU - Frederick, Blaise B.
AU - Gruber, Staci A.
AU - Kaufman, Milissa L.
AU - King, Jean
AU - Ressler, Kerry J.
AU - Winternitz, Sherry
AU - Korkin, Dmitry
AU - Lebois, Lauren A.M.
N1 - Publisher Copyright:
© 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
PY - 2022/12/19
Y1 - 2022/12/19
N2 - Background: Suicide is a leading cause of death, and rates of attempted suicide have increased during the COVID-19 pandemic. The under-diagnosed psychiatric phenotype of dissociation is associated with elevated suicidal self-injury; however, it has largely been left out of attempts to predict and prevent suicide. Objective: We designed an artificial intelligence approach to identify dissociative patients and predict prior suicide attempts in an unbiased, data-driven manner. Method: Participants were 30 controls and 93 treatment-seeking female patients with posttraumatic stress disorder (PTSD) and various levels of dissociation, including some with the PTSD dissociative subtype and some with dissociative identity disorder (DID). Results: Unsupervised learning models identified patients along a spectrum of dissociation. Moreover, supervised learning models accurately predicted prior suicide attempts with an score up to 0.83. DID had the highest risk of prior suicide attempts, and distinct subtypes of dissociation predicted suicide attempts in PTSD and DID. Conclusions: These findings expand our understanding of the dissociative phenotype and underscore the urgent need to assess for dissociation to identify individuals at high-risk of suicidal self-injury.
AB - Background: Suicide is a leading cause of death, and rates of attempted suicide have increased during the COVID-19 pandemic. The under-diagnosed psychiatric phenotype of dissociation is associated with elevated suicidal self-injury; however, it has largely been left out of attempts to predict and prevent suicide. Objective: We designed an artificial intelligence approach to identify dissociative patients and predict prior suicide attempts in an unbiased, data-driven manner. Method: Participants were 30 controls and 93 treatment-seeking female patients with posttraumatic stress disorder (PTSD) and various levels of dissociation, including some with the PTSD dissociative subtype and some with dissociative identity disorder (DID). Results: Unsupervised learning models identified patients along a spectrum of dissociation. Moreover, supervised learning models accurately predicted prior suicide attempts with an score up to 0.83. DID had the highest risk of prior suicide attempts, and distinct subtypes of dissociation predicted suicide attempts in PTSD and DID. Conclusions: These findings expand our understanding of the dissociative phenotype and underscore the urgent need to assess for dissociation to identify individuals at high-risk of suicidal self-injury.
KW - Artificial intelligence
KW - Dissociation
KW - Dissociative identity disorder
KW - Machine learning
KW - Posttraumatic stress disorder
KW - Suicidal self-injury
KW - Suicide
UR - http://www.scopus.com/inward/record.url?scp=85142221533&partnerID=8YFLogxK
U2 - 10.1080/20008066.2022.2143693
DO - 10.1080/20008066.2022.2143693
M3 - Article
C2 - 38872600
AN - SCOPUS:85142221533
SN - 2000-8066
VL - 13
JO - European Journal of Psychotraumatology
JF - European Journal of Psychotraumatology
IS - 2
M1 - 2143693
ER -