Isolating the exposomic impact of acute war and displacement within chronic crisis using multimodal, AI-enabled phenotyping

Wars often unfold within contexts of prolonged instability, yet little is known about how acute conflicts interact with cumulative exposomic adversity to shape mental health processes. Here we studied clinical and subclinical symptoms in a Lebanese sample across three groups—one assessed before the 2024 war and two assessed after, with or without displacement—within a shared background of chronic crises. Using a multimodal, AI-enabled approach combining clinical assessments, narrative coding, and large-scale linguistic and emotional profiling of life stories, we show that mental health burden does not scale linearly with acute war or displacement.

Despite higher cumulative exposure, war-time groups did not exhibit higher PTSD or depression than pre-war participants, and resilience was lowest among non-displaced individuals. In contrast, narrative organization showed non-linear reconfiguration: displacement was associated with enhanced temporal structuring but reduced global causal coherence, whereas acute war exposure without displacement amplified autobiographical reasoning and explicit self-change. AI-based analyses further revealed emotional blunting rather than emotional overload, alongside increased linguistic complexity decoupled from symptom severity.

By enabling scalable analysis of life narratives, this approach isolates acute vs chronic effects and reveals sub-clinical adaptations not captured by symptom measures alone, that can inform healthcare and policy in conflict-affected regions. Correspondence and material requests should be addressed to corresponding author Pr Laura-Joy Boulos [email protected]. We deeply thank all the students and collaborators who contributed to the data collection and analysis for this study.

ENSA lab, Department of Psychology, Saint-Joseph University-Hôtel-Dieu de France Hospital, Beirut, Lebanon M. Boulos ItaliaNLP Lab, Institute of Computational Linguistics (CNR-ILC), Pisa, Italy Univ. Lille, CNRS, UMR 9193 - SCALab - Sciences Cognitives et Sciences Affectives, 59000, Lille, France No potential conflict of interest was reported by the authors.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material.

If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Fares, M., Al Kai, N., Zahran, F. et al.