{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T04:35:58Z","timestamp":1791434158747,"version":"4.3.3"},"reference-count":68,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00457381, RS-2024-00440371"],"award-info":[{"award-number":["RS-2024-00457381, RS-2024-00440371"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Firefighters constitute a high-risk occupational cohort for alcohol use disorder (AUD) due to chronic trauma exposure, yet traditional screening methodologies relying on self-report instruments remain compromised by systematic underreporting attributable to occupational stigma and career preservation concerns. This cross-sectional investigation developed and validated a multimodal deep learning framework integrating T1-weighted structural magnetic resonance imaging with standardized neuropsychological assessments to enable objective AUD risk stratification without necessitating computationally intensive functional neuroimaging protocols.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Analysis of 689 active-duty firefighters (mean age 43.3\u00b18.8 years; 93% male) from a nationwide occupational cohort incorporated high-resolution three-dimensional T1-weighted structural MRI acquisition alongside comprehensive neuropsychological evaluation utilizing the Grooved Pegboard Test for visual-motor coordination assessment and Trail Making Test for executive function quantification. The novel computational architecture synergistically combined ResNet-50 convolutional neural networks for hierarchical morphological feature extraction, Vision Transformer modules for global neuroanatomical pattern recognition, and multilayer perceptron integration of clinical variables, with model interpretability assessed through Gradient-weighted Class Activation Mapping and SHapley Additive exPlanations methodologies. Performance evaluation employed stratified three-fold cross-validation with DeLong's test for statistical comparison of receiver operating characteristic curves.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The multimodal framework achieved 79.88% classification accuracy with area under the receiver operating characteristic curve of 79.65%, representing statistically significant performance enhancement relative to clinical-only (62.53%; p&amp;lt;0.001) and neuroimaging-only (61.53%; p&amp;lt;0.001) models, demonstrating a 17.35 percentage-point improvement attributable to synergistic cross-modal integration rather than simple feature concatenation. Interpretability analyses revealed stochastic activation patterns in unimodal neuroimaging models lacking neuroanatomically coherent feature localization, while clinical feature importance hierarchically prioritized biological sex and motor coordination metrics as primary predictive indicators. The framework maintained robust calibration across probability thresholds, supporting operational feasibility for clinical deployment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This investigation establishes that structural neuroimaging combined with targeted neuropsychological assessment achieves classification performance comparable to complex multimodal protocols while substantially reducing acquisition time and computational requirements, offering a pragmatic pathway for implementing objective AUD screening in high-risk occupational populations with broader implications for psychiatric risk stratification in trauma-exposed professions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2025.1643552","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T08:17:36Z","timestamp":1762157856000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Predicting alcohol use disorder risk in firefighters using a multimodal deep learning model: a cross-sectional study"],"prefix":"10.3389","volume":"16","author":[{"given":"MyeongGyun","family":"Jang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"DongOk","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujung","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hwamin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2395113","DOI":"10.1080\/20008066.2024.2395113","article-title":"\u2018I\u2019ve got no PPE to protect my mind\u2019: understanding the needs and experiences of first responders exposed to trauma in the workplace","volume":"15","author":"Cogan","year":"2024","journal-title":"Eur J Psychotraumatol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.shaw.2022.08.008","article-title":"Norms about alcohol use among US firefighters","volume":"13","author":"Haddock","year":"2022","journal-title":"Saf Health At Work"},{"key":"B3","doi-asserted-by":"publisher","first-page":"680","DOI":"10.3390\/microorganisms13030680","article-title":"Gut microbiome alterations, mental health, and alcohol consumption: investigating the gut\u2013brain axis in firefighters","volume":"13","author":"Yoo","year":"2025","journal-title":"Microorganisms"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1080\/10826084.2024.2422975","article-title":"Alcohol misuse and correlates with mental health indicators among firefighters","volume":"60","author":"Rotunda","year":"2025","journal-title":"Subst Use Misuse"},{"key":"B5","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1177\/0706743717723825","article-title":"Mental disorder symptoms among public safety personnel in Canada","volume":"63","author":"Carleton","year":"2018","journal-title":"Can J Psychiatry"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpr.2011.07.009","article-title":"Toward a definition of intolerance of uncertainty: A review of factor analytical studies of the Intolerance of Uncertainty Scale","volume":"31","author":"Birrell","year":"2011","journal-title":"Clin Psychol Rev"},{"key":"B7","doi-asserted-by":"publisher","first-page":"383","DOI":"10.3390\/ijerph22030383","article-title":"The relationship between intolerance of uncertainty and alcohol use in first responders: A cross-sectional study of the direct, mediating and moderating role of generalized resistance resources","volume":"22","author":"Pretorius","year":"2025","journal-title":"Int J Environ Res Public Health"},{"key":"B8","doi-asserted-by":"publisher","first-page":"100480","DOI":"10.1016\/j.abrep.2023.100480","article-title":"Negative urgency, PTSD symptoms, and alcohol risk in college students","volume":"17","author":"Hallihan","year":"2023","journal-title":"Addictive Behav Rep"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-023-02074-3","article-title":"Self-management with alcohol over lifespan: psychological mechanisms, neurobiological underpinnings, and risk assessment","volume":"28","author":"M\u00fcller","year":"2023","journal-title":"Mol Psychiatry"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1038\/s44220-024-00334-x","article-title":"Neuroimaging biomarkers of addiction","volume":"2","author":"Ekhtiari","year":"2024","journal-title":"Nat Ment Health"},{"key":"B11","article-title":"Posttraumatic stress and alcohol use among first responders","volume-title":"Mental health intervention and treatment of first responders and emergency workers","author":"Smith","year":"2020"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1136\/oemed-2022-108608","article-title":"Workplace mental health screening: a systematic review and meta-analysis","volume":"80","author":"Strudwick","year":"2023","journal-title":"Occup Environ Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"440","DOI":"10.3390\/healthcare12040440","article-title":"Firefighter health: A narrative review of occupational threats and countermeasures","volume":"12","author":"Gonzalez","year":"2024","journal-title":"Healthcare"},{"key":"B14","doi-asserted-by":"publisher","first-page":"22276057","DOI":"10.1101\/2022.06.06.22276057","article-title":"Machine learning applications and advancements in alcohol use disorder: A systematic review","author":"Hurtado","year":"2022","journal-title":"medRxiv"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-019-0534-x","article-title":"Predicting risk for Alcohol Use Disorder using longitudinal data with multimodal biomarkers and family history: a machine learning study","volume":"26","author":"Kinreich","year":"2021","journal-title":"Mol Psychiatry"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2022.912600","article-title":"Deep learning in neuroimaging: overcoming challenges with emerging approaches","volume":"13","author":"Smucny","year":"2022","journal-title":"Front Psychiatry"},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-79948-3_684","article-title":"Edinburgh handedness inventory","volume-title":"Encyclopedia of clinical neuropsychology","author":"Caplan","year":"2011"},{"key":"B18","doi-asserted-by":"publisher","first-page":"102695","DOI":"10.1016\/j.jelekin.2022.102695","article-title":"Finger dexterity measured by the Grooved Pegboard test indexes Parkinson\u2019s motor severity in a tremor-independent manner","volume":"66","author":"Buard","year":"2022","journal-title":"J Electromyography Kinesiol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.2466\/pms.1958.8.3.271","article-title":"Validity of the Trail Making Test as an indicator of organic brain damage","volume":"8","author":"Reitan","year":"1958","journal-title":"Perceptual Motor Skills"},{"key":"B20","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.neuropsychologia.2018.03.031","article-title":"Neural signatures of Trail Making Test performance: Evidence from lesion-mapping and neuroimaging studies","volume":"115","author":"Varjacic","year":"2018","journal-title":"Neuropsychologia"},{"key":"B21","article-title":"The alcohol use disorders identification test","author":"Babor","year":"2001"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1111\/acer.12593","article-title":"The use of alcohol use disorders identification test (AUDIT) in detecting alcohol use disorder and risk drinking in the general population: validation of AUDIT using schedules for clinical assessment in neuropsychiatry","volume":"39","author":"Lundin","year":"2015","journal-title":"Alcohol: Clin Exp Res"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.09.015","article-title":"Fsl","volume":"62","author":"Jenkinson","year":"2012","journal-title":"Neuroimage"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24750","article-title":"Automated brain extraction of multisequence MRI using artificial neural networks","volume":"40","author":"Isensee","year":"2019","journal-title":"Hum Brain Mapp"},{"key":"B25","first-page":"362","article-title":"Magnetic resonance imaging of the living brain: evidence for brain degeneration among alcoholics and recovery with abstinence","volume":"31","author":"Rosenbloom","year":"2008","journal-title":"Alcohol Res Health"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-19-3254-0","volume-title":"Cross-sectional Atlas of Rhesus Monkey Head: with 0.024-mm pixel size color images","author":"Park","year":"2022"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-021-00478-7","article-title":"A comprehensive study of data augmentation strategies for prostate cancer detection in diffusion-weighted MRI using convolutional neural networks","volume":"34","author":"Hao","year":"2021","journal-title":"J Digital Imaging"},{"key":"B28","article-title":"Augmenting medical imaging: a comprehensive catalogue of 65 techniques for enhanced data analysis","author":"Cossio","year":"2023"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-42750-4_6","article-title":"Data augmentation in training deep learning models for medical image analysis","volume-title":"Deep learners and deep learner descriptors for medical applications","author":"Abdollahi","year":"2020"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4842-6168-2_6","article-title":"ResNet 50","volume-title":"Convolutional neural networks with swift for tensorflow: image recognition and dataset categorization","author":"Koonce","year":"2021"},{"key":"B31","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"nature"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2101","DOI":"10.1038\/s41467-025-57181-2","article-title":"Pretrained transformers applied to clinical studies improve predictions of treatment efficacy and associated biomarkers","volume":"16","author":"Arango-Argoty","year":"2025","journal-title":"Nat Commun"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B35","article-title":"Axiomatic attribution for deep networks","author":"Sundararajan","year":"2017"},{"key":"B36","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"Xgboost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B37","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B39","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N16-3020","article-title":"Why should i trust you?\u201d Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"B40","article-title":"Sanity checks for saliency maps","volume":"31","author":"Adebayo","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"B41","doi-asserted-by":"publisher","first-page":"056037","DOI":"10.1088\/1741-2552\/ad038c","article-title":"An attention-based multi-modal MRI fusion model for major depressive disorder diagnosis","volume":"20","author":"Zheng","year":"2023","journal-title":"J Neural Eng"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2024.1384842","article-title":"Multi-modal deep learning from imaging genomic data for schizophrenia classification","volume":"15","author":"Kanyal","year":"2024","journal-title":"Front Psychiatry"},{"key":"B43","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neulet.2018.04.007","article-title":"Random forest based classification of alcohol dependence patients and healthy controls using resting state MRI","volume":"676","author":"Zhu","year":"2018","journal-title":"Neurosci Lett"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.867067","article-title":"Identifying alcohol use disorder with resting state functional Magnetic Resonance Imaging data: a comparison among machine learning classifiers","volume":"13","author":"Vergara","year":"2022","journal-title":"Front Psychol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3390\/brainsci10020115","article-title":"Random forest classification of alcohol use disorder using fMRI functional connectivity, neuropsychological functioning, and impulsivity measures","volume":"10","author":"Kamarajan","year":"2020","journal-title":"Brain Sci"},{"key":"B46","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1038\/s41598-019-56923-9","article-title":"A multimodal neuroimaging classifier for alcohol dependence","volume":"10","author":"Guggenmos","year":"2020","journal-title":"Sci Rep"},{"key":"B47","doi-asserted-by":"publisher","first-page":"101782","DOI":"10.1016\/j.nicl.2019.101782","article-title":"Resting state connectivity best predicts alcohol use severity in moderate to heavy alcohol users","volume":"22","author":"Fede","year":"2019","journal-title":"Neuroimage: Clin"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2024.1504190","article-title":"Machine learning prediction of anxiety symptoms in social anxiety disorder: utilizing multimodal data from virtual reality sessions","volume":"15","author":"Park","year":"2025","journal-title":"Front Psychiatry"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/00207411.2025.2486084","article-title":"Machine learning models to predict posttraumatic stress injuries in a sample of firefighters: A proof of concept","author":"Rapisarda","year":"2025","journal-title":"Int J Ment Health"},{"key":"B50","first-page":"1","article-title":"Mental stress detection with the multimodal data using ensemble optimization enabled explainable convolutional neural network","author":"Shinde","year":"2025","journal-title":"Biomed Mater Devices"},{"key":"B51","article-title":"Evaluating visual explanations of attention maps for transformer-based medical imaging","author":"Chung","year":"2024"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1002\/jnr.24423","article-title":"Neuroimaging in alcohol use disorder: From mouse to man","volume":"100","author":"Fritz","year":"2022","journal-title":"J Neurosci Res"},{"key":"B53","article-title":"Explainable and interpretable multimodal large language models: A comprehensive survey","author":"Dang","year":"2024"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2025.1644697","article-title":"Anomaly detection in medical via multimodal foundation models","volume":"13","author":"Wu","year":"2025","journal-title":"Front Bioengineering Biotechnol"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1007\/s00429-019-01894-w","article-title":"Relations between cognitive and motor deficits and regional brain volumes in individuals with alcoholism","volume":"224","author":"Fama","year":"2019","journal-title":"Brain Structure Funct"},{"key":"B56","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1177\/1550059418782093","article-title":"Multimodal neuroimaging: basic concepts and classification of neuropsychiatric diseases","volume":"50","author":"Tulay","year":"2019","journal-title":"Clin EEG Neurosci"},{"key":"B57","doi-asserted-by":"publisher","first-page":"bbab569","DOI":"10.1093\/bib\/bbab569","article-title":"Multimodal deep learning for biomedical data fusion: a review","volume":"23","author":"Stahlschmidt","year":"2022","journal-title":"Briefings Bioinf"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpsc.2015.12.005","article-title":"Multimodal fusion of brain imaging data: a key to finding the missing link (s) in complex mental illness","volume":"1","author":"Calhoun","year":"2016","journal-title":"Biol Psychiatry: Cogn Neurosci Neuroimaging"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.07.006","article-title":"Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation","volume":"64","author":"Zhang","year":"2020","journal-title":"Inf Fusion"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607","article-title":"Multimodal machine learning: A survey and taxonomy","volume":"41","author":"Baltru\u0161aitis","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B61","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s12938-024-01212-4","article-title":"Advantages of transformer and its application for medical image segmentation: a survey","volume":"23","author":"Pu","year":"2024","journal-title":"Biomed Eng Online"},{"key":"B62","doi-asserted-by":"publisher","first-page":"103000","DOI":"10.1016\/j.media.2023.103000","article-title":"Advances in medical image analysis with vision transformers: a comprehensive review","volume":"91","author":"Azad","year":"2024","journal-title":"Med Image Anal"},{"key":"B63","doi-asserted-by":"publisher","first-page":"e0175683","DOI":"10.1371\/journal.pone.0175683","article-title":"Evaluation of machine learning algorithms and structural features for optimal MRI-based diagnostic prediction in psychosis","volume":"12","author":"Salvador","year":"2017","journal-title":"PloS One"},{"key":"B64","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.jneumeth.2011.10.031","article-title":"A review of multivariate methods for multimodal fusion of brain imaging data","volume":"204","author":"Sui","year":"2012","journal-title":"J Neurosci Methods"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.1136\/oem.60.9.705","article-title":"Surveillance in occupational health","volume":"60","author":"Koh","year":"2003","journal-title":"Occup Environ Med"},{"key":"B66","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1038\/s41467-020-15948-9","article-title":"The UK Biobank imaging enhancement of 100,000 participants: rationale, data collection, management and future directions","volume":"11","author":"Littlejohns","year":"2020","journal-title":"Nat Commun"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2015.0584","article-title":"Epidemiology of DSM-5 alcohol use disorder: results from the National Epidemiologic Survey on Alcohol and Related Conditions III","volume":"72","author":"Grant","year":"2015","journal-title":"JAMA Psychiatry"},{"key":"B68","doi-asserted-by":"publisher","DOI":"10.1016\/j.amepre.2015.05.031","article-title":"2010 national and state costs of excessive alcohol consumption","volume":"49","author":"Sacks","year":"2015","journal-title":"Am J Prev Med"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2025.1643552\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T08:17:39Z","timestamp":1762157859000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2025.1643552\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":68,"alternative-id":["10.3389\/fpsyt.2025.1643552"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2025.1643552","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,3]]},"article-number":"1643552"}}