{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T17:00:40Z","timestamp":1778864440276,"version":"3.51.4"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychiatry"],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>To develop and validate a hierarchical machine learning model integrating static clinical features and dynamic behavioral assessments for accurately predicting violent behaviors among hospitalized schizophrenia patients.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This retrospective study included 346 schizophrenia patients hospitalized from July 2021 to July 2024 in Liaoning Province. Patients were categorized into violent (<jats:italic>n<\/jats:italic> = 123) and non-violent (<jats:italic>n<\/jats:italic> = 223) groups based on documented aggressive incidents. Eighteen static clinical variables (e.g., age, gender, history of violence, manic symptoms) were extracted from electronic medical records, and 39 dynamic behavioral indicators (e.g., anger expression, insomnia, auditory hallucinations) were assessed weekly using the Psychiatric Patient Nursing Observation Scale. Predictive models were separately developed using six machine learning algorithms: Regularized Logistic Regression (LR), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Multi-layer Perceptron (MLP), and K-Nearest Neighbor (KNN). Regularized logistic regression was selected as the final algorithm due to its superior predictive performance, indicated by the highest Area Under the Curve (AUC), in both static baseline and dynamic behavioral models. A hierarchical predictive model was then established using regularized logistic regression separately for static baseline risk and dynamic risk fluctuations, subsequently integrated using a weighted fusion approach.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The integrated hierarchical regularized logistic regression model achieved an optimal performance with an area under the curve (AUC) of 0.8741, surpassing both the static baseline model (AUC = 0.7953) and dynamic model (AUC = 0.8003) alone. Optimal predictive performance was obtained with a fusion parameter (<jats:italic>\u03b1<\/jats:italic>) of 0.37, balancing sensitivity (0.7838), specificity (0.8358), and accuracy (0.8173). Key independent predictors included static factors such as history of violence (odds ratio [OR]=4.638), manic symptoms (OR = 7.801), younger age (OR = 0.966), high-risk command hallucinations (OR = 2.602), and dynamic features like anger expression (OR = 4.649), insomnia (OR = 7.422), and auditory hallucinations (OR = 2.092).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The hierarchical machine learning model integrating clinical history and dynamic nursing observations significantly enhances predictive accuracy for violent behavior in schizophrenia inpatients, providing clinicians with valuable tools for timely risk assessment and personalized preventive interventions.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fpsyt.2025.1644341","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T05:29:41Z","timestamp":1758518981000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Hierarchical machine learning model integrating clinical history and nursing observations for predicting violent behavior in hospitalized schizophrenia patients"],"prefix":"10.3389","volume":"16","author":[{"given":"Xianfeng","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingtao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longlong","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunyuan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jintao","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e55942","DOI":"10.1371\/journal.pone.0055942","article-title":"Risk factors for violence in psychosis: Systematic review and meta-regression analysis of 110 studies","volume":"8","author":"Witt","year":"2013","journal-title":"PloS One"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1111\/acps.12053","article-title":"A review and meta-analysis of the patient factors associated with psychiatric in-patient aggression","volume":"127","author":"Dack","year":"2013","journal-title":"Acta Psychiatr Scand"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1111\/appy.12209","article-title":"Prevalence of aggression in hospitalized patients with schizophrenia in China: A meta-analysis","volume":"8","author":"Zhou","year":"2016","journal-title":"Asia-Pac Psychiatry"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e0128536","DOI":"10.1371\/journal.pone.0128536","article-title":"Prevalence and risk factors of violence by psychiatric acute inpatients: a systematic review and meta-analysis","volume":"10","author":"Iozzino","year":"2015","journal-title":"PloS One"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1111\/inm.12191","article-title":"Aggression on inpatient units: Clinical characteristics and consequences","volume":"25","author":"Renwick","year":"2016","journal-title":"Int J Ment Health Nurs"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1111\/inm.12905","article-title":"Prevalence and severity of verbal, physical, and sexual inpatient violence against nurses in swiss psychiatric hospitals and associated nurse-related characteristics: Cross-sectional multicentre study","volume":"30","author":"Schlup","year":"2021","journal-title":"Int J Ment Health Nurs"},{"key":"B7","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.schres.2007.03.027","article-title":"Clinical correlates of later violence and criminal offences in schizophrenia","volume":"94","author":"Soyka","year":"2007","journal-title":"Schizophr Res"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2024.1384828","article-title":"Machine learning for prediction of violent behaviors in schizophrenia spectrum disorders: a systematic review","volume":"15","author":"Parsaei","year":"2024","journal-title":"Front Psychiatry"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.63.5.490","article-title":"A national study of violent behavior in persons with schizophrenia","volume":"63","author":"Swanson","year":"2006","journal-title":"Arch Gen Psychiatry"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/S2215-0366(20)30262-5","article-title":"Violence and mental disorders: a structured review of associations by individual diagnoses, risk factors, and risk assessment","volume":"8","author":"Whiting","year":"2021","journal-title":"Lancet Psychiatry"},{"key":"B11","volume-title":"HCR-20 V3: Assessing Risk for Violence \u2013 User Guide","author":"Douglas","year":"2013"},{"key":"B12","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1146\/annurev-clinpsy-032816-045037","article-title":"Machine learning approaches for clinical psychology and psychiatry","volume":"14","author":"Dwyer","year":"2018","journal-title":"Annu Rev Clin Psychol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"114294","DOI":"10.1016\/j.psychres.2021.114294","article-title":"Identification of violent patients with schizophrenia using a hybrid machine learning approach at the individual level","volume":"306","author":"Gou","year":"2021","journal-title":"Psychiatry Res"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2023.1016586","article-title":"Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia","volume":"14","author":"Cheng","year":"2023","journal-title":"Front Psychiatry"},{"key":"B15","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1080\/15228932.2016.1128301","article-title":"Web-based violence risk monitoring tool in psychoses: Pilot study in community forensic patients","volume":"16","author":"Gulati","year":"2016","journal-title":"J Forensic Psychol Pract"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291721002063","article-title":"Modifiable risk factors for inpatient violence in psychiatric hospital: Prospective study and prediction model","volume":"53","author":"Fazel","year":"2023","journal-title":"psychol Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e0258346","DOI":"10.1371\/journal.pone.0258346","article-title":"Aggression on the psychiatric ward: Prevalence and risk factors. a systematic review of the literature","volume":"16","author":"Weltens","year":"2021","journal-title":"PloS One"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2023.1106950","article-title":"Characteristics and associated factors of violence in male patients with schizophrenia in China","volume":"14","author":"Guo","year":"2023","journal-title":"Front Psychiatry"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e1000120","DOI":"10.1371\/journal.pmed.1000120","article-title":"Schizophrenia and violence: Systematic review and meta-analysis","volume":"6","author":"Fazel","year":"2009","journal-title":"PloS Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1176\/appi.ps.51.10.1288","article-title":"The relationship between command hallucinations and violence","volume":"51","author":"McNiel","year":"2000","journal-title":"Psychiatr Serv"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.2466\/pr0.1966.19.1.180","article-title":"Nosie-30: A treatment-sensitive ward behaviour scale","volume":"19","author":"Honigfeld","year":"1966","journal-title":"psychol Rep"},{"key":"B22","doi-asserted-by":"publisher","first-page":"281","DOI":"10.4103\/jehp.jehp_156_20","article-title":"Validation of the 30-item nurses\u2019 observation scale for inpatient evaluation and mental health-care promotion","volume":"9","author":"Sirati Nir","year":"2020","journal-title":"J Educ Health Promotion"},{"key":"B23","unstructured":"Logistic regression: scikit-learn documentation\n          \n          \n          \n          2023"},{"key":"B24","unstructured":"L1 penalty and sparsity in logistic regression\n          \n          \n          \n          2025"},{"key":"B25","unstructured":"Tuning the hyper-parameters of an estimator: scikit-learn documentation\n          \n          \n          \n          2023"},{"key":"B26","unstructured":"Multi-layer perceptron: scikit-learn documentation\n          \n          \n          \n          2023"},{"key":"B27","unstructured":"Random forest (orange widget catalog)\n          \n          \n          \n          2025"},{"key":"B28","unstructured":"Nearest neighbors: scikit-learn documentation\n          \n          \n          \n          2023"},{"key":"B29","unstructured":"Support vector machines: scikit-learn documentation\n          \n          \n          \n          2023"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXgboost: A scalable tree boosting system\u201c","author":"Chen","year":"2016"},{"key":"B31","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1192\/pb.bp.113.043315","article-title":"Violence risk assessment as a medical intervention: ethical tensions","volume":"38","author":"Roychowdhury","year":"2014","journal-title":"Psychiatr Bull"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/S2215-0366(23)00256-0","article-title":"Violence risk assessment instruments in forensic psychiatric populations: a systematic review and meta-analysis","volume":"10","author":"Ogonah","year":"2023","journal-title":"Lancet Psychiatry"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e4692","article-title":"Use of risk assessment instruments to predict violence and antisocial behaviour in 73 samples involving 24827 people: systematic review and meta-analysis","volume":"345","author":"Fazel","year":"2012","journal-title":"BMJ"},{"key":"B34","doi-asserted-by":"publisher","first-page":"e100921","DOI":"10.1136\/gpsych-2022-100921","article-title":"Calibrating violence risk assessments for uncertainty","volume":"36","author":"Connors","year":"2023","journal-title":"Gen Psychiatry"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2021.3721","article-title":"Association of schizophrenia spectrum disorders and violence perpetration in adults and adolescents from 15 countries: a systematic review and meta-analysis","volume":"79","author":"Whiting","year":"2022","journal-title":"JAMA Psychiatry"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2022.799899","article-title":"The prediction and influential factors of violence in male schizophrenia patients with machine learning algorithms","volume":"13","author":"Yu","year":"2022","journal-title":"Front Psychiatry"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1093\/schbul\/sbr041","article-title":"Pathways to aggression in schizophrenia affect results of treatment","volume":"37","author":"Volavka","year":"2011","journal-title":"Schizophr Bull"},{"key":"B38","doi-asserted-by":"publisher","first-page":"7571939","DOI":"10.1155\/2020\/7571939","article-title":"Prevalence and associated factors of aggressive behavior among patients with schizophrenia at ayder comprehensive specialized hospital, Ethiopia","volume":"2020","author":"Araya","year":"2020","journal-title":"BioMed Res Int"},{"key":"B39","doi-asserted-by":"publisher","first-page":"102645","DOI":"10.1016\/j.ajp.2021.102645","article-title":"Candidate symptomatic markers for predicting violence in schizophrenia: a cross-sectional study of 7711 patients in a chinese population","volume":"59","author":"Sun","year":"2021","journal-title":"Asian J Psychiatry"},{"key":"B40","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1093\/oxfordjournals.schbul.a033396","article-title":"Violence in inpatients with schizophrenia: a prospective study","volume":"25","author":"Arango","year":"1999","journal-title":"Schizophr Bull"},{"key":"B41","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ijnurstu.2004.08.005","article-title":"Forecasting violent behaviors for schizophrenic outpatients using their disease insights: development of a binary logistic regression model and a support vector model","volume":"33","author":"Tzeng","year":"2004","journal-title":"Int J Ment Health"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2023.08.034","article-title":"Classification of suicidality by training supervised machine learning models with brain mri findings: A systematic review","volume":"340","author":"Parsaei","year":"2023","journal-title":"J Affect Disord"},{"key":"B43","doi-asserted-by":"publisher","first-page":"112960","DOI":"10.1016\/j.psychres.2020.112960","article-title":"Prediction of physical violence in schizophrenia with machine learning algorithms","volume":"289","author":"Wang","year":"2020","journal-title":"Psychiatry Res"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1503\/cmaj.202434","article-title":"Implementing machine learning in medicine","volume":"193","author":"Verma","year":"2021","journal-title":"Cmaj"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291716001367","article-title":"Machine learning, statistical learning and the future of biological research in psychiatry","volume":"46","author":"Iniesta","year":"2016","journal-title":"psychol Med"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1470","DOI":"10.3390\/jpm12091470","article-title":"Effectiveness of artificial intelligence methods in personalized aggression risk prediction within inpatient psychiatric treatment settings\u2014a systematic review","volume":"12","author":"Tay","year":"2022","journal-title":"J Pers Med"},{"key":"B47","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s44333-024-00022-4","article-title":"Causation versus prediction in travel mode choice modeling","volume":"2","author":"Chauhan","year":"2025","journal-title":"NPJ Sustain Mobil Transport"},{"key":"B48","doi-asserted-by":"publisher","first-page":"eabk1942","DOI":"10.1126\/sciadv.abk1942","article-title":"Mapping of machine learning approaches for description, prediction, and causal inference in the social and health sciences","volume":"8","author":"Leist","year":"2022","journal-title":"Sci Adv"},{"key":"B49","doi-asserted-by":"publisher","first-page":"e1001744","DOI":"10.1371\/journal.pmed.1001744","article-title":"Critical appraisal and data extraction for systematic reviews of prediction modelling studies: the charms checklist","volume":"11","author":"Moons","year":"2014","journal-title":"PloS Med"},{"key":"B50","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1186\/s12888-022-04331-1","article-title":"Prediction of violence in male schizophrenia using smri, based on machine learning algorithms","volume":"22","author":"Yu","year":"2022","journal-title":"BMC Psychiatry"},{"key":"B51","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1038\/s41537-023-00332-5","article-title":"Relapse prediction in schizophrenia with smartphone digital phenotyping during covid-19: a prospective, three site, two-country, longitudinal study","volume":"9","author":"Cohen","year":"2023","journal-title":"Schizophrenia"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2025.1644341\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T05:29:43Z","timestamp":1758518983000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2025.1644341\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":51,"alternative-id":["10.3389\/fpsyt.2025.1644341"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2025.1644341","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"article-number":"1644341"}}