Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia
ObjectiveTo establish a predictive model of aggressive behaviors from hospitalized patients with schizophrenia through applying multiple machine learning algorithms, to provide a reference for accurately predicting and preventing of the occurrence of aggressive behaviors.MethodsThe cluster sampling...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-03-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1016586/full |
| _version_ | 1797867219496992768 |
|---|---|
| author | Nuo Cheng Meihao Guo Fang Yan Zhengjun Guo Jun Meng Kui Ning Yanping Zhang Zitian Duan Yong Han Changhong Wang |
| author_facet | Nuo Cheng Meihao Guo Fang Yan Zhengjun Guo Jun Meng Kui Ning Yanping Zhang Zitian Duan Yong Han Changhong Wang |
| author_sort | Nuo Cheng |
| collection | DOAJ |
| description | ObjectiveTo establish a predictive model of aggressive behaviors from hospitalized patients with schizophrenia through applying multiple machine learning algorithms, to provide a reference for accurately predicting and preventing of the occurrence of aggressive behaviors.MethodsThe cluster sampling method was used to select patients with schizophrenia who were hospitalized in our hospital from July 2019 to August 2021 as the survey objects, and they were divided into an aggressive behavior group (611 cases) and a non-aggressive behavior group (1,426 cases) according to whether they experienced obvious aggressive behaviors during hospitalization. Self-administered General Condition Questionnaire, Insight and Treatment Attitude Questionnaire (ITAQ), Family APGAR (Adaptation, Partnership, Growth, Affection, Resolve) Questionnaire (APGAR), Social Support Rating Scale Questionnaire (SSRS) and Family Burden Scale of Disease Questionnaire (FBS) were used for the survey. The Multi-layer Perceptron, Lasso, Support Vector Machine and Random Forest algorithms were used to build a predictive model for the occurrence of aggressive behaviors from hospitalized patients with schizophrenia and to evaluate its predictive effect. Nomogram was used to build a clinical application tool.ResultsThe area under the receiver operating characteristic curve (AUC) values of the Multi-Layer Perceptron, Lasso, Support Vector Machine, and Random Forest were 0.904 (95% CI: 0.877–0.926), 0.901 (95% CI: 0.874–0.923), 0.902 (95% CI: 0.876–0.924), and 0.955 (95% CI: 0.935–0.970), where the AUCs of the Random Forest and the remaining three models were statistically different (p < 0.0001), and the remaining three models were not statistically different in pair comparisons (p > 0.5).ConclusionMachine learning models can fairly predict aggressive behaviors in hospitalized patients with schizophrenia, among which Random Forest has the best predictive effect and has some value in clinical application. |
| first_indexed | 2024-04-09T23:37:54Z |
| format | Article |
| id | doaj.art-fd74aedc801440119306f74fd879b3c0 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-04-09T23:37:54Z |
| publishDate | 2023-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-fd74aedc801440119306f74fd879b3c02023-03-20T05:37:29ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402023-03-011410.3389/fpsyt.2023.10165861016586Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophreniaNuo Cheng0Meihao Guo1Fang Yan2Zhengjun Guo3Jun Meng4Kui Ning5Yanping Zhang6Zitian Duan7Yong Han8Changhong Wang9Department of Clinical Medicine, Zhengzhou University, Zhengzhou, Henan, ChinaDepartment of Infection Prevention and Control, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaDepartment of Infection Prevention and Control, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaHenan Mental Disease Prevention and Control Center, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaEditorial Department of Journal of Clinical Psychosomatic Diseases, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaDepartment of Medical Administration, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaDepartment of Medicine, Zhengzhou University, Zhengzhou, Henan, ChinaThe Seventh Psychiatric Department, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaHenan Key Laboratory of Biological Psychiatry, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaDepartment of Clinical Psychiatry, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, ChinaObjectiveTo establish a predictive model of aggressive behaviors from hospitalized patients with schizophrenia through applying multiple machine learning algorithms, to provide a reference for accurately predicting and preventing of the occurrence of aggressive behaviors.MethodsThe cluster sampling method was used to select patients with schizophrenia who were hospitalized in our hospital from July 2019 to August 2021 as the survey objects, and they were divided into an aggressive behavior group (611 cases) and a non-aggressive behavior group (1,426 cases) according to whether they experienced obvious aggressive behaviors during hospitalization. Self-administered General Condition Questionnaire, Insight and Treatment Attitude Questionnaire (ITAQ), Family APGAR (Adaptation, Partnership, Growth, Affection, Resolve) Questionnaire (APGAR), Social Support Rating Scale Questionnaire (SSRS) and Family Burden Scale of Disease Questionnaire (FBS) were used for the survey. The Multi-layer Perceptron, Lasso, Support Vector Machine and Random Forest algorithms were used to build a predictive model for the occurrence of aggressive behaviors from hospitalized patients with schizophrenia and to evaluate its predictive effect. Nomogram was used to build a clinical application tool.ResultsThe area under the receiver operating characteristic curve (AUC) values of the Multi-Layer Perceptron, Lasso, Support Vector Machine, and Random Forest were 0.904 (95% CI: 0.877–0.926), 0.901 (95% CI: 0.874–0.923), 0.902 (95% CI: 0.876–0.924), and 0.955 (95% CI: 0.935–0.970), where the AUCs of the Random Forest and the remaining three models were statistically different (p < 0.0001), and the remaining three models were not statistically different in pair comparisons (p > 0.5).ConclusionMachine learning models can fairly predict aggressive behaviors in hospitalized patients with schizophrenia, among which Random Forest has the best predictive effect and has some value in clinical application.https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1016586/fullschizophreniapredictive modelsmachine learningaggressive behaviorsrisk factors |
| spellingShingle | Nuo Cheng Meihao Guo Fang Yan Zhengjun Guo Jun Meng Kui Ning Yanping Zhang Zitian Duan Yong Han Changhong Wang Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia Frontiers in Psychiatry schizophrenia predictive models machine learning aggressive behaviors risk factors |
| title | Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia |
| title_full | Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia |
| title_fullStr | Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia |
| title_full_unstemmed | Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia |
| title_short | Application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia |
| title_sort | application of machine learning in predicting aggressive behaviors from hospitalized patients with schizophrenia |
| topic | schizophrenia predictive models machine learning aggressive behaviors risk factors |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1016586/full |
| work_keys_str_mv | AT nuocheng applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT meihaoguo applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT fangyan applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT zhengjunguo applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT junmeng applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT kuining applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT yanpingzhang applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT zitianduan applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT yonghan applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia AT changhongwang applicationofmachinelearninginpredictingaggressivebehaviorsfromhospitalizedpatientswithschizophrenia |