Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophrenia

Abstract Early warning of long-term hospitalization in schizophrenia (SCZ) patients at the time of admission is crucial for effective resource allocation and individual treatment planning. In this study, we developed a deep learning model that integrates demographic, behavioral, and blood test data...

Full description

Saved in:
Bibliographic Details
Main Authors: Yihang Bao, Wanying Wang, Zhe Liu, Weidi Wang, Xue Zhao, Shunying Yu, Guan Ning Lin
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Schizophrenia
Online Access:https://doi.org/10.1038/s41537-025-00585-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850028067714498560
author Yihang Bao
Wanying Wang
Zhe Liu
Weidi Wang
Xue Zhao
Shunying Yu
Guan Ning Lin
author_facet Yihang Bao
Wanying Wang
Zhe Liu
Weidi Wang
Xue Zhao
Shunying Yu
Guan Ning Lin
author_sort Yihang Bao
collection DOAJ
description Abstract Early warning of long-term hospitalization in schizophrenia (SCZ) patients at the time of admission is crucial for effective resource allocation and individual treatment planning. In this study, we developed a deep learning model that integrates demographic, behavioral, and blood test data from admission to forecast extended hospital stays using a retrospective cohort. By utilizing language models, our developed algorithm efficiently extracts 95% of the unstructured electronic health records data needed for this work, while ensuring data privacy and low error rate. This paradigm has also been demonstrated to have significant advantages in reducing potential discrimination and erroneous dependencies. By utilizing multimodal features, our deep learning model achieved a classification accuracy of 0.81 and an AUC of 0.9. Key risk factors identified included advanced age, longer disease duration, and blood markers such as elevated neutrophil-to-lymphocyte ratio, lower lymphocyte percentage, and reduced albumin levels, validated through comprehensive interpretability analyses and ablation studies. The inclusion of multimodal data significantly improved prediction performance, with demographic variables alone achieving an accuracy of 0.73, which increased to 0.81 with the addition of behavioral and blood test data. Our approach outperformed traditional machine learning methods, which were less effective in predicting long-term stays. This study demonstrates the potential of integrating diverse data types for enhanced predictive accuracy in mental health care, providing a robust framework for early intervention and personalized treatment in SCZ management.
format Article
id doaj-art-2e790d0ecbff4987aab90d7ea510faa1
institution DOAJ
issn 2754-6993
language English
publishDate 2025-03-01
publisher Nature Portfolio
record_format Article
series Schizophrenia
spelling doaj-art-2e790d0ecbff4987aab90d7ea510faa12025-08-20T02:59:57ZengNature PortfolioSchizophrenia2754-69932025-03-0111111210.1038/s41537-025-00585-2Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophreniaYihang Bao0Wanying Wang1Zhe Liu2Weidi Wang3Xue Zhao4Shunying Yu5Guan Ning Lin6Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong UniversityShanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong UniversityShanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong UniversityShanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong UniversityShanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong UniversityShanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong UniversityShanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, School of Biomedical Engineering, Shanghai Jiao Tong UniversityAbstract Early warning of long-term hospitalization in schizophrenia (SCZ) patients at the time of admission is crucial for effective resource allocation and individual treatment planning. In this study, we developed a deep learning model that integrates demographic, behavioral, and blood test data from admission to forecast extended hospital stays using a retrospective cohort. By utilizing language models, our developed algorithm efficiently extracts 95% of the unstructured electronic health records data needed for this work, while ensuring data privacy and low error rate. This paradigm has also been demonstrated to have significant advantages in reducing potential discrimination and erroneous dependencies. By utilizing multimodal features, our deep learning model achieved a classification accuracy of 0.81 and an AUC of 0.9. Key risk factors identified included advanced age, longer disease duration, and blood markers such as elevated neutrophil-to-lymphocyte ratio, lower lymphocyte percentage, and reduced albumin levels, validated through comprehensive interpretability analyses and ablation studies. The inclusion of multimodal data significantly improved prediction performance, with demographic variables alone achieving an accuracy of 0.73, which increased to 0.81 with the addition of behavioral and blood test data. Our approach outperformed traditional machine learning methods, which were less effective in predicting long-term stays. This study demonstrates the potential of integrating diverse data types for enhanced predictive accuracy in mental health care, providing a robust framework for early intervention and personalized treatment in SCZ management.https://doi.org/10.1038/s41537-025-00585-2
spellingShingle Yihang Bao
Wanying Wang
Zhe Liu
Weidi Wang
Xue Zhao
Shunying Yu
Guan Ning Lin
Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophrenia
Schizophrenia
title Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophrenia
title_full Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophrenia
title_fullStr Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophrenia
title_full_unstemmed Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophrenia
title_short Leveraging deep neural network and language models for predicting long-term hospitalization risk in schizophrenia
title_sort leveraging deep neural network and language models for predicting long term hospitalization risk in schizophrenia
url https://doi.org/10.1038/s41537-025-00585-2
work_keys_str_mv AT yihangbao leveragingdeepneuralnetworkandlanguagemodelsforpredictinglongtermhospitalizationriskinschizophrenia
AT wanyingwang leveragingdeepneuralnetworkandlanguagemodelsforpredictinglongtermhospitalizationriskinschizophrenia
AT zheliu leveragingdeepneuralnetworkandlanguagemodelsforpredictinglongtermhospitalizationriskinschizophrenia
AT weidiwang leveragingdeepneuralnetworkandlanguagemodelsforpredictinglongtermhospitalizationriskinschizophrenia
AT xuezhao leveragingdeepneuralnetworkandlanguagemodelsforpredictinglongtermhospitalizationriskinschizophrenia
AT shunyingyu leveragingdeepneuralnetworkandlanguagemodelsforpredictinglongtermhospitalizationriskinschizophrenia
AT guanninglin leveragingdeepneuralnetworkandlanguagemodelsforpredictinglongtermhospitalizationriskinschizophrenia