Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model
Mood disorders are ubiquitous mental disorders with familial aggregation. Extracting family history of psychiatric disorders from large electronic hospitalization records is helpful for further study of onset characteristics among patients with a mood disorder. This study uses an observational clini...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-05-01
|
Series: | Frontiers in Psychiatry |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2022.861930/full |
_version_ | 1811340204328353792 |
---|---|
author | Cheng Wan Cheng Wan Xuewen Ge Junjie Wang Junjie Wang Xin Zhang Xin Zhang Yun Yu Yun Yu Jie Hu Jie Hu Yun Liu Yun Liu Hui Ma |
author_facet | Cheng Wan Cheng Wan Xuewen Ge Junjie Wang Junjie Wang Xin Zhang Xin Zhang Yun Yu Yun Yu Jie Hu Jie Hu Yun Liu Yun Liu Hui Ma |
author_sort | Cheng Wan |
collection | DOAJ |
description | Mood disorders are ubiquitous mental disorders with familial aggregation. Extracting family history of psychiatric disorders from large electronic hospitalization records is helpful for further study of onset characteristics among patients with a mood disorder. This study uses an observational clinical data set of in-patients of Nanjing Brain Hospital, affiliated with Nanjing Medical University, from the past 10 years. This paper proposes a pretrained language model: Bidirectional Encoder Representations from Transformers (BERT)–Convolutional Neural Network (CNN). We first project the electronic hospitalization records into a low-dimensional dense matrix via the pretrained Chinese BERT model, then feed the dense matrix into the stacked CNN layer to capture high-level features of texts; finally, we use the fully connected layer to extract family history based on high-level features. The accuracy of our BERT–CNN model was 97.12 ± 0.37% in the real-world data set from Nanjing Brain Hospital. We further studied the correlation between mood disorders and family history of psychiatric disorder. |
first_indexed | 2024-04-13T18:37:36Z |
format | Article |
id | doaj.art-f93f3f644ddc4a2dbe25b63e2a1d9e11 |
institution | Directory Open Access Journal |
issn | 1664-0640 |
language | English |
last_indexed | 2024-04-13T18:37:36Z |
publishDate | 2022-05-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Psychiatry |
spelling | doaj.art-f93f3f644ddc4a2dbe25b63e2a1d9e112022-12-22T02:34:50ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402022-05-011310.3389/fpsyt.2022.861930861930Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language ModelCheng Wan0Cheng Wan1Xuewen Ge2Junjie Wang3Junjie Wang4Xin Zhang5Xin Zhang6Yun Yu7Yun Yu8Jie Hu9Jie Hu10Yun Liu11Yun Liu12Hui Ma13Department of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, ChinaInstitute of Medical Informatics and Management, Nanjing Medical University, Nanjing, ChinaDepartment of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, ChinaDepartment of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, ChinaInstitute of Medical Informatics and Management, Nanjing Medical University, Nanjing, ChinaDepartment of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, ChinaDepartment of Information, First Affiliated Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, ChinaInstitute of Medical Informatics and Management, Nanjing Medical University, Nanjing, ChinaDepartment of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, ChinaInstitute of Medical Informatics and Management, Nanjing Medical University, Nanjing, ChinaDepartment of Medical Informatics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, ChinaDepartment of Information, First Affiliated Hospital, Nanjing Medical University, Nanjing, ChinaDepartment of Medical Psychology, Affiliated Nanjing Brain Hospital, Nanjing Medical University, Nanjing, ChinaMood disorders are ubiquitous mental disorders with familial aggregation. Extracting family history of psychiatric disorders from large electronic hospitalization records is helpful for further study of onset characteristics among patients with a mood disorder. This study uses an observational clinical data set of in-patients of Nanjing Brain Hospital, affiliated with Nanjing Medical University, from the past 10 years. This paper proposes a pretrained language model: Bidirectional Encoder Representations from Transformers (BERT)–Convolutional Neural Network (CNN). We first project the electronic hospitalization records into a low-dimensional dense matrix via the pretrained Chinese BERT model, then feed the dense matrix into the stacked CNN layer to capture high-level features of texts; finally, we use the fully connected layer to extract family history based on high-level features. The accuracy of our BERT–CNN model was 97.12 ± 0.37% in the real-world data set from Nanjing Brain Hospital. We further studied the correlation between mood disorders and family history of psychiatric disorder.https://www.frontiersin.org/articles/10.3389/fpsyt.2022.861930/fullfamily historymood disorderpsychiatric disorderelectronic health recordspretrained BERT CNN model |
spellingShingle | Cheng Wan Cheng Wan Xuewen Ge Junjie Wang Junjie Wang Xin Zhang Xin Zhang Yun Yu Yun Yu Jie Hu Jie Hu Yun Liu Yun Liu Hui Ma Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model Frontiers in Psychiatry family history mood disorder psychiatric disorder electronic health records pretrained BERT CNN model |
title | Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model |
title_full | Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model |
title_fullStr | Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model |
title_full_unstemmed | Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model |
title_short | Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model |
title_sort | identification and impact analysis of family history of psychiatric disorder in mood disorder patients with pretrained language model |
topic | family history mood disorder psychiatric disorder electronic health records pretrained BERT CNN model |
url | https://www.frontiersin.org/articles/10.3389/fpsyt.2022.861930/full |
work_keys_str_mv | AT chengwan identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT chengwan identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT xuewenge identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT junjiewang identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT junjiewang identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT xinzhang identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT xinzhang identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT yunyu identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT yunyu identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT jiehu identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT jiehu identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT yunliu identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT yunliu identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel AT huima identificationandimpactanalysisoffamilyhistoryofpsychiatricdisorderinmooddisorderpatientswithpretrainedlanguagemodel |