Augmenting DSM-5 diagnostic criteria with self-attention-based BiLSTM models for psychiatric diagnosis

Most previous studies make psychiatric diagnoses based on diagnostic terms. In this study we sought to augment Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-5) diagnostic criteria with deep neural network models to make psychiatric diagnoses based on psychiatric notes. We a...

Full description

Saved in:
Bibliographic Details
Published in:Artificial intelligence in medicine 2023-02, Vol.136, p.102488-102488, Article 102488
Main Authors: Wu, Chi-Shin, Chen, Chien-Hung, Su, Chu-Hsien, Chien, Yi-Ling, Dai, Hong-Jie, Chen, Hsin-Hsi
Format: Article
Language:English
Subjects:
Bipolar Disorder - diagnosis
Diagnostic and Statistical Manual of Mental Disorders
Electronic health records
Humans
Knowledge-augmented deep neural network
Mental Disorders - diagnosis
Psychiatric diagnosis
Schizophrenia - diagnosis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most previous studies make psychiatric diagnoses based on diagnostic terms. In this study we sought to augment Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-5) diagnostic criteria with deep neural network models to make psychiatric diagnoses based on psychiatric notes. We augmented DSM-5 diagnostic criteria with self-attention-based bidirectional long short-term memory (BiLSTM) models to identify schizophrenia, bipolar, and unipolar depressive disorders. Given that the diagnostic criteria for psychiatric diagnosis include a certain symptom profile and functional impairment, we first extracted psychiatric symptoms and functional features with two approaches, including a lexicon-based approach and a dependency parsing approach. Then, we incorporated free-text discharge notes and extracted features for psychiatric diagnoses with the proposed models. The micro-averaged F1 scores of the two automatic annotation approaches were greater than 0.8. BiLSTM models with self-attention outperformed the rule-based models with DSM-5 criteria in the prediction of schizophrenia and bipolar disorder, while the latter outperformed the former in predicting unipolar depressive disorder. Approaches for augmenting DSM-5 criteria with a self-attention-based BiLSTM outperformed both pure rule-based and pure deep neural network models. In terms of classification of psychiatric diagnoses, we observed that the performance for schizophrenia and bipolar disorder was acceptable. This DSM-5-augmented deep neural network models showed good performance in identifying psychiatric diagnoses from psychiatric notes. We conclude that it is possible to establish a model that consults clinical notes to make psychiatric diagnoses comparably to physicians. Further research will be extended to outpatient notes and other psychiatric disorders. •Most previous studies make psychiatric diagnoses based on diagnostic terms.•We developed model to identify diagnosis from history and mental status examination.•DSM-5 augmented BiLSTM models outperformed the rule-based or pure deep network model.
ISSN:0933-3657
1873-2860
DOI:10.1016/j.artmed.2023.102488