![]() Another example is that depressive symptoms are frequently observed in patients with dementia. The use of antidepressants for bipolar depression might also induce mood swings or a manic episode. If a psychiatrist were to ignore previous hypomanic or manic episodes, bipolar disorders would be misdiagnosed as depressive disorders. For example, depressive symptoms are often observed in patients with bipolar disorders. However, making a diagnosis is not easy because symptoms are commonly shared among these diagnoses. The differential diagnosis of mental disorders is quite important because the decision for treatment selection and prediction of prognosis are dependent on the accuracy of diagnosis. These diagnostic criteria are derived from the clinical observation of the symptoms, signs, and course of mental diseases. Our results also suggested that the use of the feature dependency strategy to build multi-labeling models instead of problem transformation is superior considering its higher performance and simplicity in the training process.Ĭurrently, the diagnosis and classification of mental disorders are commonly based on the International Statistical Classification of Diseases and Related Health Problems (ICD) and the Diagnostic and Statistical Manual of Mental Disorders (DSM) system. The experimental results demonstrated that the models with the pre-trained techniques outperformed the models without transferred knowledge by micro-avg. We hypothesized that the models that rely on transferred knowledge would be expected to outperform the models learned from scratch. ![]() Several state-of-the-art NLP methods based on deep learning along with pre-trained models based on shallow or deep transfer learning were adapted to develop models to classify the aforementioned diseases. ![]() Three annotators with clinical experience reviewed the notes to make diagnoses for major/minor depression, bipolar disorder, schizophrenia, and dementia to form a small and highly imbalanced corpus. A total of 500 patients were randomly selected from a medical center database. This study explored the feasibility of applying NLP to a small EHR dataset to investigate the power of transfer learning to facilitate the process of patient screening in psychiatry. The introduction of pre-trained language models in natural language processing (NLP) based on deep learning and the availability of electronic health records (EHRs) presents a great opportunity to transfer the “knowledge” learned from data in the general domain to enable the analysis of unstructured textual data in clinical domains. 7Department of Psychiatry, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.6Taipei City Psychiatric Center, Taipei City Hospital, Taipei, Taiwan.5Big Data Laboratory, Chunghwa Telecom Laboratories, Taoyuan, Taiwan.4Department of Psychiatry, National Taiwan University Hospital, Taipei, Taiwan.3National Institute of Cancer Research, National Health Research Institutes, Tainan, Taiwan.2School of Post-Baccalaureate Medicine, Kaohsiung Medical University, Kaohsiung, Taiwan.1Intelligent System Laboratory, Department of Electrical Engineering, College of Electrical Engineering and Computer Science, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan.Hong-Jie Dai 1,2,3 *, Chu-Hsien Su 4, You-Qian Lee 1, You-Chen Zhang 1, Chen-Kai Wang 5, Chian-Jue Kuo 6,7 and Chi-Shin Wu 4 *
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |