Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Association between lithium and arterial atherosclerosis in physically healthy bipolar disorder.

Journal of affective disorders·2026

Same author

Social participation and mental health among older adults during and after the COVID-19 pandemic.

Journal of the Formosan Medical Association = Taiwan yi zhi·2026

Same author

Familial coaggregation and shared genetic loading of mental disorders and cardiovascular diseases.

Psychological medicine·2026

Same author

The Effect of a Nationwide Aftercare Program for Self-Harm Presentations on the Risk of Self-Harm Repetition and Suicide: A Cohort Study.

The Journal of clinical psychiatry·2026

Same author

Evaluating real-world deployment of an HL7-CDA-aligned LLM for ICD-10-CM coding.

NPJ digital medicine·2026

Same author

Image-free dual-target single-pixel tracking.

Optics letters·2026

Same journal

Attention-deficit/hyperactivity disorder in India: epidemiology, diagnostic inequities, treatment gaps, and public mental health implications.

Frontiers in psychiatry·2026

Same journal

Frontotemporal cortical activity in Chinese male alcohol-dependent patients during a verbal fluency task: a functional near-infrared spectroscopy study.

Frontiers in psychiatry·2026

Same journal

Depression and anxiety before and after bariatric surgery: a longitudinal cohort study at King Abdulaziz University Hospital, Jeddah, Saudi Arabia.

Frontiers in psychiatry·2026

Same journal

Compassionate self-talk enhances autonomic flexibility during cognitive stress in generalized anxiety disorder: a randomized controlled trial with HRV evidence.

Frontiers in psychiatry·2026

Same journal

A systematic review and meta-analysis of diagnostic test accuracy of mental health screening tools applicable to adolescents in sub-Saharan Africa.

Frontiers in psychiatry·2026

Same journal

From digital access to social connectedness: the digital divide, bonding social capital, and depressive symptoms among older adults in China.

Frontiers in psychiatry·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 17, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Deep Learning-Based Natural Language Processing for Screening Psychiatric Patients.

Hong-Jie Dai^1,2,3, Chu-Hsien Su⁴, You-Qian Lee¹

¹Intelligent System Laboratory, Department of Electrical Engineering, College of Electrical Engineering and Computer Science, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan.

Frontiers in Psychiatry

|February 15, 2021

Summary

This summary is machine-generated.

Transfer learning with pre-trained natural language processing models significantly improved patient screening for psychiatric disorders using electronic health records. These advanced models outperformed those trained from scratch, demonstrating the power of transferring general knowledge to clinical data analysis.

Keywords:

deep learning natural language processing patient screening psychiatric diagnoses text classification

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Nov 17, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

Clinical Informatics
Artificial Intelligence in Medicine
Natural Language Processing

Background:

Electronic Health Records (EHRs) contain vast amounts of unstructured clinical notes.
Pre-trained language models (PLMs) offer a powerful approach for analyzing complex text data.
Transfer learning enables the application of knowledge from general domains to specialized fields like clinical psychiatry.

Purpose of the Study:

To explore the feasibility of applying NLP and transfer learning to a small EHR dataset for psychiatric patient screening.
To investigate the effectiveness of pre-trained models versus models trained from scratch for classifying psychiatric disorders.
To compare different modeling strategies for multi-label classification of psychiatric conditions.

Main Methods:

Utilized a dataset of 500 patients' clinical notes from EHRs.
Employed experienced clinical annotators for diagnoses of depression, bipolar disorder, schizophrenia, and dementia.
Adapted state-of-the-art deep learning NLP methods and pre-trained models (shallow and deep transfer learning) for disease classification.
Implemented feature dependency strategy for multi-label modeling.

Main Results:

Models incorporating transfer learning demonstrated superior performance compared to models trained from scratch.
Pre-trained models achieved higher micro-average and macro-average F-scores (0.11 and 0.28, respectively) than models without transferred knowledge.
The feature dependency strategy proved more effective and simpler for multi-label classification than problem transformation.

Conclusions:

Transfer learning significantly enhances the performance of NLP models in analyzing clinical text for psychiatric diagnoses.
Pre-trained models are a valuable tool for improving patient screening and analysis of EHR data.
The feature dependency strategy is a recommended approach for building efficient multi-label classification models in clinical NLP applications.