Abstract

Background: The integration of artificial intelligence (AI) into healthcare, especially nursing, offers transformative possibilities for mental health diagnosis. This study explores how MRI-based machine learning can support nurses in accurately identifying schizophrenia, addressing a growing need for innovative diagnostic support in nursing practice.

Objective: To evaluate the effectiveness of AI algorithms utilizing MRI data in differentiating patients with schizophrenia from healthy individuals, focusing on the practical applications for nursing in clinical environments.

Methods: MRI data, including Functional Network Connectivity and Source-Based Morphometry from 86 participants (40 patients with schizophrenia, 46 controls), were used to train machine learning models such as k-NN, SVM, decision trees, random forest, and deep neural networks.

Findings: The deep neural network achieved the highest accuracy (0.76), F1 score (0.73), and AUC (0.86), with SVM as the next best performer (accuracy: 0.65, F1 score: 0.58, AUC: 0.82).

Conclusion: This research underscores AI’s potential to support nursing practice in mental health by enabling early detection and personalized patient care. By integrating AI-driven MRI analysis, nurses can assume a more proactive role in mental health assessment, enhancing patient outcomes and contributing to AI-enabled clinical innovation.

Notes

References:

1. Hosna Tavakoli, Reza Rostami, Reza Shalbaf, Mohammad-Reza Nazem-Zadeh
medRxiv 2024.08.09.24311726; doi: https://doi.org/10.1101/2024.08.09.24311726

2. Zhang J, Rao VM, Tian Y, Yang Y, Acosta N, Wan Z, Lee PY, Zhang C, Kegeles LS, Small SA, Guo J. Detecting schizophrenia with 3D structural brain MRI using deep learning. Sci Rep. 2023 Sep 2;13(1):14433. doi: 10.1038/s41598-023-41359-z. PMID: 37660217; PMCID: PMC10475022.

Description

This research explores the use of AI-driven MRI analysis in enhancing nursing capabilities for schizophrenia detection. Participants will learn how integrating machine learning into clinical practice empowers nurses to improve diagnostic accuracy, early intervention, and personalized care for mental health patients.

Author Details

Yi Hsuan Chiang, PhD

Sigma Membership

Lambda Beta at-Large

Type

Presentation

Format Type

Text-based Document

Study Design/Type

Other

Research Approach

Other

Keywords:

Academic-clinical Partnership, Artificial Intelligence, AI, MRI-based Machine Learning, Schizophrenia Identification, Diagnostics

Conference Name

36th International Nursing Research Congress

Conference Host

Sigma Theta Tau International

Conference Location

Seattle, Washington, USA

Conference Year

2025

Rights Holder

All rights reserved by the author(s) and/or publisher(s) listed in this item record unless relinquished in whole or part by a rights notation or a Creative Commons License present in this item record.

Review Type

Abstract Review Only: Reviewed by Event Host

Acquisition

Proxy-submission

Click on the above link to access the slide deck.

Share

COinS
 

Advancing Nursing Practice with AI: MRI-Enhanced Machine Learning for Schizophrenia Screening

Seattle, Washington, USA

Background: The integration of artificial intelligence (AI) into healthcare, especially nursing, offers transformative possibilities for mental health diagnosis. This study explores how MRI-based machine learning can support nurses in accurately identifying schizophrenia, addressing a growing need for innovative diagnostic support in nursing practice.

Objective: To evaluate the effectiveness of AI algorithms utilizing MRI data in differentiating patients with schizophrenia from healthy individuals, focusing on the practical applications for nursing in clinical environments.

Methods: MRI data, including Functional Network Connectivity and Source-Based Morphometry from 86 participants (40 patients with schizophrenia, 46 controls), were used to train machine learning models such as k-NN, SVM, decision trees, random forest, and deep neural networks.

Findings: The deep neural network achieved the highest accuracy (0.76), F1 score (0.73), and AUC (0.86), with SVM as the next best performer (accuracy: 0.65, F1 score: 0.58, AUC: 0.82).

Conclusion: This research underscores AI’s potential to support nursing practice in mental health by enabling early detection and personalized patient care. By integrating AI-driven MRI analysis, nurses can assume a more proactive role in mental health assessment, enhancing patient outcomes and contributing to AI-enabled clinical innovation.