Artificial Intelligence Cerebral Gray-white Matter Ratio Module Usage in Hsinchu District Hsinchu District Using an Artificial Intelligence Cerebral Gray-white Matter Ratio Module

Extrapolative Study on the Prognosis of Out-of-hospital Cardiac Arrest in the Hsinchu District Using an Artificial Intelligence Cerebral Gray-white Matter Ratio Module

This study aims to establish an electronic medical record and imaging database for out-of-hospital cardiac arrest (OHCA) patients at NTUH Hsinchu Branch. Leveraging an AI deep learning model and an automated brain gray-white matter analysis system developed at NTUH, the research seeks to validate these tools externally. By integrating electronic medical records and brain imaging data, the project strives to enhance the accuracy of prognostic assessments, supporting physicians and families in decision-making for post-cardiac arrest care. Validation at Hsinchu Branch will assess the model's reliability across diverse medical settings and patient populations, optimizing its applicability and accuracy.

Study Overview

• Status: Active, not recruiting
• Conditions: Out of Hospital Cardiac Arrest

Detailed Description

The purpose of this study is to establish an electronic medical record and imaging database for out-of-hospital cardiac arrest patients at National Taiwan University Hospital Hsinchu Branch. Our team have developed an AI deep learning model and an automated analysis system for brain gray-white matter based on data from National Taiwan University Hospital.

These developments will be externally validated using the database at Hsinchu Branch in this project. Accurate prognosis assessment is crucial for physicians and families in making decisions regarding post-cardiac arrest care period. However, the current available assessment tools have limited accuracy. This study aims to develop a multimodal prognostic evaluation model that combines electronic medical records and the automated analysis system for brain graywhite matter. This integration will enhance the accuracy and predictive capability of prognosis assessment. The research team has already developed an automated analysis system for calculating brain gray-white matter ratio from brain computed tomography images, providing important information about pathological changes in the brain.

Additionally, the team has also developed an AI-based predictive model for post-cardiac arrest prognosis, incorporating multiple indicators and variables. This system has been validated using data from National Taiwan University Hospital.

To further validate the accuracy and reliability of our models, the research team plans to collaborate with Hsinchu Branch in collecting and organizing relevant data of post-cardiac arrest patients, including electronic medical records and imaging files. The developed automated analysis system for brain gray-white matter and the AI-based predictive model will be applied for external validation. Through this research, the goal is to establish and optimize a more comprehensive and accurate prognosis assessment model, assisting physicians and families in making better decisions for post-cardiac arrest patients.

Furthermore, the collaboration with Hsinchu Branch will enable the validation of our models'applicability in different medical institutions and patient populations.

• Study Type: Observational
• Enrollment (Estimated): 350

Contacts and Locations

Study Locations

• Taiwan
  • Hsinchu, Taiwan, 300
    • National Taiwan University Hospital Hsin-Chu Branch

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients with out-of-hospital cardiac arrest

Description

Inclusion Criteria:

- Patients at National Taiwan University Hospital Hsinchu Branch who experienced non-traumatic cardiac arrest between January 1, 2014, and December 31, 2020, and successfully achieved return of spontaneous circulation (ROSC) following resuscitation.

Exclusion Criteria:

1. Under 18 years of age;
2. Pregnant women;
3. Individuals who did not achieve successful resuscitation
4. Individuals without computed tomography (CT) imaging after resuscitation.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Cerebral Performance Categories (CPC) Scale	The Cerebral Performance Categories (CPC) scale is crucial for evaluating neurological outcomes in OHCA patients, providing a standardized framework to assess brain function and recovery after cardiac arrest. Ranging from CPC 1 (good recovery) to CPC 5 (brain death), it categorizes levels of neurological impairment, offering insights into the patient's prognosis. This scale is widely used in clinical and research settings to ensure consistent outcome measurement and facilitate comparison across studies. Additionally, it plays a vital role in guiding clinical decisions and discussions with families about post-resuscitation care and expectations, ultimately supporting better-informed decision-making.	From the time of ROSC achievement until hospital discharge or death, assessed up to 700 days

Collaborators and Investigators

• Sponsor: National Taiwan University Hospital

Publications and helpful links

General Publications

• Mutasa S, Sun S, Ha R. Understanding artificial intelligence based radiology studies: What is overfitting? Clin Imaging. 2020 Sep;65:96-99. doi: 10.1016/j.clinimag.2020.04.025. Epub 2020 Apr 23.
• Chang HC, Tsai MS, Kuo LK, Hsu HH, Huang WC, Lai CH, Shih MC, Huang CH. Factors affecting outcomes in patients with cardiac arrest who receive target temperature management: The multi-center TIMECARD registry. J Formos Med Assoc. 2022 Jan;121(1 Pt 2):294-303. doi: 10.1016/j.jfma.2021.04.006. Epub 2021 Apr 29.
• Rea TD, Eisenberg MS, Sinibaldi G, White RD. Incidence of EMS-treated out-of-hospital cardiac arrest in the United States. Resuscitation. 2004 Oct;63(1):17-24. doi: 10.1016/j.resuscitation.2004.03.025.
• Wang CH, Huang CH, Chang WT, Tsai MS, Yu PH, Wu YW, Chen WJ. Prognostic performance of simplified out-of-hospital cardiac arrest (OHCA) and cardiac arrest hospital prognosis (CAHP) scores in an East Asian population: A prospective cohort study. Resuscitation. 2019 Apr;137:133-139. doi: 10.1016/j.resuscitation.2019.02.015. Epub 2019 Feb 20.
• Adrie C, Cariou A, Mourvillier B, Laurent I, Dabbane H, Hantala F, Rhaoui A, Thuong M, Monchi M. Predicting survival with good neurological recovery at hospital admission after successful resuscitation of out-of-hospital cardiac arrest: the OHCA score. Eur Heart J. 2006 Dec;27(23):2840-5. doi: 10.1093/eurheartj/ehl335. Epub 2006 Nov 2.

Study record dates

Study Major Dates

• Study Start (Actual): December 1, 2024
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): December 31, 2026

Study Registration Dates

• First Submitted: November 17, 2024
• First Submitted That Met QC Criteria: March 2, 2025
• First Posted (Actual): March 4, 2025

Study Record Updates

• Last Update Posted (Actual): November 18, 2025
• Last Update Submitted That Met QC Criteria: November 17, 2025
• Last Verified: November 1, 2025

More Information

Terms related to this study

• Keywords: Out-of-hospital cardiac arrest patients; resuscitation,; artificial intelligence deep learning model
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Heart Diseases; Heart Arrest; Out-of-Hospital Cardiac Arrest
• Other Study ID Numbers: 202404018RINA

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: The file contains private information and requires too much storage capacity, making it impossible to share.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No