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

Overview

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.

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.