The Faculty of Engineering, Mahidol University, through its Centre of Logistics Management and Healthcare Supply Chain (LogHealth) and the Faculty of Medicine, Ramathibodi Hospital, in collaboration with the National Research Council of Thailand (NRCT) and the Department of Disease Control, Ministry of Public Health, have jointly developed the prototype project for an intelligent information technology system to manage epidemic situations in Thailand, known as the "Thailand Epidemic AI."

The project, spearheaded by the Faculty of Engineering, Mahidol University, aims to prepare for future epidemics by applying big data management and artificial intelligence (AI) technology. This system is designed to manage data, forecast the number of infected individuals across various epidemics, and estimate the resources needed for effective epidemic management and control.

Dr. Wiparat De-ong, Executive Director of the National Research Council of Thailand, Ministry of Higher Education, Science, Research, and Innovation, highlighted the importance of this initiative. She noted that the global COVID-19 pandemic provided significant lessons and opportunities for improving responses to future epidemics. The collaboration between Mahidol University, the Department of Disease Control, and other related agencies in 2023 led to the development of a pilot system for forecasting epidemics. This system, which utilized historical infection data, delivered promising results and proved valuable in detecting trends in both existing and emerging epidemics. The NRCT is committed to fully supporting the expansion of this research project to further develop research knowledge and apply these findings for the betterment of the country.

Associate Professor Dr. Sittiwat Lertsiri, Acting Vice President of Mahidol University, reaffirmed the university’s dedication to conducting research that contributes to the development of the country and society. He emphasized that the application of AI technology in managing epidemic situations allows for more accurate forecasting of epidemic trends, more efficient resource management, and integrated epidemic response strategies that can prevent public health threats more effectively.

Dr. Wichan Bhunyakitikorn, Director of the Epidemiology Division, Department of Disease Control, Ministry of Public Health, explained the significance of this collaboration. He emphasized that the Department of Disease Control, as the primary organization responsible for national and international disease surveillance, prevention, and control, recognizes the value of AI technology in enhancing its capabilities. The AI system developed through this partnership will facilitate more accurate outbreak predictions and better resource management, making the Department's work more effective.

Associate Professor Dr. Duangpun Kritchanchai, Head of the Centre of Logistics Management and Healthcare Supply Chain (LogHealth), Faculty of Engineering, Mahidol University, discussed the importance of applying technology to enhance data management efficiency. The collaboration with the Department of Disease Control has integrated Big Data management principles and AI technology with logistics and supply chain management expertise to improve resource management for future epidemics. The epidemic forecasting system, developed using historical infection data, aims to predict and prepare for future outbreaks.

Ms. Atchara Dokkulap, Head of Quality Development, Faculty of Medicine, Ramathibodi Hospital, Mahidol University, and the research project leader, shared insights into the project’s achievements. In 2023, the team developed an epidemic forecasting system using five years of retrospective data. The Neural Networks Model they created achieved an 84% accuracy rate in predicting epidemics, outperforming Facebook's Prophet Model, which had a 55% accuracy rate. Additionally, the system can detect likely outbreaks of infectious diseases and immediately alert relevant officials when new data is entered.

Looking ahead, the research team envisions two key phases for the continued development of this system:

1. Epidemic Forecasting System Enhancement: Initially, the model was developed to forecast epidemics on a broad scale using data from the past five years. The next step is to refine the system to forecast at the local level for each specific disease, integrating data on reported cases to detect outbreaks promptly.

2. Resource Management Optimization: The use of technology to forecast and manage resources for epidemic control, including ordering, storing, and distributing supplies, will be further refined. This will help manage resources more effectively at both the local and national levels, reducing inefficiencies such as over-ordering or resource duplication, and ensuring comprehensive and appropriate resource distribution.