|
Policy Recommendations for the Strategic Implementation of Public Health Policy to Mitigate PM 2.5 Pollution through Artificial Intelligence: A Case Study on AI-Driven Lung Cancer Diagnosis |
|---|---|
| รหัสดีโอไอ | |
| Creator | Techatach Khlaisokk |
| Title | Policy Recommendations for the Strategic Implementation of Public Health Policy to Mitigate PM 2.5 Pollution through Artificial Intelligence: A Case Study on AI-Driven Lung Cancer Diagnosis |
| Contributor | Janita Boriboon, Jutamas Moolkamsri, Pongphon Chamat, Rangsiman Songklod, Thanakon Sangkhaloke, Saowalak Klamsakun |
| Publisher | Graduate School of Public Administration, National Institute of Development Administration (NIDA) |
| Publication Year | 2568 |
| Journal Title | Journal of Public Administration, Public Affairs, and Management |
| Journal Vol. | 23 |
| Journal No. | 1 |
| Page no. | 55-92 |
| Keyword | Public Health Policy Development, AI-Driven Governance, Big Data-Based Policymaking |
| URL Website | https://so05.tci-thaijo.org/index.php/pajournal/article/view/281008 |
| ISSN | 2985-0762 |
| Abstract | This study investigates the application of big data and artificial intelligence (AI) to support the formulation of evidence-based public health policy recommendations, with an emphasis on mitigating lung cancer risks linked to PM2.5 air pollution. Using 15,000 social media images, an AI model was trained via a convolutional neural network using Google’s Teachable Machine. The model achieved high performance with an accuracy of 100 percent and test accuracy of 99.5 percent, and low prediction error with loss of 0.01 percent and test loss of 1.67 percent. Key factors influencing policy implementation include policy resources, organizational capacity, and teamwork. The resulting AI model was deployed as a web application using the Python Flask framework, enabling real-time lung cancer diagnosis and rapid treatment responses. The study’s contributions include the design of a policy framework for the National Health Environment Data Center (NHEDC), the development of an AI-driven platform for real-time risk prediction, and the integration of proactive public health surveillance policy in high-risk PM2.5 areas. |
