Applications of Case-based Reasoning in the Disease Prevention and Control of Congenital Syphilis in Southern China

Description

The increased Congenital Syphilis/先天性梅毒(CS) cases are a major public health concern in many regions of China [1-4]. The Chinese Ministry of Health announced a comprehensive 10-year national policy plan on averting and controlling the epidemic of CS cases, includes 4 main strategies: educational campaigns on safer sex practices, increasing prenatal screening coverage, increasing treatment completion rates, and providing additional training to health professionals. An initial study has been carried out on the effectiveness of such a policy implementation in relation to its outcomes, which aims to reduce the cases of CS according to the national policy plan. Based on the Guangdong syphilis surveillance and a CS intervention program datasets collected, a four-pronged comprehensive syphilis control strategy was recommended using a decision tree model to reach a large reduction of CS cases. However more comprehensive measures are required. Similar to many other scientific domains, data modeling can benefit from systematic knowledge management using techniques such from artificial intelligence and machine learning. In this project, we propose to use Case-based reasoning to develop analytical and prediction models to predict birth outcomes and recommend abortion decisions based on symptoms and pregnancy stages, and more importantly to discover the best policy strategy combinations, which will result in the lowest CS incidents allowing policy makers to make informed decisions on the diseases prevention and control of the CS epidemic in China.