Unknown Disease Outbreaks Detection: A Pilot Study on Feature-Based Knowledge Representation and Reasoning Model

Background: The outbreak of COVID-19 in 2019 has rapidly swept the world, causing irreparable loss to human beings. The pandemic has shown that there is still a delay in early response to disease outbreaks and needs a method for unknown disease outbreaks detection. The study's objective is to establish a new medical knowledge representation and reasoning model, and use the model to explore unknown disease outbreaks detection. Methods: The study defined abnormal values with diagnostic significances from clinical data as Features, and defined the Features as the preconditions of inference rules to match with knowledge bases, achieved in detecting unknown or emerging infectious disease outbreaks. Meanwhile, the study built a syndromic surveillance base to capture syndromic Features to improve the reliability and fault-tolerant ability of the system. Results: Based on the empirical study of China’s surveillance guideline for pneumonia with uncertain etiologies and early COVID-19 data in Wuhan, 2019, the result showed that the method proposed in this study can detect early COVID-19 cases with 82% of accuracy, and the duration from illness onset to local authorities notification of the early pandemic can be reduced to 7.0-10.0 days. Conclusions: This study offers a new solution to transfer traditional medical knowledge into structural data and forms diagnosis rules, enables the representation of doctors’ logistic thinking and knowledge transfer among different users. The empirical study of unknown disease outbreaks detection shows that the proposed method has a good detection accuracy and can perform an early response to unknown disease outbreaks.