A personalized infectious disease risk prediction system

•Personal risk factor is not the only factor that affecting a person's risk contracting of an infectious disease.•Few modifications from the existing knowledge representations are added to (1) capture all factors affecting an infectious disease risk in a person, and (2) allow automatic generation of a prediction model.•A special-purpose algorithm was built to automatically generate an equivalent prediction model from the knowledge representation to predict the personalized infectious disease risks.•A system which aims to incorporate current data and declarative knowledge, as well as tailoring the knowledge-base, algorithm, and the generated prediction model is presented.•Evaluations for three major infectious diseases at country-level are included with intention to seek the reliability of the personalized infectious disease risk probabilities from the generated prediction model. This article presents a system for predicting a human's risk of contracting infectious diseases based on their personal attributes and environments (region, specific location features and climate contexts). This system is also intended to help human experts in the domain (i.e. epidemiologists) to represent their knowledge and ease their jobs related to personalized infectious disease risk prediction. The system consists of a knowledge representation to encode epidemiological knowledge about infectious disease risk, and an algorithm that auto-converts the encoded knowledge into a model that predicts the risk as a probability. The knowledge representation, Infectious Disease Risk (IDR), consists of an ontology and rules to represent the knowledge structure and its quantification in a way that allows auto-generation to a prediction model, Bayesian Network (BN). The algorithm, BN-Builder, converts the IDR knowledge-base to an infectious disease risk BN, including populating the basis of predictive reasoning from the IDR rules. A user interface facilitates encoding of epidemiological knowledge into the IDR knowledge-base. The system's output, personalized infectious disease risk prediction, is validated for three disease-country contexts: Dengue Fever and Tuberculosis in Indonesia, and Cholera in India. The personalized infectious disease risks are reliable (p values > 0.05) for each population parameter. The personalized infectious disease risk probability can be reliably predicted using this system. Inclusion of more granularity on contexts in this domain will be considered in further