Machine learning to improve the understanding of rabies epidemiology in low surveillance settings

• Published in: Scientific reports 2024-10, Vol.14 (1), p.25851-10, Article 25851
• Main Authors: Keshavamurthy, Ravikiran, Boutelle, Cassandra, Nakazawa, Yoshinori, Joseph, Haim, Joseph, Dady W., Dilius, Pierre, Gibson, Andrew D., Wallace, Ryan M.
• Format: Article
• Language: English
• Subjects: 631/114/1305; 631/114/2413; 631/114/2415; 639/705/531; 692/699/255/2514; Animals; Bites and Stings - epidemiology; Bites and Stings - virology; Dogs; Epidemiological Monitoring; Epidemiology; Extreme gradient boosting; Humanities and Social Sciences; Humans; Learning algorithms; Logistic Models; Machine Learning; Mathematical models; multidisciplinary; Prediction; Rabies; Rabies - epidemiology; Rabies - veterinary; Risk stratification; Science; Science (multidisciplinary); Zoonoses; Zoonotic disease surveillance
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-024-76089-3

In low and middle-income countries, a large proportion of animal rabies investigations end without a conclusive diagnosis leading to epidemiologic interpretations informed by clinical, rather than laboratory data. We compared Extreme Gradient Boosting (XGB) with Logistic Regression (LR) for their ability to estimate the probability of rabies in animals investigated as part of an Integrated Bite Case Management program (IBCM). To balance our training data, we used Random Oversampling (ROS) and Synthetic Minority Oversampling Technique. We developed a risk stratification framework based on predicted rabies probabilities. XGB performed better at predicting rabies cases than LR. Oversampling strategies enhanced the model sensitivity making them the preferred technique to predict rare events like rabies in a biting animal. XGB-ROS classified most of the confirmed rabies cases and only a small proportion of non-cases as either high (confirmed cases = 85.2%, non-cases = 0.01%) or moderate (confirmed cases = 8.4%, non-cases = 4.0%) risk. Model-based risk stratification led to a 3.2-fold increase in epidemiologically useful data compared to a routine surveillance strategy using IBCM case definitions. Our study demonstrates the application of machine learning to strengthen zoonotic disease surveillance under resource-limited settings.