Prediction of measles patients using machine learning classifiers: a comparative study

Abstract

Abstract Background Measles has high primary reproductive number, extremely infectious and ranked second to malaria in terms of disease burden in Ghana. Owing to the disease’s high infectious rate, making early diagnosis based on an accurate system can help limit the spread of the disease. Studies have been conducted to derive models to serve as preliminary tools for early detection. However, these derived models are based on traditional methods, which may be limited in terms of model sensitivity and prediction power. This study focuses on comparing the performance of five machine learning classification techniques with a traditional method for predicting measles patients in Ghana. The study was an analytical cross-sectional design of suspected measles cases in Ghana. Results The performance of six classifiers were compared and the random forest (RF) model demonstrated better performance among other models. The RF model achieved the highest sensitivity (0.88) specificity (0.96), ROC (0.92) and total accuracy (0.92). Conclusions Our findings showed that, despite all the six methods had good performance in classifying measles patients, the RF model outperformed all the other classifiers in terms of different criteria in prediction accuracy. Accordingly, this approach is an effective classifier for predicting measles in the early stage.