Cardiovascular disease (CVD) has become a significant contributor to premature deaths for many years in Fiji. CVD's late detection also significantly impacts annual deaths and casualties. Currently, Fiji lacks diagnosis tools to enable people to know their risk levels. In this paper, a machine learning mobile application was developed that can be easily accessible to the local population for early prediction of CVD risk. The design science approach was used to guide the development of the application. The design process involved identifying the problem and motivation, setting objectives, creating a machine-learning mobile application for medical record analysis, demonstrating the application to selected participants, evaluating its usability and the machine-learning model's performance, and communicating the findings. The results revealed that the proposed machine learning application achieved a high usability score of 87 on the System Usability Scale, indicating strong user-friendliness and adaptability. The machine learning model by random forest algorithm demonstrated the accuracy of 89% and was selected for implementation for CVD prediction in Fiji, as it outperformed other algorithms in the study: k-nearest neighbour, support vector machine, decision tree, and Naïve Bayes. The results highlight the effectiveness and user acceptance of the developed system in Fiji’s medical facilities for CVD prediction.

• APA 7th style

• Chicago style

• IEEE style

• Vancouver style