Naive Bayes for Diabetes Prediction: Developing a Classification Model for Risk Identification in Specific Populations

Depending on persuasive statistics, the increasing prevalence of diabetes worldwide is a huge challenge for individuals, families, and nations. According to International Diabetes Federation (IDF) projections, the number of adults with diabetes is expected to rise by an astounding 46% by 2045, to reach 783 million, or one in eight. In response to this growing concern, this research explores the implementation of the Naive Bayes algorithm for predicting diabetes, employing comprehensive data cleansing and randomization techniques. A systematic evaluation of the model's performance is conducted using several training and testing split ratios (65:35, 75:25, 85:15). The outcome showed that the model performed best at the 65:35 split ratio, with accuracy reaching its maximum of 88.16%, precision 0.883, recall 0.881, and f1-score 0.882.