Sickle cell disease (SCD) is a genetic illness that affects red blood cells and can lead to major complications like Acute Chest Syndrome (ACS), Cerebrovascular Accident (CVA), and even death from a stroke. SCD is frequent in some places of the world, especially where consanguineous marriages are common, such as in Saudi Arabia. This research presents artificial intelligence (AI) models that were tested on hospital clinical data collected between 2008 to 2020 using five different classifiers: Naive Bayes, Neural Networks (NN), Support Vector Machine (SVM), J48, and PART. To select the optimum classification approach, we analyzed the models based on the accuracy kappa statistics and the classification time. We also compared performance criteria such as sensitivity, specificity, accuracy, F1 measure, and AUC. The naive Bayes classifier outperformed the other classifiers with 92.22% accuracy in our investigation, which was then utilized to determine key elements that are common between SCD patients' inheritance and demographic data. The findings of this study through AI are aimed to assist hospital doctors and practitioners understand the correlation between disease inheritance and other factors, allowing them to better manage the disease by increasing disease awareness in the community, particularly among mothers. In terms of accuracy, all classifiers obtained above 92%. J48, NN and SVM exhibited 92.99% accuracy, then PART exhibits accuracy as 92.92% followed by Naï ve Bayes at 92.22%. In terms of classification time, Naï ve Bayes was fastest (0.01 sec), then J48 (0.03 sec), then PART (0.24 sec) and SVM (0.28 sec) while NN was slowest at 22.43 sec.