This study by Ooko and Oginga evaluated whether machine-learning models designed for edge deployment (utilization far from the datacenter) could enable early detection of chronic diseases in Africa, using diabetes as a proof-of-concept example. Using a Design Science Research framework, they compare Decision Trees, Support Vector Machines, Naïve Bayes, K-Nearest Neighbors, and an optimized neural network. The optimized neural network achieved the highest performance (accuracy 89%, precision 0.87, recall 0.90, F1-score 0.88, ROC-AUC 0.91), outperforming SVM (accuracy 77.2%), Decision Tree (75.3%), and Naïve Bayes (75.9%). Across models, glucose, BMI, and age were the most influential predictors, while blood pressure did not differ significantly between diabetic and non-diabetic groups (p=0.087). The optimized network met low-resource targets (~1ms latency within a 100ms budget using ~1kb RAM and ~15kb ROM). This indicates potential for edge deployment. The discussion notes performance consistent with or exceeding some global reports and emphasizes the need for future multi-site African validation, interpretability, and bias monitoring.