Public health surveillance systems in Rwanda are crucial for monitoring infectious diseases such as cholera and typhoid fever. However, these systems have room for improvement to enhance their effectiveness. A randomized field trial was conducted across three regions of Rwanda. Surveillance data were collected from healthcare facilities and analysed using statistical models to assess system performance. The analysis revealed an increase in the proportion of reported cases by 20% when utilising a novel combination of machine learning algorithms for early detection compared to traditional surveillance methods. This randomized field trial demonstrated that incorporating advanced analytics can significantly enhance the yield and accuracy of public health surveillance systems, particularly for infectious diseases. Health authorities in Rwanda should consider implementing these enhanced surveillance techniques to improve disease reporting and control efforts. public health surveillance, machine learning, yield improvement, randomized field trial Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.