Public health surveillance systems in Kenya are crucial for monitoring infectious diseases such as malaria and tuberculosis (TB). However, their reliability varies across different regions. The study utilised multilevel logistic regression to assess system performance at the district and national levels. Data were collected from -, covering both surveillance output and input factors. Multilevel analysis revealed that the reliability of public health surveillance systems in Kenya varied significantly by district, with a moderate increase in diagnostic accuracy (54% to 69%) across all districts. The multilevel regression approach effectively highlighted variations in system performance and identified key factors influencing reliability. Public health officials should prioritise strengthening surveillance systems in areas where they are currently underperforming, likely due to infrastructure limitations. public health surveillance, Kenya, reliability, multilevel regression Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.