Cassava is a crucial crop for food and nutritional security. It is an important source of carbohydrates in African countries. Cassava crops can sometimes be infected by leaf diseases, affecting overall production and reducing farmers' incomes. Early detection is therefore essential to reduce the impact of these diseases. Light reflections from leaves are known to convey information about plant health. In this study, healthy and inoculated cassava were detected from the reflections obtained from the leaves using a USB 4000 spectrometer with a spectral range of (350-1050) nm. Artificial neural networks (ANNs) and nearest neighbours (KNNs) were used with principal components and vegetation indices as input for classification. Various performance metrics, i.e. Precision, Recall, Accuracy and F1_score for KNN, Accuracy, RMSE and R2 for ANN were calculated to evaluate the different established models. Using the principal components (PC1, PC2) we obtained the best models with the ANNs with the following metrics (R2=0.9678; RMSE=0.0146; Accuracy =98.30%) for the variety IM 84 and (R2=0.9291; RMSE=0.0354 Accuracy=91.30%) for the Yacé variety. With vegetation indices, the best performing models were obtained with KNN whose input parameters are RatiodRE_703 ((Accuracy =92.50% and F1-score=0.9449) and fWBI ((Accuracy =90% and F1-score=0.9326) for Yacé and vog 3 (Accuracy=100% and F1-score=1), DD (Accuracy=100% and F1_score=1) and dNIRmin920_980 (Accuracy=95% and F1_score=0.9373) for the IM 84. Overall, the results showed that leaf spectral reflectance can be used successfully for the early detection of cassava bacterial blight.