Evaluating Advanced Machine Learning Models for Histopathological Diagnosis of Hansen Disease.

Abstract

Leprosy is a neglected infectious disease caused by Mycobacterium leprae and Mycobacterium lepromatosis and remains a public health challenge in tropical regions. Therefore, the development of technological tools such as machine learning (ML) offers an opportunity to innovate strategies for improving the diagnosis of this complex disease. To validate the utility of different ML models for the histopathological diagnosis of Hansen disease. An observational study was conducted where 55 H&E-stained tissue slides from leprosy patients and 51 healthy skin controls were analyzed using microphotographs captured at various magnifications. These images were categorized based on histopathological findings and processed using the Cross-Industry Standard Process for Data Mining methodology for designing and training ML models. Five types of ML models were evaluated using standard metrics such as accuracy, sensitivity, and specificity, emphasizing data normalization as a fundamental step in optimizing model performance. The artificial neural network (ANN) model demonstrated an accuracy of 70%, sensitivity of 74%, and specificity of 65%, demonstrating its ability to identify leprosy cases with moderate precision. The receiver operating characteristic curve of the ANN model showed an area under the curve of 0.71. Conversely, models such as decision trees, logistic regression, and random forests showed similar accuracy results but with slightly lower sensitivity, potentially indicating a higher risk of false negatives in detecting leprosy-positive cases. The ANN model emerges as a promising alternative for leprosy detection. However, further refinement of these models is necessary to enhance their adaptability across different clinical settings and participation in patient care.