AIM in Medical Informatics

Providing accurate diagnoses of diseases and maximizing the effectiveness of treatments requires, in general, complex analyses of many clinical, omics, and pathological data. Making a fruitful use of such data is not straightforward, as they are usually stored in electronic health records (EHRs) that need to be properly handled and processed in order to successfully perform medical diagnosis. In recent years, machine learning and deep learning techniques have emerged as powerful tools to perform specific disease detection and classification using EHRs data, thus providing significant clinical decision support. However, approaches based on such techniques suffer from the lack of proper means for interpreting the choices made by the models, especially in the case of deep-learning ones. In this chapter, we describe clinical and omics data along with the popular processing operations performed to improve the medical analyses. We present the most common used algorithms in automatic medical diagnosis and the advance in explainability of machine learning-based systems to validate healthcare decision-making.