AIM in Medical Informatics

A large amount of patient-related information is collected by healthcare operators in their everyday activities, which span over a wide spectrum of medical processes, such as wellness check-ups or examinations at healthcare hospitals or medical offices, just to name a few. For instance, when a patient undergoes a medical examination for the first time, the physician usually creates a patient file including his medical history, current treatments, medications, diagnosis, and other relevant information [1]. Considering that disease diagnosis is crucial for health condition monitoring, it is natural to envisage that such large amount of data can be profitably used to guide data-driven disease classification tasks in the quest for early and accurate diagnoses, taking care of the complex interactions among clinical, biological, and pathological variables. Indeed, with the aim of identifying the best services and treatments for the patients, recent advances in medicine have proposed various models for personalized, predictive, and preventive medicine that make use of electronic health records (EHRs) and high-dimensional omics data [2]. However, accessing and using EHRs and omics data can be rather challenging in practice, because they are heterogeneous and usually stored in different data formats.