The increasing amount of data has allowed researchers to talk about the so-called “big data” and this is particularly true in the healthcare sector, where data are currently produced in several ways. They can be acquired from clinical electronic records that are methodically recorded in health facilities, from sensors that are widely employed for measuring physiological parameters, and from laboratories. Indeed, there are several applications of gait analysis, postural control, and rehabilitation engineering, particularly with elderly patients, and people affected by neurological diseases such as strokes, Parkinson’s disease, Alzheimer's, and Huntington’s disease.

New practices have been used for extracting quantitative parameters from medical images: radiomics allows researchers to acquire quantitative parameters describing images. Converting a set of images from computed tomography (CT), magnetic resonance imaging (MRI), or positron emission tomography (PET) to a set of numerical variables has been tested, especially in oncology, however, there is hope that this can also be applied in other medical specialties. Increasing data, growth of computational and mathematical models, availability of innovative machine learning, data mining techniques, and tools indicate the potential applications in healthcare. Using such methods is important to exploit the big heterogeneous data and help both clinicians and physicians in producing diagnosis, and prognosis where they can be harder. Moreover, these techniques can help examine pathologies with the use of mathematical and engineering approaches (e.g., simulation models, algorithms for the analysis of biomedical data, and signals). Other potential applications of these methods in medical specialties include fetal monitoring for distinguishing healthy and pathological fetuses, neurology and neuroscience for the above-mentioned pathologies, rehabilitation engineering, oncology for detecting adenomas or predicting tumor grade and nodal status, cardiology for the detection of coronary artery disease, mortality risk, etc.

The aim of this Special Issue is to solicit original research articles in particular focusing on the application of computational models, machine learning, and data mining algorithms dealing with biomedical problems, and model healthcare data rather than theoretical contributions. Review articles describing the recent methodological advances related to one of the different medical specialties are also welcome.

Potential topics include but are not limited to the following:

• Analysing medical images
• Analysing biomedical signals for classification, and regression studies
• Techniques in machine learning and modelling to help clinicians, and physicians with prognosis
• Tackling the issue of unbalanced datasets in the medical framework
• Radiomic studies in clinical settings
• Exploiting clinical electronic records to improve diagnosis through machine learning, and computational models
• Comparing biomedical technologies through machine learning, and mathematical models
• Speech, and audio processing in diseases
• Extracting features from wearable sensors, and exploiting their potential through machine learning, and modelling
• Using gait analysis, and machine learning to overcome movement disorders