Multiple Sclerosis Severity Estimation and Progression Prediction Based on Machine Learning Techniques.

The aim of the study is to address the Multiple Sclerosis (MS) severity estimation problem based on EDSS score and the prediction of the disease's progression with the application of Machine Learning (ML) approaches. Several ML techniques are implemented. The data are provided by the Neurology Clinic of the University Hospital of Ioannina and were collected in the framework of the ProMiSi project. The features recorded are grouped into: general demographic information, MS clinical related data, results of special tests, treatment, and comorbidities. The records from 30 patients are utilized and are recorded in three time points. The ML methods provided quite high results with 94.87% accuracy for the MS severity estimation and 83.33% for the disease's progression prediction.

Heart Failure diagnosis based on deep learning techniques.

The aim of the study is to address the heart failure (HF) diagnosis with the application of deep learning approaches. Seven deep learning architectures are implemented, where stacked Restricted Boltzman Machines (RBMs) and stacked Autoencoders (AEs) are used to pre-train Deep Belief Networks (DBN) and Deep Neural Networks (DNN). The data is provided by the University College Dublin and the 2nd Department of Cardiology from the University Hospital of Ioannina. The features recorded are grouped into: general demographic information, physical examination, classical cardiovascular risk factors, personal history of cardiovascular disease, symptoms, medications, echocardiographic features, laboratory findings, lifestyle/habits and other diseases. The total number of subjects utilized is 422. The deep learning methods provide quite high results with the Autoencoder plus DNN approach to demonstrate accuracy 91.71%, sensitivity 90.74%, specificity 92.31% and f-score 89.36%.