A deeper understanding of Multiple Sclerosis (MS) symptom progression is required for diagnostic accuracy and patient care. Remote monitoring through smartphones can provide continuous insights in the well-being of MS patients. This research aims to explore differences between MS and healthy typing behavior through collected typing behavior data (keystroke dynamics) on smartphones. The main contribution of this work was finding patterns within typing data that distinguish healthy typing behavior from MS with unlabeled time series data, except the diagnosis. A dataset of three combined studies was provided, which included 182 patients suffering from MS and 335 healthy subjects. An autoencoder was fitted on healthy samples to learn the temporal patterns in healthy typing behavior. Then, an anomaly detection method leveraged both the reconstruction loss and embeddings of these samples to determine whether MS samples deviated from healthy behavior. MS subjects were evaluated against healthy subjects through the ROC-AUC on both sample level and subject level. An initial hold out dataset of 20\% of the subjects was left out for validation. The overall performance was poor (AUC 0.6-0.8), because we aimed to find one general method for all MS subjects. Key limitations were the large variance in healthy typing behavior, relatively short window lengths, and difficulty in quantification of the training step of the autoencoder. Despite the difficulty of evaluating the performance of our suggested method, the described methods provide interesting monitoring possibilities for neurologists to enhance MS diagnosis. These monitoring possibilities could extend towards monitoring the effect of treatment, which is the first step towards personalised healthcare in MS.

Patient monitoring and clinical trial management generate continuous large volumes of healthcare data, causing the healthcare industry to be a data-intensive domain. Existing data storage techniques and access mechanics in the healthcare domain exhibit several challenges related to data security, patient privacy, and interoperability. Blockchain technology, together with the support from smart contracts, is considered a proper facilitator for secure and efficient healthcare data storage and sharing. Blockchain technology has unique features, such as decentralization, trustlessness, immutability, traceability, and transparency. Ongoing efforts show promising results considering blockchain technology to improve different aspects of healthcare data sharing and data management. However, all of these initiatives are still in the initial stages and lack technical details. This specifically pertains to the lack of investigation and evaluation of existing storage methods and techniques. Therefore, we will provide a comprehensive evaluation of different storage methods and techniques in ongoing efforts. We introduce a storage architecture for a possible blockchain-based healthcare system. The research proposals are evaluated considering the different storage methods and techniques. Additionally, we investigate the presence of six key requirements to provide a good storage solution. These requirements consist of data location, storage security, access mechanisms, third parties, storage purpose, operations and data integrity. None of the investigated systems meet all six requirements identified in this study. Therefore, we have proposed a storage architecture of our own.