Contact: Nuno Silva ( nuno.asilva@hospitaldaluz.pt )
 
Markov models and electronic health records: probabilistic modelling in healthcare

In recent years, there has been a clear interest on the representation of patients through their Electronic Health Records (EHRs). This representation is, in fact, the first step to use these data for several research and clinical predictive tasks. Machine Learning (ML) can be the technology to unlock the full potential of these data, by discovering hidden relationships in complex problems, such as what factors determine new interactions with the hospital. The goal of this project is to use Hidden Markov Models (HMM) to model the sequence of interactions of patients with Hospital da Luz, based on their EHRs. The work includes data acquisition, data processing, model training and data visualization. It will take place in a hybrid environment, with data acquisition performed at Hospital da Luz Learning Health and processing at home or onsite (whatever is more convenient to the student).