The paper “Learning dynamic Bayesian networks from time-dependent and time-independent data: Unraveling disease progression in Amyotrophic Lateral Sclerosis” co-authored by Sara C. Madeira has been published in Journal of Biomedical Informatics, a top-ranked journal (h5-index: 60).
In the paper the authors use dynamic Bayesian networks (DBNs), a machine learning model, that graphically represents the conditional dependencies among variables to profile the progression of amyotrophic lateral sclerosis (ALS) in patients from a Portuguese ALS dataset. Since the standard DBN framework only includes dynamic (time-dependent) variables, while most ALS datasets have dynamic and static (time-independent) observations, the authors propose the use of a sdtDBN framework, which learns optimal DBNs with static and dynamic variables. The results showed sdtDBNs are a promising predictive and descriptive tool, competitive with tools from state-of-the-art studies.
The article is available here.