Modeling disease progression via multi-task learning

208 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Distributed Multi-Task Learning (2015, methodology): “It has been successfully exploited in, e.g., spam ﬁltering [Weinberger et al., 2009], web search [Chapelle et al., 2010], disease prediction [Zhou et al., 2013] and eQTL mapping [Kim and Xing, 2010].”
Interactive Multi-task Relationship Learning (2016, background): “For example, capturing temporal relatedness among multiple learning tasks allows researchers to build high performance disease progression models for Alzheimer’s disease by transfer knowledge among time points [36].”
Multi-Task Feature Interaction Learning (2016, methodology): “We follow the procedure of preprocessing mentioned in [39] and obtain 648 subjects and 305 MRI features.”
FORMULA: FactORized MUlti-task LeArning for task discovery in personalized medical models (2015, background): “In the study of Alzheimer’s disease (AD), for example, various predictive models are designed to study the courses of the disease and its progression patterns, to identity sensitive biomarkers that signal progression of the disease, and to build accurate models that identify high risk patients [25, ”
Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, background): “currently not used very often, but can improve prediction (Zhou et al., 2013).”