Representation Learning for Medical Data
Karol Antczak
Abstract
We propose a representation learning framework for medical diagnosis domain. It is based on heterogeneous network-based model of diagnostic data as well as modified metapath2vec algorithm for learning latent node representation. We compare the proposed algorithm with other representation learning methods in two practical case studies: symptom/disease classification and disease prediction. We observe a significant performance boost in these task resulting from learning representations of domain data in a form of heterogeneous network.
Related Papers
Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper2025-07-20Hear Your Code Fail, Voice-Assisted Debugging for Python2025-07-20Smart fault detection in satellite electrical power system2025-07-18Spectral Bellman Method: Unifying Representation and Exploration in RL2025-07-17Boosting Team Modeling through Tempo-Relational Representation Learning2025-07-17Demographic-aware fine-grained classification of pediatric wrist fractures2025-07-17Analysis of Image-and-Text Uncertainty Propagation in Multimodal Large Language Models with Cardiac MR-Based Applications2025-07-17Similarity-Guided Diffusion for Contrastive Sequential Recommendation2025-07-16