Computational Phenotype Discovery via Probabilistic Independence

2019/07/25 by Thomas A. Lasko, Lasko, Thomas A., Diego Mesa +1 · 2 citations
Computer Science · Biochemistry, Genetics and Molecular Biology · Health Professions · #Machine Learning in Healthcare #Biomedical Text Mining and Ontologies #Artificial Intelligence in Healthcare

paper · pdf · doi:10.48550/arxiv.1907.11051

Abstract

Computational Phenotype Discovery research has taken various pragmatic approaches to disentangling phenotypes from the episodic observations in Electronic Health Records. In this work, we use transformation into continuous, longitudinal curves to abstract away the sparse irregularity of the data, and we introduce probabilistic independence as a guiding principle for disentangling phenotypes into patterns that may more closely match true pathophysiologic mechanisms. We use the identification of liver disease patterns that presage development of Hepatocellular Carcinoma as a proof-of-concept demonstration.

Cited by

• A tutorial on discovering and quantifying the effect of latent causal sources of multimodal EHR data
• Self-supervised learning of imaging and clinical signatures using a multimodal joint-embedding predictive architecture

Related

• Unsupervised Learning for Computational Phenotyping
• Phenotype Inference with Semi-Supervised Mixed Membership Models
• Unsupervised Discovery of Clinical Disease Signatures Using Probabilistic Independence
• Phenotyping with Positive Unlabelled Learning for Genome-Wide Association Studies
• Phenotype Detection in Real World Data via Online MixEHR Algorithm