Joseph A. Carcillo

DeepDiff-SHAP identifies subgroup-specific causal relationships in biomedical data using deep learning and SHAP, revealing clinically meaningful changes in feature interactions across patient subgroups.

This study uses proteomics to analyze immune responses in tracheal aspirate and plasma from critically ill children with viral lower respiratory tract infections, identifying diagnostic biomarkers and correlations with viral load and coinfections.

DeepEXPOKE uses deep learning with knockoff features to distinguish genetic and non-genetic exposure risks in sepsis and coronary heart disease, identifying metabolites and asthma as risk factors.

This paper introduces causalDeepVASE, a deep-learning method for causal inference that identifies both direct and indirect causal relationships in biological systems, outperforming existing methods in simulated and biological data.

The paper presents VIStEDD, a database of SARS-CoV-2 structural and evolutionary dynamics, highlighting conserved amino acids and variants in ACE2/SLC6A19/TMPRSS2 linked to pandemic susceptibility.