Michael Hoffmeister

This paper introduces hiPRS, a novel polygenic risk score method that models high-order SNP interactions, demonstrating superior performance in simulation studies and real data applications.

This study improves polygenic risk scores for colorectal cancer by combining Asian and European ancestry data, enhancing risk prediction across diverse racial and ethnic groups.

This paper demonstrates swarm learning for training AI models on decentralized histopathology data to predict molecular features in colorectal cancer.

This study benchmarks AI methods for end-to-end computational pathology, showing ResNet and ViT outperform MIL and CLAM in mutation prediction but not in tumor subtyping.

This study identifies 13 new genetic loci specific to proximal or distal colorectal cancer subtypes, revealing partly distinct genetic architectures for these tumor locations.

This paper develops a deep learning method to predict genetic alterations from histological images across multiple cancer types.

This study assesses polygenicity and risk prediction using common variants across 14 cancers, finding varying numbers of susceptibility variants and risk score effectiveness.

This study uses Mendelian randomization to show that higher physical activity levels are associated with lower risks of breast and colorectal cancer.