Paul Monsarrat

mosna analyzes spatial omics data to identify cell interactions predictive of immunotherapy response and survival in cancer.

This paper introduces a hybrid calibration framework that integrates expert knowledge into multi-objective optimization for biological model parameter estimation, showing improved biological relevance and reduced overfitting.

The paper introduces a visualization method to analyze SHAP feature interactions in ML models for biomedical applications, revealing hidden patterns of explainability.

This paper introduces discernibility as a metric to evaluate the clarity of explanations in machine learning models for medicine, finding that the dcor metric best captures user-perceived relationships between data and explanations.