Interpretable Multiple Myeloma Prognosis with Observational Medical Outcomes Partnership Data
This work addresses the need for interpretable ML models in clinical decision-making for multiple myeloma prognosis, though it is incremental as it builds on existing interpretability methods.
The authors tackled the problem of opaque machine learning models in healthcare by proposing two novel regularization techniques to ensure interpretability for predicting five-year survival in multiple myeloma patients, achieving an accuracy of up to 0.721 on a test set.
Machine learning (ML) promises better clinical decision-making, yet opaque model behavior limits the adoption in healthcare. We propose two novel regularization techniques for ensuring the interpretability of ML models trained on real-world data. In particular, we consider the prediction of five-year survival for multiple myeloma patients using clinical data from Helsinki University Hospital. To ensure the interpretability of the trained models, we use two alternative constructions for a penalty term used for regularization. The first one penalizes deviations from the predictions obtained from an interpretable logistic regression method with two manually chosen features. The second construction requires consistency of model predictions with the revised international staging system (R-ISS). We verify the usefulness of the proposed regularization techniques in numerical experiments using data from 812 patients. They achieve an accuracy up to 0.721 on a test set and SHAP values show that the models rely on the selected important features.