Efficient Normalized Conformal Prediction and Uncertainty Quantification for Anti-Cancer Drug Sensitivity Prediction with Deep Regression Forests
This work addresses uncertainty quantification for critical decision-making in drug response prediction, representing an incremental improvement in conformal prediction methods.
The paper tackled the problem of providing heteroskedastic uncertainty intervals for deep learning models in anti-cancer drug sensitivity prediction, showing that using deep regression forest variance improves efficiency and coverage in normalized inductive conformal prediction.
Deep learning models are being adopted and applied on various critical decision-making tasks, yet they are trained to provide point predictions without providing degrees of confidence. The trustworthiness of deep learning models can be increased if paired with uncertainty estimations. Conformal Prediction has emerged as a promising method to pair machine learning models with prediction intervals, allowing for a view of the model's uncertainty. However, popular uncertainty estimation methods for conformal prediction fail to provide heteroskedastic intervals that are equally accurate for all samples. In this paper, we propose a method to estimate the uncertainty of each sample by calculating the variance obtained from a Deep Regression Forest. We show that the deep regression forest variance improves the efficiency and coverage of normalized inductive conformal prediction on a drug response prediction task.