paper-with-me

홈 › Papers

SurvSHAP(t): Time-dependent explanations of machine learning survival models

2022-08-23 · Mateusz Krzyziński, Mikołaj Spytek, Hubert Baniecki, Przemysław Biecek

Machine and deep learning survival models demonstrate similar or even improved time-to-event prediction capabilities compared to classical statistical learning methods yet are too complex to be interpreted by humans. Several model-agnostic explanations are available to overcome this issue; however, none directly explain the survival function prediction. In this paper, we introduce SurvSHAP(t), the first time-dependent explanation that allows for interpreting survival black-box models. It is based on SHapley Additive exPlanations with solid theoretical foundations and a broad adoption among machine learning practitioners. The proposed methods aim to enhance precision diagnostics and support domain experts in making decisions. Experiments on synthetic and medical data confirm that SurvSHAP(t) can detect variables with a time-dependent effect, and its aggregation is a better determinant of the importance of variables for a prediction than SurvLIME. SurvSHAP(t) is model-agnostic and can be applied to all models with functional output. We provide an accessible implementation of time-dependent explanations in Python at http://github.com/MI2DataLab/survshap.

📄 PDF Abstract BibTeX arXiv:2208.11080

Code (1)

mi2datalab/survshap 공식 구현 pytorch

Tasks

PredictionTime-to-Event Prediction

Similar Papers 제목 키워드 기반

Functional Decomposition and Shapley Interactions for Interpreting Survival Models

2026-02-18 · Sophie Hanna Langbein, Hubert Baniecki, Fabian Fumagalli, Niklas Koenen 외 arxiv

Hazard and survival functions are natural, interpretable targets in time-to-event prediction, but their inherent non-additivity fundamentally limits standard additive explanation methods. We introduce Survival Functional…

Gradient-based Explanations for Deep Learning Survival Models

2025-02-07 · Sophie Hanna Langbein, Niklas Koenen, Marvin N. Wright

Deep learning survival models often outperform classical methods in time-to-event predictions, particularly in personalized medicine, but their "black box" nature hinders broader adoption. We propose a framework for grad…

Deep Learning

SurvBeX: An explanation method of the machine learning survival models based on the Beran estimator

2023-08-07 · Lev V. Utkin, Danila Y. Eremenko, Andrei V. Konstantinov

An explanation method called SurvBeX is proposed to interpret predictions of the machine learning survival black-box models. The main idea behind the method is to use the modified Beran estimator as the surrogate explana…

Interpretable machine learning for time-to-event prediction in medicine and healthcare

2023-03-17 · Hubert Baniecki, Bartlomiej Sobieski, Patryk Szatkowski, Przemyslaw Bombinski 외

Time-to-event prediction, e.g. cancer survival analysis or hospital length of stay, is a highly prominent machine learning task in medical and healthcare applications. However, only a few interpretable machine learning m…

Decision MakingFeature ImportanceInterpretable Machine LearningLength-of-Stay prediction+2

Deep Copula-Based Survival Analysis for Dependent Censoring with Identifiability Guarantees

2023-12-24 · Weijia Zhang, Chun Kai Ling, Xuanhui Zhang

Censoring is the central problem in survival analysis where either the time-to-event (for instance, death), or the time-tocensoring (such as loss of follow-up) is observed for each sample. The majority of existing machin…

Survival Analysis