mlsanityData to 7 Oct 2026

SurvNAM: The machine learning survival model explanation

arXiv 2104.08903 ↗First posted 18 Apr 2021cs.LG stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

A new modification of the Neural Additive Model (NAM) called SurvNAM and its modifications are proposed to explain predictions of the black-box machine learning survival model. The method is based on applying the original NAM to solving the explanation problem in the framework of survival analysis. The basic idea behind SurvNAM is to train the network by means of a specific expected loss function which takes into account peculiarities of the survival model predictions and is based on approximating the black-box model by the extension of the Cox proportional hazards model which uses the well-known Generalized Additive Model (GAM) in place of the simple linear relationship of covariates. The proposed method SurvNAM allows performing the local and global explanation. A set of examples around the explained example is randomly generated for the local explanation. The global explanation uses the whole training dataset. The proposed modifications of SurvNAM are based on using the Lasso-based regularization for functions from GAM and for a special representation of the GAM functions using their weighted linear and non-linear parts, which is implemented as a shortcut connection. A lot of numerical experiments illustrate the SurvNAM efficiency.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 48 of its 94 references that are in the map. First posted on arXiv 18 Apr 2021.

Builds on

48 of 94 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  6. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  7. 2018Attention-based Deep Multiple Instance Learningcited by 1,077
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  9. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  10. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  11. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  12. 2016DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Networkcited by 354
36 more
  1. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  2. 2019Counterfactual Visual Explanationscited by 312
  3. 2020A Survey on Neural Network Interpretabilitycited by 291
  4. 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 243
  5. 2018Techniques for Interpretable Machine Learningcited by 237
  6. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  7. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  8. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  9. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  10. 2020Principles and Practice of Explainable Machine Learningcited by 99
  11. 2018Grounding Visual Explanationscited by 92
  12. 2020GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactionscited by 82
  13. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  14. 2016Deep Survival Analysiscited by 60
  15. 2019DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systemscited by 59
  16. 2019Measurable Counterfactual Local Explanations for Any Classifiercited by 48
  17. 2020How Interpretable and Trustworthy are GAMs?cited by 44
  18. 2019ALIME: Autoencoder Based Approach for Local Interpretabilitycited by 41
  19. 2018Contrastive Explanations with Local Foil Treescited by 34
  20. 2020SurvLIME: A method for explaining machine learning survival modelscited by 34
  21. 2016Unbiased split variable selection for random survival forests using maximally selected rank statisticscited by 24
  22. 2019Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Alephcited by 23
  23. 2018Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP)cited by 19
  24. 2019Towards Understanding the Importance of Shortcut Connections in Residual Networkscited by 18
  25. 2019NormLime: A New Feature Importance Metric for Explaining Deep Neural Networkscited by 16
  26. 2019Multiple instance dense connected convolution neural network for aerial image scene classificationcited by 15
  27. 2015On the use of Harrell's C for clinical risk prediction via random survival forestscited by 14
  28. 2020Interpretable Machine Learning with an Ensemble of Gradient Boosting Machinescited by 14
  29. 2018A Deep Active Survival Analysis Approach for Precision Treatment Recommendations: Application of Prostate Cancercited by 12
  30. 2019Generalized Sparse Additive Modelscited by 11
  31. 2019Deep Learning for Survival Outcomescited by 7
  32. 2019c-Eval: A Unified Metric to Evaluate Feature-based Explanations via Perturbationcited by 7
  33. 2020Adaptive Explainable Neural Networks (AxNNs)cited by 7
  34. 2020A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov-Smirnov boundscited by 7
  35. 2016An Efficient Training Algorithm for Kernel Survival Support Vector Machinescited by 6
  36. 2019Interpreting Black Box Models via Hypothesis Testingcited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 5; 2024: 4; 2025: 4.

16 papers.

Sort:

  1. 2023Deep Learning for Survival Analysis: A Reviewcited by 75
  2. 2022SurvSHAP(t): Time-dependent explanations of machine learning survival modelscited by 24
  3. 2023Interpretable machine learning for time-to-event prediction in medicine and healthcarecited by 7
  4. 2022Extending the Neural Additive Model for Survival Analysis with EHR Datacited by 6
  5. 2023Interpretable Survival Analysis for Heart Failure Risk Predictioncited by 6
  6. 2024Interpretable Machine Learning for Survival Analysiscited by 4
  7. 2021Attention-like feature explanation for tabular datacited by 3
  8. 2023SurvBeX: An explanation method of the machine learning survival models based on the Beran estimatorcited by 3
  9. 2025Interpretable Clinical Classification with Kolmogorov-Arnold Networkscited by 3
  10. 2024Transparent Networks for Multivariate Time Seriescited by 2
  11. 2024CoxSE: Exploring the Potential of Self-Explaining Neural Networks with Cox Proportional Hazards Model for Survival Analysiscited by 1
  12. 2024DNAMite: Interpretable Calibrated Survival Analysis with Discretized Additive Modelscited by 1
4 more
  1. 2023SurvBeNIM: The Beran-Based Neural Importance Model for Explaining the Survival Modelscited by 0
  2. 2025CRISP-NAM: Competing Risks Interpretable Survival Prediction with Neural Additive Modelscited by 0
  3. 2025ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regressioncited by 0
  4. 2025Interpretable Fine-Gray Deep Survival Model for Competing Risks: Predicting Post-Discharge Foot Complications for Diabetic Patients in Ontariocited by 0