SurvLIME: A method for explaining machine learning survival models

Kovalev, Maxim S.; Utkin, Lev V.; Kasimov, Ernest M.

doi:10.1016/j.knosys.2020.106164

Cited by 76 publications

(39 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that the proposed method of the local uncertainty interpretation like methods SurvLIME [14] and SurvLIME-KS [15] is based on the idea of using the Cox model because this is a unique survival model providing a simple linear relationship between features and the model outcome. At the same time, UncSurvEx and methods SurvLIME and SurvLIME-KS solve quite different problems.…”

Section: A General Preliminary Scheme Of Uncsurvexmentioning

confidence: 99%

“…It should be noted that several explanation methods for machine learning survival models have been developed, for example, survival modifications [14], [15] of LIME [16], a counterfactual explanation method [17]. In contrast to many available explanation methods, the survival methods try to explain predications in the form of time-dependent functions, for example, the survival function (SF) or the cumulative hazard function (CHF).…”

mentioning

confidence: 99%

“…As a result, we propose a method for uncertainty interpretation of the black-box survival model predictions called UncSurvEx, which uses some ideas of the SurvLIME method [14]. One of the ideas behind UncSurvEx is to apply the Cox model to approximate the survival model at a local area around a test example because the Cox model assumes a linear combination of covariates which do not depend on time.…”

mentioning

confidence: 99%

“…Hence, the coefficients of the approximating Cox model are determined by minimizing the mean distance between uncertainty measures of the actual predictions corresponding to the synthetic examples and the approximating Cox model predictions. However, in contrast to the SurvLIME method [14] where the black-box model CHF is approximated by the Cox model CHF, the proposed UncSurvEx method aims to approximate the uncertainty measure of the actual prediction by the uncertainty measure of the Cox model prediction. The method finally aims to find features and their values which linearly contribute to the prediction uncertainty.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Uncertainty Interpretation of the Machine Learning Survival Model Predictions

Utkin¹,

Zaborovsky

Kovalev

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

A method for interpreting uncertainty of predictions provided by machine learning survival models is proposed. It is called UncSurvEx and aims to determine which features of an analyzed example lead to uncertain predictions of an explainable black-box survival model. One of the ideas behind the proposed method is to approximate the uncertainty measure of a local black-box survival model prediction by the uncertainty measure of the Cox proportional hazards model at the local area around a test example. The linear relationship between covariates and predictions in the corresponding Cox model allows determining quantitative impacts of covariates on the uncertainty measure. A specific certainty measure of the survival function, taking into account the most uncertain survival function, is introduced to interpret the prediction uncertainty. The L 2 -norm is used to compute the distance between survival functions. The method leads to an unconstrained non-convex optimization problem which is solved by means of the well-known Broyden-Fletcher-Goldfarb-Shanno algorithm. A lot of numerical experiments demonstrate the uncertainty interpretation method.INDEX TERMS explainable AI, survival analysis, uncertainty, censored data, the Cox model I. INTRODUCTION A. EXPLANATION OF SURVIVAL MODELS AND UNCERTAINTY INTERPRETATION

show abstract

Section: A General Preliminary Scheme Of Uncsurvexmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Uncertainty Interpretation of the Machine Learning Survival Model Predictions

Utkin¹,

Zaborovsky

Kovalev

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The main intuition of LIME is that the explanation may be derived locally from a set of synthetic instances generated randomly in the neighborhood of the instance to be explained such that every synthetic instance has a weight according to its proximity to the explained instance. Several modifications of LIME have been proposed due to success and simplicity of the method, for example, ALIME [12], NormLIME [13], DLIME [14], Anchor LIME [15], LIME-SUP [16], LIME-Aleph [17], SurvLIME [18]. Garreau and Luxburg [19] proposed a thorough theoretical analysis of LIME.…”

Section: Explanation Modelsmentioning

confidence: 99%

Explanation of Siamese Neural Networks for Weakly Supervised Learning

Utkin

Kovalev

Kasimov

2020

cai

View full text Add to dashboard Cite

A new method for explaining the Siamese neural network (SNN) as a black-box model for weakly supervised learning is proposed under condition that the output of every subnetwork of the SNN is a vector which is accessible. The main problem of the explanation is that the perturbation technique cannot be used directly for input instances because only their semantic similarity or dissimilarity is known. Moreover, there is no an "inverse" map between the SNN output vector and the corresponding input instance. Therefore, a special autoencoder is proposed, which takes into account the proximity of its hidden representation and the SNN outputs. Its pre-trained decoder part as well as the encoder are used to reconstruct original instances from the SNN perturbed output vectors. The important features of the explained instances are determined by averaging the corresponding changes of the reconstructed instances. Numerical experiments with synthetic data and with the well-known dataset MNIST illustrate the proposed method.

show abstract

Explainable machine learning predicts survival of retroperitoneal liposarcoma: A study based on theSEERdatabase and external validation in China

Wang,

Li,

Zeng

et al. 2024

Cancer Medicine

View full text Add to dashboard Cite

ObjectiveWe have developed explainable machine learning models to predict the overall survival (OS) of retroperitoneal liposarcoma (RLPS) patients. This approach aims to enhance the explainability and transparency of our modeling results.MethodsWe collected clinicopathological information of RLPS patients from The Surveillance, Epidemiology, and End Results (SEER) database and allocated them into training and validation sets with a 7:3 ratio. Simultaneously, we obtained an external validation cohort from The First Affiliated Hospital of Naval Medical University (Shanghai, China). We performed LASSO regression and multivariate Cox proportional hazards analysis to identify relevant risk factors, which were then combined to develop six machine learning (ML) models: Cox proportional hazards model (Coxph), random survival forest (RSF), ranger, gradient boosting with component‐wise linear models (GBM), decision trees, and boosting trees. The predictive performance of these ML models was evaluated using the concordance index (C‐index), the integrated cumulative/dynamic area under the curve (AUC), and the integrated Brier score, as well as the Cox–Snell residual plot. We also used time‐dependent variable importance, analysis of partial dependence survival plots, and the generation of aggregated survival SHapley Additive exPlanations (SurvSHAP) plots to provide a global explanation of the optimal model. Additionally, SurvSHAP (t) and survival local interpretable model‐agnostic explanations (SurvLIME) plots were used to provide a local explanation of the optimal model.ResultsThe final ML models are consisted of six factors: patient's age, gender, marital status, surgical history, as well as tumor's histopathological classification, histological grade, and SEER stage. Our prognostic model exhibits significant discriminative ability, particularly with the ranger model performing optimally. In the training set, validation set, and external validation set, the AUC for 1, 3, and 5 year OS are all above 0.83, and the integrated Brier scores are consistently below 0.15. The explainability analysis of the ranger model also indicates that histological grade, histopathological classification, and age are the most influential factors in predicting OS.ConclusionsThe ranger ML prognostic model exhibits optimal performance and can be utilized to predict the OS of RLPS patients, offering valuable and crucial references for clinical physicians to make informed decisions in advance.

show abstract

SurvLIME: A method for explaining machine learning survival models

Cited by 76 publications

References 24 publications

Uncertainty Interpretation of the Machine Learning Survival Model Predictions

Uncertainty Interpretation of the Machine Learning Survival Model Predictions

Explanation of Siamese Neural Networks for Weakly Supervised Learning

Explainable machine learning predicts survival of retroperitoneal liposarcoma: A study based on theSEERdatabase and external validation in China

Contact Info

Product

Resources

About