Related Experiment Video
Updated: May 9, 2026
03:37
Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
Published on: March 1, 2024
A systematic evaluation of explainable AI methods for high-dimensional transcriptome-based cancer survival prediction
Yiyi Zuo1, Shuting Yang2, Wenxue Zhao1
1Shenzhen Campus of Sun Yat-sen University, Molecular Cancer Research Center, School of Medicine, Shenzhen, China.
Frontiers in Physiology
|May 8, 2026
Summary
This study benchmarks Explainable Artificial Intelligence (XAI) methods for cancer survival prediction using transcriptomic data. DeepSHAP and Layer-wise Relevance Propagation (LRP) show promise, while Permutation Feature Importance (PFI) fails with high-dimensional data.
Area of Science:
- Computational Biology
- Genomics
- Artificial Intelligence
Background:
- Deep learning models for cancer survival prediction are often "black boxes," hindering clinical trust.
- Explainable Artificial Intelligence (XAI) offers potential solutions but lacks systematic evaluation for high-dimensional survival data.
Purpose of the Study:
- To systematically benchmark six representative XAI methods for transcriptome-based cancer survival prediction.
- To develop a unified framework for evaluating XAI methods on high-dimensional survival data.
- To identify the most reliable XAI tools for precision medicine applications.
Main Methods:
- Evaluated six XAI methods (gradient-based, propagation-based, perturbation-based) using a Self-Normalizing Neural Network (SNN) baseline.
- Analyzed 6,248 samples across 15 cancer types from The Cancer Genome Atlas (TCGA).
- Assessed methods based on prognostic factor enrichment, biological consistency, and explanation stability.
Main Results:
- DeepSHAP demonstrated superior performance, identifying significant prognostic factors with high explanation stability.
- Layer-wise Relevance Propagation (LRP) showed strong biological consistency, suitable for validating general cancer genes.
- Permutation Feature Importance (PFI) failed due to an inability to handle feature collinearity in high-dimensional transcriptomic data.
Conclusions:
- Explanation stability is a reliable indicator of XAI biological validity.
- DeepSHAP and LRP are promising XAI tools for cancer survival prediction.
- This study provides an empirical framework for selecting trustworthy XAI tools in precision medicine.
Related Concept Videos
01:21Cancer Survival Analysis
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
01:24Kaplan-Meier Approach
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
01:20Comparing the Survival Analysis of Two or More Groups
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and Cox...
01:19Survival Tree
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...
Building a Survival Tree
Constructing a survival tree begins...