Related Experiment Video
Updated: Jun 26, 2026
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
7.6K
Mitigating Algorithmic Bias in Cancer Site Classification Models
Abhishek Shivanna1, Adam Spannaus1, Jordan Tschida1
1Advanced Computing for Health Sciences, Oak Ridge National Laboratory, Oak Ridge, TN.
JCO Clinical Cancer Informatics
|March 11, 2026
Summary
This study found that artificial intelligence models for cancer diagnostics do not significantly encode racial bias in their predictions. Removing race-correlated data dimensions did not impact diagnostic accuracy, confirming model fairness.
Area of Science:
- Artificial Intelligence
- Oncology
- Medical Informatics
Background:
- Artificial intelligence (AI) enhances cancer diagnostics, but may perpetuate demographic biases.
- Deep learning models require rigorous bias evaluation for equitable healthcare.
Purpose of the Study:
- Quantify race information encoded in AI cancer diagnostic models.
- Assess performance changes after removing race-correlated data dimensions.
Main Methods:
- Trained a deep learning model on 3.5 million cancer pathology reports.
- Used hierarchical self-attention networks for document embeddings.
- Performed post-training pruning of race-correlated dimensions to assess impact on accuracy and fairness.
Main Results:
- Minimal overlap found between cancer site and race prediction features.
- Removing race-correlated dimensions negligibly affected diagnostic accuracy (0.07% loss).
- No significant demographic bias influenced clinical predictions.
Conclusions:
- AI embeddings from SEER data are effective for cancer site classification without significant bias.
- Post-training pruning serves as a viable audit for AI model fairness.
Related Concept Videos
02:43Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
02:43Mouse Models of Cancer Study
Mice have long served as models for studying human biology and pathology because of their phylogenetic and physiological similarity with humans. They are also easy to maintain and breed in the laboratory, and hence, many inbred strains are now available for research. Studies on mice have contributed immeasurably to our understanding of cancer biology.
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
01:17Clearance Models: Noncompartmental Models
Clearance is a pharmacokinetic parameter traditionally defined by compartment models, signifying the rate at which a drug is expelled from the body. However, a noncompartmental model offers an alternative method for assessing clearance, primarily employing empirical data obtained after administering a single drug dose.
The noncompartmental approach capitalizes on extensive sampling data, correlating the volume of distribution to systemic exposure and the administered dosage. This method enables...
The noncompartmental approach capitalizes on extensive sampling data, correlating the volume of distribution to systemic exposure and the administered dosage. This method enables...
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...