Risk Assessment of Lymph Node Metastases in Endometrial Cancer Patients: A Causal Approach

TL;DR

This paper develops a causal Bayesian network approach to assess lymph node metastasis risk in endometrial cancer, addressing data quality issues and bias, to improve clinical risk prediction.

Contribution

It introduces a bootstrap-based causal discovery algorithm with context variables to mitigate bias and handle missing data in observational clinical datasets.

Findings

Causal Bayesian network effectively models risk factors.

Bootstrap resampling improves causal discovery reliability.

Analysis highlights limitations due to missing-not-at-random data.

Abstract

Assessing the pre-operative risk of lymph node metastases in endometrial cancer patients is a complex and challenging task. In principle, machine learning and deep learning models are flexible and expressive enough to capture the dynamics of clinical risk assessment. However, in this setting we are limited to observational data with quality issues, missing values, small sample size and high dimensionality: we cannot reliably learn such models from limited observational data with these sources of bias. Instead, we choose to learn a causal Bayesian network to mitigate the issues above and to leverage the prior knowledge on endometrial cancer available from clinicians and physicians. We introduce a causal discovery algorithm for causal Bayesian networks based on bootstrap resampling, as opposed to the single imputation used in related works. Moreover, we include a context variable to evaluate whether selection bias results in learning spurious associations. Finally, we discuss the strengths and limitations of our findings in light of the presence of missing data that may be missing-not-at-random, which is common in real-world clinical settings.