A feature-stable and explainable machine learning framework for trustworthy decision-making under incomplete clinical data

TL;DR

This paper introduces CACTUS, an explainable machine learning framework that enhances feature stability and trustworthiness in clinical data analysis, especially under conditions of data incompleteness and heterogeneity.

Contribution

CACTUS uniquely combines feature abstraction, interpretability, and stability analysis to improve robustness and trustworthiness of models on small, incomplete biomedical datasets.

Findings

CACTUS achieves high predictive accuracy with stable feature importance under missing data.

Feature stability correlates with trustworthiness and complements traditional performance metrics.

Demonstrated effectiveness on a real-world bladder cancer dataset.

Abstract

Machine learning models are increasingly applied to biomedical data, yet their adoption in high stakes domains remains limited by poor robustness, limited interpretability, and instability of learned features under realistic data perturbations, such as missingness. In particular, models that achieve high predictive performance may still fail to inspire trust if their key features fluctuate when data completeness changes, undermining reproducibility and downstream decision-making. Here, we present CACTUS (Comprehensive Abstraction and Classification Tool for Uncovering Structures), an explainable machine learning framework explicitly designed to address these challenges in small, heterogeneous, and incomplete clinical datasets. CACTUS integrates feature abstraction, interpretable classification, and systematic feature stability analysis to quantify how consistently informative features are preserved as data quality degrades. Using a real-world haematuria cohort comprising 568 patients evaluated for bladder cancer, we benchmark CACTUS against widely used machine learning approaches, including random forests and gradient boosting methods, under controlled levels of randomly introduced missing data. We demonstrate that CACTUS achieves competitive or superior predictive performance while maintaining markedly higher stability of top-ranked features as missingness increases, including in sex-stratified analyses. Our results show that feature stability provides information complementary to conventional performance metrics and is essential for assessing the trustworthiness of machine learning models applied to biomedical data. By explicitly quantifying robustness to missing data and prioritising interpretable, stable features, CACTUS offers a generalizable framework for trustworthy data-driven decision support.