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

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.

The Significance of Data Abstraction Methods in Machine Learning Classification Processes for Critical Decision-Making

The applicability of widely adopted machine learning (ML) methods to classification is circumscribed by the imperatives of explicability and uncertainty, particularly evident in domains such as healthcare, behavioural sciences, and finances, wherein accountability assumes priority. Recently, Small and Incomplete Dataset Analyser (SaNDA) has been proposed to enhance the ability to perform classification in such domains, by developing a data abstraction protocol using a ROC curve-based method. This paper focuses on column-wise data transformations called abstractions, which are crucial for SaNDA's classification process and explores alternative abstractions protocols, such as constant binning and quantiles. The best-performing methods have been compared against Random Forest as a baseline for explainable methods. The results suggests that SaNDA can be a viable substitute for Random Forest when data is incomplete, even with minimal missing values. It consistently maintains high accuracy even when half of the dataset is missing, unlike Random Forest which experiences a significant decline in accuracy under similar conditions.