# Causal Explainability of Machine Learning in Heart Failure Prediction from Electronic Health Records

arXiv: https://arxiv.org/abs/2506.03068 · HTML: https://mlsanity.com/paper/2506.03068/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Learning Sparse Nonparametric DAGs](https://mlsanity.com/paper/1909.13189/) (2019)
- [Causal Inference in the Presence of Latent Variables and Selection Bias](https://mlsanity.com/paper/1302.4983/) (2013)
- [A Survey on Causal Discovery: Theory and Practice](https://mlsanity.com/paper/2305.10032/) (2023)
- [gCastle: A Python Toolbox for Causal Discovery](https://mlsanity.com/paper/2111.15155/) (2021)
- [Federated Causality Learning with Explainable Adaptive Optimization](https://mlsanity.com/paper/2312.05540/) (2023)
- [Recent Advances in Predictive Modeling with Electronic Health Records](https://mlsanity.com/paper/2402.01077/) (2024)
- [Nonlinear Causal Discovery with Confounders](https://mlsanity.com/paper/2302.03178/) (2023)
- [Applying Large Language Models for Causal Structure Learning in Non Small Cell Lung Cancer](https://mlsanity.com/paper/2311.07191/) (2023)
- [A direct method for estimating a causal ordering in a linear non-Gaussian acyclic model](https://mlsanity.com/paper/1408.2038/) (2014)
- [MIxBN: library for learning Bayesian networks from mixed data](https://mlsanity.com/paper/2106.13194/) (2021)
- [A novel method for Causal Structure Discovery from EHR data, a demonstration on type-2 diabetes mellitus](https://mlsanity.com/paper/2011.05489/) (2020)
- [Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine](https://mlsanity.com/paper/2110.07785/) (2021)
- [Learning causal graphs using variable grouping according to ancestral relationship](https://mlsanity.com/paper/2403.14125/) (2024)
- [Greedy equivalence search for nonparametric graphical models](https://mlsanity.com/paper/2406.17228/) (2024)

## Built on by (most cited first, 2 of 2)

- [Ensemble of Unsupervised Deep Learning for Clustering Imbalanced Tabular Data](https://mlsanity.com/paper/2608.00346/) (2026)
- [From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis](https://mlsanity.com/paper/2609.32514/) (2026)

## Abstract (arXiv)

The importance of clinical variables in the prognosis of the disease is explained using statistical correlation or machine learning (ML). However, the predictive importance of these variables may not represent their causal relationships with diseases. This paper uses clinical variables from a heart failure (HF) patient cohort to investigate the causal explainability of important variables obtained in statistical and ML contexts. Due to inherent regression modeling, popular causal discovery methods strictly assume that the cause and effect variables are numerical and continuous. This paper proposes a new computational framework to enable causal structure discovery (CSD) and score the causal strength of mixed-type (categorical, numerical, binary) clinical variables for binary disease outcomes. In HF classification, we investigate the association between the importance rank order of three feature types: correlated features, features important for ML predictions, and causal features. Our results demonstrate that CSD modeling for nonlinear causal relationships is more meaningful than its linear counterparts. Feature importance obtained from nonlinear classifiers (e.g., gradient-boosting trees) strongly correlates with the causal strength of variables without differentiating cause and effect variables. Correlated variables can be causal for HF, but they are rarely identified as effect variables. These results can be used to add the causal explanation of variables important for ML-based prediction modeling.