Biomedical AI · Published

Interpretable heart disease risk prediction via FCA-constrained logistic regression

Arman Salehi, Ashkan Heydarian, Hamid Reza Goudarzi, Zahra Farzin Rad

Venue
Health Informatics Journal
Published
2026-04-29
DOI
10.1177/14604582261444612
Citations
No citations indexed
Google Scholar · 2026-07-26
Last verified
2026-07-26

Research question

Can hierarchical co-occurrence structure be built into logistic regression while keeping the resulting risk model inspectable?

Condensed abstract

Formal Concept Analysis extracts closed itemsets from binarized health indicators. A closure penalty then encourages coefficients belonging to the same concepts to remain coherent while preserving a linear prediction function.

Key contribution

An interpretability-by-design objective that embeds FCA-derived structure directly into logistic-regression training, evaluated against linear and tree-ensemble baselines on a large survey-derived cohort.

My contribution

The published contribution statement credits Arman Salehi with conceptualization, methodology, coding, formal analysis, and writing the original draft.

Method overview

Closed itemsets are extracted from binarized indicators. The model adds a weighted within-concept coefficient-variance term to logistic loss; closure strength and minimum support are selected through cross-validation.

Interactive method figure

Structure becomes a training constraint

Illustrative Formal Concept Analysis latticeA shared concept connects three health indicators whose coefficients are encouraged to remain coherent.shared conceptHighBPDiabetesStrokeclosure structure informs the penalty

Illustrative coefficient coherence

β10.66
β20.44
β30.30

Higher is better.

FCA model0.7094
Logistic regression0.2492
Random forest0.3257
Gradient boosting0.5055
Coefficient movement is illustrative, not fitted patient-level coefficients. The comparison uses values reported in the paper’s held-out test table.

Dataset and evaluation

Data

Heart Disease Health Indicators derived from the 2015 Behavioral Risk Factor Surveillance System, with approximately 380,000 complete survey records after preprocessing.

Protocol

An 80/20 stratified split was used. Five-fold cross-validation within the training data selected closure strength and minimum support; the held-out test set was evaluated with discrimination, classification, imbalance-sensitive, and calibration metrics.

Main results

The held-out test set results were accuracy 0.906, AUC 0.810, precision 0.709, recall 0.544, F1 0.556, PR-AUC 0.265, and Brier score 0.078.

Accuracy0.906
AUC0.810
Precision0.709
F10.556
PR-AUC0.265
Brier score0.078Lower is better

Baseline comparison

At the reported threshold, the FCA-constrained model had the highest precision and F1 among the listed baselines. Logistic regression and Gradient Boosting had higher AUC; Gradient Boosting also had the lower Brier score (0.0715 versus 0.078).

Limitations and failure modes

  • BRFSS variables are self-reported, observational, and not a prospective clinical cohort.
  • Binarization improves inspectability but discards information.
  • The evaluation uses a single U.S. survey-derived dataset.
  • External, subgroup, prospective, and workflow validation remain necessary before clinical use.

Reproducibility resources

The paper-associated computational material is available as a versioned Zenodo artifact. The source data are described at Heart Disease Health Indicators (BRFSS 2015).

Verification sources

Cite this work

Download .bibDownload .ris

Arman Salehi, Ashkan Heydarian, Hamid Reza Goudarzi, Zahra Farzin Rad (2026). Interpretable heart disease risk prediction via FCA-constrained logistic regression. Health Informatics Journal. https://doi.org/10.1177/14604582261444612

BibTeX
@article{salehi2026fca,
  title = {Interpretable heart disease risk prediction via FCA-constrained logistic regression},
  author = {Arman Salehi and Ashkan Heydarian and Hamid Reza Goudarzi and Zahra Farzin Rad},
  year = {2026},
  doi = {10.1177/14604582261444612},
  journal = {Health Informatics Journal},
  publisher = {SAGE Publications}
}

Publication record last verified 2026-07-26.