SavedAdd your journal

Journals / Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi / 2026 / Cilt: 16 Sayı: 1

Stability-Bound Binary Rule Search: A General Workflow for Explainable Prediction on Binarized Clinical Data

Kararlılığa Bağlı İkili Kural Arama: Açıklanabilir Genel Bir İş Akışı İkilileştirilmiş Klinik Verilere İlişkin Tahmin

Mehmet Tahir Huyut(ERZİNCAN ÜNİVERSİTESİ, TIP FAKÜLTESİ)0000-0002-2564-991X
Andrei Velichko(Petrozavodsk State University)0000-0001-8760-316X
Pages
80–95
Publication Date
2026-03-01
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Overall, this stability-bound binary rule search workflow yields sparse, stable and clinically interpretable rule sets for cardiovascular risk stratification and chronic liver disease screening.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Explainable prediction is increasingly required in clinical decision support, especially when models must generalize across institutions.
📊
Key Findings & Data:We present a stability-bound binary rule search workflow that operates on fully binarized clinical data and expresses decisions as sparse, human-readable rules.
💡
Conclusion & Impact:Overall, this stability-bound binary rule search workflow yields sparse, stable and clinically interpretable rule sets for cardiovascular risk stratification and chronic liver disease screening.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Açıklanabilir Klinik Tahmin · İkili Kural Araması (BRS) · Kararlılık Sınır Kuralı Puanı (SBRS)

Abstract

Explainable prediction is increasingly required in clinical decision support, especially when models must generalize across institutions. We present a stability-bound binary rule search workflow that operates on fully binarized clinical data and expresses decisions as sparse, human-readable rules. Clinical variables are converted into 0/1 indicators using clinically meaningful thresholds, so that each rule corresponds to a binary mask over a small set of interpretable features. A Binary Rule Search (BRS) engine explores conjunctions of up to four predictors (k=1–4), and candidate rules are evaluated by the Matthews-correlation-coefficient (MCC) on development and validation splits. Robustness is summarized by the Stability-Bound-Rule-Score (SBRS), a geometric-style combination of the lower 95% confidence bounds of MCC in both splits. The workflow was applied to two open-access datasets: a heart attack dataset (303 patients) and a hepatitis C dataset (615 patients). In the heart attack data, a four-feature rule combining age 55–64 years, typical chest pain, absence of angiographically stenosed vessels (CA = 0) and a reversible thallium perfusion defect achieved MCC 0.71 and 0.73 in the development and validation sets, with SBRS = 1.59. In the hepatitis C data, rules built from elevated aspartate aminotransferase together with intermediate or high alkaline phosphatase and increased bilirubin reached MCC 0.75 and 0.84, with SBRS = 1.67. Because all predictors are binarized, the final rules can be displayed as compact binary mask plots or implemented as short checklists and look-up tables. Overall, this stability-bound binary rule search workflow yields sparse, stable and clinically interpretable rule sets for cardiovascular risk stratification and chronic liver disease screening.

Özet

Açıklanabilir tahmin, özellikle modellerin kurumlar arasında genelleştirilmesi gerektiğinde, klinik karar desteğinde giderek daha fazla ihtiyaç duyulmaktadır. Tamamen ikilileştirilmiş klinik veriler üzerinde çalışan ve kararları seyrek, insan tarafından okunabilir kurallar olarak ifade eden kararlılığa bağlı bir ikili kural arama iş akışı sunuyoruz. Klinik değişkenler, klinik olarak anlamlı eşikler kullanılarak 0/1 göstergelerine dönüştürülür, böylece her kural, yorumlanabilir özelliklerin küçük bir kümesi üzerinde ikili bir maskeye karşılık gelir. Bir İkili Kural Arama (BRS) motoru, dört öngörücünün (k=1"–" 4) birleşimlerini araştırır ve aday kurallar, geliştirme ve doğrulama bölümlerinde Matthews korelasyon katsayısı (MCC) ile değerlendirilir. Sağlamlık, her iki bölümdeki MCC'nin alt %95 güven sınırlarının geometrik bir kombinasyonu olan Kararlılığa Bağlı Kural Puanı (SBRS) ile özetlenir. İş akışı, iki açık erişimli veri kümesine uygulanmıştır: bir kalp krizi veri kümesi (303 hasta) ve bir hepatit C veri kümesi (615 hasta). Kalp krizi verilerinde, 55-64 yaş aralığını, tipik göğüs ağrısını, anjiyografik olarak stenozlu damarların yokluğunu (CA = 0) ve geri dönüşümlü talyum perfüzyon defektini birleştiren dört özellikli bir kural, geliştirme ve doğrulama setlerinde MCC 0,71 ve 0,73'e ulaşırken, SBRS = 1,59'a ulaştı. Hepatit C verilerinde, yüksek aspartat aminotransferaz ile birlikte orta veya yüksek alkalen fosfataz ve artmış bilirubinden oluşturulan kurallar, MCC 0,75 ve 0,84'e ulaşırken, SBRS = 1,67'ye ulaştı. Tüm öngörücüler ikili hale getirildiği için, nihai kurallar kompakt ikili maske çizimleri olarak gösterilebilir veya kısa kontrol listeleri ve arama tabloları olarak uygulanabilir. Genel olarak, bu kararlılığa bağlı ikili kural arama iş akışı, kardiyovasküler risk tabakalandırması ve kronik karaciğer hastalığı taraması için seyrek, kararlı ve klinik olarak yorumlanabilir kural setleri üretir.

🔖

Cite This Article

Huyut, M. T., Velichko, A. (2026). Stability-Bound Binary Rule Search: A General Workflow for Explainable Prediction on Binarized Clinical Data. Iğdır Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt: 16 Sayı: 1, 80–95. https://doi.org/10.21597/jist.1836750

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (24)

  1. Amsterdam, E. A., Wenger, N. K., Brindis, R. G., et al. (2014). 2014 AHA/ACC Guideline for the Management of Patients With Non–ST-Elevation Acute Coronary Syndromes. Circulation, 130(25), e344–e426. https://doi.org/10.1016/j.jacc.2014.09.017.
  2. Angelino, E., Larus-Stone, N., Alabi, D., et al. (2018). Learning Certifiably Optimal Rule Lists for Categorical Data. Journal of Machine Learning Research, 19, 1-43. https://www.jmlr.org/papers/v19/17-716.html.
  3. Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., & Elhadad, N. (2015). Intelligible models for healthcare. Proceedings of the 21st ACM SIGKDD, 1721–1730. https://doi.org/10.1145/2783258.2788613.
  4. Cui, Y., Wang, Y., Wang, Y., & Liu, J. (2018). Serum liver enzyme levels and hepatitis C virus infection: A systematic review and meta-analysis. Journal of Clinical Laboratory Analysis, 32(2), e22215. https://doi.org/10.1002/jcla.25127.
  5. Dilsizian, V., & Ficaro, E. P. (2011). Cardiac SPECT imaging: State-of-the-art and future directions. Journal of Nuclear Cardiology, 18(6), 1026–1043. https://doi.org/10.1007/s12350-011-9480-1.
  6. Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608. https://doi.org/10.48550/arXiv.1702.08608.
  7. European Association for the Study of the Liver (EASL). (2018). EASL clinical practice guidelines: Management of hepatitis C virus infection. Journal of Hepatology, 69(2), 461–511. https://doi.org/10.1016/j.jhep.2018.03.026.
  8. Foy, A. J., Liu, G., Davidson, W. R., et al. (2015). Comparative effectiveness of diagnostic testing strategies in emergency department patients with chest pain. BMJ, 351, h5447. https://doi.org/10.1001/jamainternmed.2014.7657.
  9. Giannini, E. G., Testa, R., & Savarino, V. (2005). Liver enzyme alteration: A guide for clinicians. Canadian Medical Association Journal, 172(3), 367–379. https://doi.org/10.1503/cmaj.1040752.
  10. Gulati, M., Levy, P. D., Mukherjee, D., et al. (2021). 2021 AHA/ACC Guideline for the Evaluation and Diagnosis of Chest Pain. Circulation, 144(22), e368–e454. https://doi.org/10.1161/CIR.0000000000001029.
  11. Harrell FE Jr. Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis. 2nd ed. Springer; New York, NY; 2015. https://doi.org/10.1007/978-3-319-19425-7.
  12. Holzinger, A., Biemann, C., Pattichis, C. S., & Kell, D. B. (2019). What do we need to build explainable AI systems for the medical domain? arXiv preprint arXiv:1712.09923. https://doi.org/10.48550/arXiv.1712.09923.
  13. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An introduction to statistical learning (2nd ed.). Springer. https://doi.org/10.1007/978-1-0716-1418-1.
  14. Lakkaraju, H., Bach, S. H., & Leskovec, J. (2016). Interpretable decision sets: A joint framework for description and prediction. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1675–1684). ACM. https://doi.org/10.1145/2939672.2939874.
  15. Lipton, Z. C. (2018). The mythos of model interpretability. Communications of the ACM, 61(10), 36–43. https://doi.org/10.1145/3233231.
  16. Molnar, C. (2022). Interpretable machine learning: A guide for making black box models explainable (2nd ed.). Lulu.com.
  17. Patel, M. R., et al. (2017). Low diagnostic yield of elective coronary angiography. New England Journal of Medicine, 362(10), 886–895. https://doi.org/10.1056/NEJMoa0907272.
  18. Pratt, D. S., & Kaplan, M. M. (2000). Evaluation of abnormal liver-enzyme results in asymptomatic patients. New England Journal of Medicine, 342(17), 1266–1271. https://doi.org/10.1056/NEJM200004273421707.
  19. Rockey, D. C., Caldwell, S. H., Goodman, Z. D., Nelson, R. C., & Smith, A. D. (2009). Liver biopsy. Hepatology, 49(3), 1017–1044. https://doi.org/10.1002/hep.22742.
  20. Rudin, C. (2019). Interpretable machine learning for high-stakes decisions. Nature Machine Intelligence, 1(5), 206–215. https://doi.org/10.1038/s42256-019-0048-x.
  21. Schuppan, D., & Afdhal, N. H. (2008). Liver cirrhosis. The Lancet, 371(9615), 838–851. https://doi.org/10.1016/S0140-6736(08)60383-9.
  22. Shortliffe, E. H., & Sepúlveda, M. J. (2018). Clinical decision support in the era of artificial intelligence. JAMA, 320(21), 2199–2200. https://doi.org/10.1001/jama.2018.17163.
  23. Steyerberg, E. W. (2019). Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating (2nd ed.). Springer. https://doi.org/10.1007/978-3-030-16399-0.
  24. Yu, B., & Kumbier, K. (2020). Veridical data science. Proceedings of the National Academy of Sciences, 117(8), 3920–3929. https://doi.org/10.1073/pnas.1901326117.