Machine Learning Approaches in Medical Data Processing: A Proposal for an Intelligent Stroke Diagnosis System

Öz

This study proposes an intelligent diagnostic system based on machine learning and deep learning for stroke detection. The use of artificial intelligence (AI) in healthcare is increasing alongside big data analytics and digitalization. Stroke, a prevalent neurological disease worldwide, can have its mortality and disability rates significantly reduced through early diagnosis. The study utilizes the “Stroke Prediction Dataset” from Kaggle, encompassing 4909 individuals. This dataset includes 12 input features such as age, gender, hypertension, heart disease, and lifestyle factors, along with one output feature indicating stroke status. Data preprocessing steps involved filling missing values with the mean, converting categorical data to numerical format using One-Hot Encoding, applying Min-Max Scaling, and addressing class imbalance with SMOTE. Fifteen different machine learning and deep learning algorithms (e.g., Random Forest, Voting Classifier, Histogram Gradient Boosting, SVM, MLP) were evaluated, with performance measured using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The Voting Classifier achieved the highest performance with 98.5% accuracy and an AUC of 0.99. Tree-based models like Random Forest and Histogram Gradient Boosting also demonstrated high accuracy. Hyperparameter optimization was performed using GridSearchCV and RandomizedSearchCV, while early stopping, regularization, and dropout techniques were applied to prevent overfitting. The findings highlight the superiority of ensemble learning methods over traditional approaches in stroke diagnosis. The study underscores the importance of integrating AI-based clinical decision support systems into healthcare and suggests that model performance could be further enhanced with larger datasets in the future.

Anahtar Kelimeler

• Stroke diagnosis
• Machine learning
• Deep learning
• Ensemble learning
• Clinical decision support systems

Destekleyen Kurum

TÜBİTAK

Etik Beyan

There is no need for an ethics committee approval in the prepared article. Also, there is no conflict of interest with any person/institution in the proposed article.

Teşekkür

Our research was funded by the Scientific and Technological Research Council of Turkey (TÜBİTAK) under the 2209-A University Students Research Projects Support Program with project number 1919B012323732 This support provided a fundamental contribution to the execution of our project and is gratefully acknowledged.

Medikal Veri İşlemede Makine Öğrenme Yaklaşımları: Felç için Akıllı Teşhis Sistemi Önerisi

Öz

Bu çalışma, felç teşhisi için makine öğrenmesi ve derin öğrenme tabanlı bir akıllı teşhis sistemi önermektedir. Sağlık sektöründe yapay zekânın (AI) kullanımı, büyük veri analitiği ve dijitalleşme ile birlikte artmaktadır. Felç, dünya genelinde yaygın bir nörolojik hastalık olup erken teşhisle ölüm ve sakatlık oranları önemli ölçüde azaltılabilir. Çalışmada, Kaggle platformundaki 4909 bireyi kapsayan “Felç Tahmin Veri Seti” kullanılmıştır. Bu veri seti, yaş, cinsiyet, hipertansiyon, kalp hastalığı, yaşam tarzı gibi 12 giriş özelliği ve felç durumunu gösteren bir çıkış özelliği içermektedir. Veri ön işleme adımları olarak eksik verilerin ortalama ile doldurulması, kategorik verilerin One-Hot Encoding ile sayısallaştırılması, Min-Max Ölçeklendirme ve SMOTE ile sınıf dengesizliği çözülmüştür. Çalışmada, 15 farklı makine öğrenmesi ve derin öğrenme algoritması (Random Forest, Voting Classifier, Histogram Gradient Boosting, SVM, MLP vb.) değerlendirilmiş; performansları doğruluk, hassasiyet, geri çağırma, F1-skoru ve ROC-AUC metrikleriyle ölçülmüştür. Voting Classifier, %98,5 doğruluk ve 0,99 AUC ile en yüksek performansı göstermiştir. Random Forest ve Histogram Gradient Boosting gibi ağaç tabanlı modeller de yüksek doğruluk oranlarıyla dikkat çekmiştir. Hiperparametre optimizasyonu için GridSearchCV ve RandomizedSearchCV kullanılmış, aşırı öğrenmeyi önlemek için erken durdurma, düzenlileştirme ve dropout teknikleri uygulanmıştır. Bulgular, topluluk öğrenme yöntemlerinin felç teşhisinde geleneksel yöntemlere üstünlük sağladığını göstermektedir. Çalışma, yapay zeka tabanlı klinik karar destek sistemlerinin sağlık sektörüne entegrasyonunun önemini vurgulamakta ve gelecekte daha büyük veri setleriyle model performansının artırılabileceğini önermektedir.

Anahtar Kelimeler

• Felç teşhisi
• Makine öğrenmesi
• Derin öğrenme
• Topluluk öğrenmesi
• Klinik karar destek sistemleri

Destekleyen Kurum

TÜBİTAK

Etik Beyan

Hazırlanan makalede etik kurul onayına gerek yoktur. Ayrıca önerilen makalede herhangi bir kişi/kurumla çıkar çatışması yoktur.

Teşekkür

Araştırmamız, Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (TÜBİTAK) tarafından 2209-A Üniversite Öğrencileri Araştırma Projeleri Destek Programı kapsamında, proje numarası 1919B012323732 ile finanse edilmiştir. Bu destek, projemizin yürütülmesine temel bir katkı sağlamıştır, tüm TÜBİTAK ekibine teşekkür ederiz.

Kaynakça

1. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
2. A. Esteva et al., “A guide to deep learning in healthcare,” Nat. Med., vol. 25, no. 1, pp. 24–29, Jan. 2019.
3. E. J. Topol, “High-performance medicine: the convergence of human and artificial intelligence,” Nat. Med., vol. 25, no. 1, pp. 44–56, Jan. 2019.
4. M. Elhaddad, S. Hamam, M. Elhaddad, and S. Hamam, “AI-Driven Clinical Decision Support Systems: An Ongoing Pursuit of Potential,” Cureus, vol. 16, no. 4, Apr. 2024.
5. World Health Organization, World Health Statistics 2023, vol. 69, no. 9, 2023.
6. V. L. Feigin et al., “Global, regional, and national burden of stroke and its risk factors, 1990–2019: A systematic analysis for the Global Burden of Disease Study 2019,” Lancet Neurol., vol. 20, no. 10, pp. 1–26, Oct. 2021.
7. E. J. Benjamin et al., “Heart disease and stroke statistics – 2018 update: A report from the American Heart Association,” Circulation, vol. 137, no. 12, pp. e67–e492, Mar. 2018.
8. G. Litjens et al., “Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis,” Sci. Rep., vol. 6, May 2016.

9. M. Wang, G. Yang, K. Luo, Y. Li, and L. He, “Early stroke behavior detection based on improved video masked autoencoders for potential patients,” Complex Intell. Syst., vol. 11, no. 1, p. 30, 2025.
10. I. Goodfellow, Y. Bengio, and A. Courville, “Deep learning,” Genet. Program. Evolvable Mach., vol. 19, no. 1–2, pp. 305–307, 2018, [Online]. Available: https://books.google.com/books/about/Deep_Learning.html?hl=tr&id=Np9SDQAAQBAJ
11. G. Thakre, R. Raut, C. Puri, and P. Verma, “A Hybrid Deep Learning Approach for Improved Detection and Prediction of Brain Stroke,” Appl. Sci., vol. 15, no. 9, p. 4639, 2025.
12. H. A. Ateş, “Detection of Stroke (Cerebrovascular Accident) Using Machine Learning Methods,” Bitlis Eren Üniversitesi Fen Bilim. Derg., pp. 242–246, 2023.
13. Ö. Oğuz, “Makine Öğrenmesi Yöntemlerinin Felç Riskinin Belirlenmesinde Performansı: Karşılaştırmalı bir çalışma,” pp. 274–287, 2021.
14. R. A. J. Alhatemi and S. Savaş, Journal of Computer Science, vol. 55, no. 35, pp. 1–100, 2010.
15. P. Nancy, M. Parameswari, and J. S. Priya, “ASO-DKELM: Alpine skiing optimization based deep kernel extreme learning machine for elderly stroke detection from EEG signal,” Biomed. Signal Process. Control, vol. 88, no. PC, p. 105295, 2024.
16. S. K. UmaMaheswaran et al., “Enhanced non-contrast computed tomography images for early acute stroke detection using machine learning approach,” Expert Syst. Appl., vol. 240, p. 122559, 2024.
17. A. Srinivas and J. P. Mosiganti, “A brain stroke detection model using soft voting based ensemble machine learning classifier,” Meas. Sensors, vol. 29, p. 100871, 2023.
18. “Stroke Prediction Dataset.” [Online]. Available: https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset
19. S. Uddin et al., “Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction,” Sci. Rep., vol. 12, no. 1, pp. 1–11, Dec. 2022.
20. L. Breiman, “Random forests,” Int. J. Adv. Comput. Sci. Appl., vol. 7, no. 6, pp. 1–33, 2016.
21. J. H. Friedman, “Greedy function approximation: a gradient boosting machine,” Ann. Statist., vol. 29, no. 5, pp. 1189–1232, Oct. 2001.
22. A. Natekin and A. Knoll, “Gradient boosting machines, a tutorial,” Front. Neurorobot., vol. 7, p. 63623, Dec. 2013.
23. G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” Adv. Neural Inf. Process. Syst., vol. 30, 2017, [Online]. Available: https://github.com/Microsoft/LightGBM
24. Y. Freund and R. E. Schapire, “A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting,” J. Comput. Syst. Sci., vol. 55, no. 1, pp. 119–139, Aug. 1997.
25. L. I. Kuncheva, Combining Pattern Classifiers, Jul. 2004.
26. P. Rajpurkar et al., “Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists,” PLOS Med., vol. 15, no. 11, p. e1002686, Nov. 2018.
27. C. Cortes, V. Vapnik, and L. Saitta, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, Sep. 1995.
28. W. S. Noble, “What is a support vector machine?,” Nat. Biotechnol., vol. 24, no. 12, pp. 1565–1567, Dec. 2006.
29. J. R. Quinlan, “Induction of decision trees,” Mach. Learn., vol. 1, no. 1, pp. 81–106, Mar. 1986.
30. L. Rokach and O. Maimon, “Top-down induction of decision trees classifiers – a survey,” IEEE Trans. Syst. Man Cybern. C Appl. Rev., vol. 35, no. 4, pp. 476–487, Nov. 2005.
31. P. Geurts, D. Ernst, and L. Wehenkel, “Extremely randomized trees,” Mach. Learn., vol. 63, no. 1, pp. 3–42, Apr. 2006.
32. D. D. Lewis, “Naive (Bayes) at forty: The independence assumption in information retrieval,” Lect. Notes Comput. Sci., vol. 1398, pp. 4–15, 1998.
33. D. W. Hosmer, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression: Third Edition, pp. 1–510, Aug. 2013.
34. R. Wijaya et al., “An Ensemble Machine Learning and Data Mining Approach to Enhance Stroke Prediction,” Bioengineering, vol. 11, no. 7, 2024.
35. N. Biswas, K. M. M. Uddin, S. T. Rikta, and S. K. Dey, “A comparative analysis of machine learning classifiers for stroke prediction: A predictive analytics approach,” Healthc. Anal., vol. 2, p. 100116, 2022.
36. M. Al Duhayyim et al., “An Ensemble Machine Learning Technique for Stroke Prognosis,” Comput. Syst. Sci. Eng., vol. 47, no. 1, pp. 413–429, 2023.