Ensemble and Non-Ensemble Machine Learning-Based Classification of Liver Cirrhosis Stages

Abstract

Cirrhosis is a chronic liver condition characterized by gradual scarring of the tissue in the liver, which then leads to one of the more serious health problems. Early diagnosis and detection of this condition are critical to managing the patient's situation and planning his treatment. Machine learning is a computer science field in which many complex issues have otherwise been successfully resolved, especially in medicine. This work focuses on constructing an artificial intelligence system, assisted by machine learning algorithms, to help professionals diagnose liver cirrhosis at its early stage. In this paper, four different models have been constructed with the aid of clinical parameters of patients and machine learning techniques: Random Forest, KNN, histogram-based Gradient Boosting, and Soft Voting. Two Feature selection methods (Chi-Square and mutual information) have been combined to select the most relevant features in the dataset. Then non-ensemble and ensemble methods are used to detect the condition. The random forest model achieved the highest score among other model with 97.4 % accuracy with a 10-fold Cross-validation method.

Keywords

• Liver cirrhosis
• Artificial intelligence
• Mutual information
• Soft voting
• K-fold cross-validation

Topluluk ve Topluluk Olmayan Makine Öğrenmesine Dayalı Karaciğer Sirozu Evrelerinin Sınıflandırılması

Öz

Siroz, karaciğerdeki dokunun kademeli olarak yaralanmasıyla karakterize kronik bir karaciğer rahatsızlığıdır. Bu rahatsızlık ilerleyen dönemde daha ciddi sağlık sorunlarına yol açar. Bu rahatsızlığın erken teşhisi ve tespiti, hastanın durumunu yönetmek ve tedavisini planlamak için kritik öneme sahiptir. Makine öğrenimi, özellikle tıpta birçok karmaşık sorunun başarıyla çözüldüğü bir bilgisayar bilimi alanıdır. Bu çalışma, profesyonellerin karaciğer sirozunu erken aşamada teşhis etmelerine yardımcı olmak için makine öğrenimi algoritmalarıyla desteklenen bir yapay zeka sistemi oluşturmaya odaklanmaktadır. Bu makalede, hastaların klinik parametreleri ve makine öğrenimi tekniklerinin yardımıyla dört farklı model oluşturulmuştur: Rastgele Orman, KNN, Histogram Tabanlı Gradyan Artırma ve Yumuşak Oylama. Veri kümesindeki en alakalı özellikleri seçmek için iki özellik seçme yöntemi (Chi-square ve karşılıklı bilgi) birleştirilmiştir. Ardından durumu tespit etmek için topluluk dışı ve topluluk yöntemleri kullanılmıştır. Rastgele orman modeli, 10 katlı çapraz doğrulama yöntemi ile %97,4 doğrulukla diğer modeller arasında en yüksek puanı elde etmiştir.

Anahtar Kelimeler

• Karaciğer sirozu
• Yapay zeka
• Karşılıklı bilgi
• Yumuşak oylama
• K-katlı çapraz doğrulama

Kaynakça

1. The Digestive Process: The Liver and its Many Functions. Johns Hopkins Medicine. 2019 Nov 19. Available from: https://www.hopkinsmedicine.org/health/conditions-and-diseases/the-digestive-process-the-liver-and-its-many-functions.
2. H. Devarbhavi, S. K. Asrani, J. P. Arab, Y. A. Nartey, E. Pose, and P. S. Kamath, “Global Burden of Liver Disease: 2023 Update,” Journal of Hepatology, vol. 79, no. 2, Mar. 2023, doi: https://doi.org/10.1016/j.jhep.2023.03.017.
3. Mohamed AA, Elbedewy TA, El-Serafy M, El-Toukhy N, Ahmed W, et al. Liver cirrhosis virus: A global view. World Journal of Hepatology. 2015;7(26):2676-80.
4. Cirrhosis of the Liver. American Liver Foundation. 2023 Mar 16. Available from: https://liverfoundation.org/liver-diseases/complications-of-liver-disease/cirrhosis/.
5. Buechter M, Gerken G. Liver Function—How to Screen and to Diagnose: Insights from Personal Experiences, Controlled Clinical Studies and Future Perspectives. J Pers Med. 2022;12(10):1657.
6. Hanif I, Khan MM. Liver Cirrhosis Prediction using Machine Learning Approaches. 2022 IEEE 13th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON). 2022.
7. Ahsan MM, Luna SA, Siddique Z. Machine-Learning-Based Disease Diagnosis: A Comprehensive Review. Healthcare (Basel). 2022;10(3):541.
8. Meng D, Zhang L, Cao G, Cao W, Zhang G, Hu B. Liver Fibrosis Classification Based on Transfer Learning and FCNet for Ultrasound Images. IEEE Access. 2017;5:2169-3536.

9. Huang R, Rao H, Yang M, Gao Y, Wang J, et al. Noninvasive measurements predict liver fibrosis well in liver cirrhosis virus patients after direct-acting antiviral therapy. Dig Dis Sci. 2020;65(5):1491-500.
10. Cheng Z, Zhang Y, Zhou C. QSAR models for phosphoramidate prodrugs of 2'-methylcytidine as inhibitors of Liver cirrhosis virus based on PSO boosting. Chem Biol Drug Des. 2011;78(6):948-59.
11. Bedeir A, El-Hadi M. A Proposed Framework for Predictive Analytics for Cirrhosis of the Liver Using Machine Learning. Maǧallaẗ Al-Ǧamʿiyyaẗ Al-Miṣriyyaẗ Li Nuẓum Al-Maʿlūmāt wa Tiknūlūğyā Al-Ḥāsibāt. 2023;31(31):114-23.
12. Rahman AKMS, Javed M, Tasnim Z, Roy J, Hossain SA. A Comparative Study On Liver Disease Prediction Using Supervised Machine Learning Algorithms. 2019;8(11):419-22.
13. Sürücü S, Diri B. Transferemble: a classification method for the detection of fake satellite images created with deep convolutional generative adversarial network. J Electron Imaging. 2023;32(4):043004.
14. Topcu AE, Elbasi E, Alzoubi YI. Machine Learning-Based Analysis and Prediction of Liver Cirrhosis. In: Proceedings of the 2024 47th International Conference on Telecommunications and Signal Processing (TSP); 2024; Prague, Czech Republic. p. 191-194.
15. Zhang C, Shu Z, Chen S, et al. A machine learning-based model analysis for serum markers of liver fibrosis in chronic hepatitis B patients. Sci Rep. 2024;14:12081.
16. Choi YS, Oh E. Investigating of Machine Learning Based Algorithms for Liver Cirrhosis Prediction. Adv Eng Intell Syst. 2024;3(1):115-130.
17. Hirano R, Rogalla P, Farrell C, et al. Development of a classification method for mild liver fibrosis using non-contrast CT image. Int J Comput Assist Radiol Surg. 2022;17:2041-2049.
18. Devikanniga D, Ramu A, Haldorai A. Efficient Diagnosis of Liver Disease using Support Vector Machine Optimized with Crow Search Algorithm. EAI Endorsed Trans Energy Web. 2020;7(29):e10.
19. Md AQ, Kulkarni S, Joshua CJ, Vaichole T, Mohan S, Iwendi C. Enhanced preprocessing approach using ensemble machine learning algorithms for detecting liver disease. Biomedicines. 2023;11(2):581.
20. Dickson ER, Grambsch PM, Fleming TR, Fisher LD, Langworthy A. Prognosis in primary biliary cirrhosis: model for decision making. Hepatology. 1989;10(1):1-7.
21. Straw I, Wu H. Investigating for bias in healthcare algorithms: a sex-stratified analysis of supervised machine learning models in liver disease prediction. BMJ Health Care Inform. 2022;29(1).
22. Lee GY, Alzamil L, Doskenov B, Termehchy A. A survey on data cleaning methods for improved machine learning model performance. arXiv preprint arXiv:2109.07127. 2021.
23. Kwak SK, Kim JH. Statistical data preparation: management of missing values and outliers. Korean J Anesthesiol. 2017;70(4):407-411.
24. Batista GEAPA, Prati RC, Monard MC. A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor Newsl. 2004;6(1):20-29.
25. Chen X, Ishwaran H. Random forests for genomic data analysis. Genomics. 2012;99(6):323-329.
26. Tembusai ZR, Mawengkang H, Zarlis M. K-nearest neighbor with K-fold cross validation and analytic hierarchy process on data classification. Int J Adv Data Inf Syst. 2021;2(1):45-52.