Karaciğer Fonksiyon Bozukluğu Teşhisinde Tahmin Algoritmalarının Değerlendirilmesi

Öz

Akut karaciğer yetmezliği, karaciğerdeki fonksiyon bozukluğuna bağlı olarak gelişir. Kısa sürede gelişen ve vücutta ciddi hasarlara sebep olan akut karaciğer yetmezliği için erken tanı büyük önem taşır. Hekimin daha erken tanı koyabilmesi açısından makine öğrenimi yöntemlerine dayalı tahmin işlemleri, hekime karar verme sürecinde yardım sağlayabilir. Bu çalışma, akut karaciğer yetmezliği varlığının tahmini için hekime yardımcı olabilecek, yakın zamanda sunulan ve yüksek tahmin kabiliyetlerine sahip üç algoritmanın değerlendirilmesini amaçlar. Çalışmada kamuya açık veri kümeleri üzerinde XGBoost, LightGBM ve NGBoost yöntemlerinin tahmin başarımları incelenir. Bu araştırmada iki veri kümesi kullanılır; ilk veri kümesi 2008–2009 ve 2014–2015 dönemlerinde “JPAC Health Diagnostic and Control” Merkezinde toplandı. Veri kümesinde, toplam 8785 hastanın bilgisi bulunur ve hastaların çoğunda "akut karaciğer yetmezliği" geliştiğine dair bilgi yer almıyor. Ayrıca ikinci değerlendirme için Iesu vd. tarafından toplanan ve "akut karaciğer fonksiyon bozukluğu" gelişen veya gelişmeyen hastalar hakkında bilgi içeren bir veri kümesi kullanılır. Veri kümesinden edinilen bilgiye göre, 208 hastada "akut karaciğer fonksiyon bozukluğu" gelişirken, 166 hastada bu durum gelişmemiştir. Eğitim ve test aşamalarında her üç algoritmanın yüksek tahmin sonuçları verdiği ve LightGBM yönteminin daha kısa sürede sonuca ulaştığı, NGBoost yönteminin ise diğer algoritmalara göre daha uzun sürede sonuç verdiği değerlendirmeler kapsamında gözlenmiştir.

Anahtar Kelimeler

• XGBoost
• LightGBM
• NGBoost
• akut karaciğer yetmezliği
• sınıflandırma

Evaluation of the Prediction Algorithms for the Diagnosis of Hepatic Dysfunction

Öz

Acute liver failure develops due to liver dysfunction. Early diagnosis is crucial for acute liver failure, which develops in a short time and causes serious damage to the body. Prediction processes based on machine learning methods can provide assistance to the physician in the decision-making process in order for the physician to make a diagnosis earlier. This study aims to evaluate three recently presented algorithms with high predictive capabilities that can assist the doctor in determining the existence of acute liver failure. In this study, the prediction performances of the XGBoost, LightGBM, and NGBoost methods are examined on publicly available data sets. In this research, two datasets are used; the first dataset was gathered in the “JPAC Health Diagnostic and Control Center” during the periods 2008–2009 and 2014–2015. The dataset includes a total of 8785 patients' information, and it mostly does not contain patients' information that "acute liver failure" was developing. Furthermore, a dataset collected by Iesu et al., containing information on patients who developed or did not develop "acute liver dysfunction," is used for the second evaluation. According to the information obtained from the data set, "acute liver dysfunction" developed in 208 patients, while this situation did not develop in 166 patients. It is observed within the scope of the evaluations that all three algorithms give high estimation results during the training and testing stages, and moreover, the LightGBM method achieves results in a shorter time while the NGBoost method provides results in a longer time compared to other algorithms.

Anahtar Kelimeler

• XGBoost
• LightGBM
• NGBoost
• acute liver failure
• classification

Kaynakça

1. [1]. Arshad M. A., Murphy N., Bangash M. N.,” Acute liver failure” Clinical Medicine Journal, 20 (5), 505-508, 2020 DOI: 10.7861/clinmed.2020-0612
2. [2]. Kayaalp C., Ersan V., Yılmaz S., “Acute liver failure in Turkey: A systematic review” Turkish Journal of Gastroenterology, 25(1), 35 – 40, 2014 DOI: 10.5152/tjg.2014.4231
3. [3]. Sugawara K., Nakayama N., Mochida S., “Acute liver failure in Japan: definition, classification, and prediction of the outcome” Journal of Gastroenterology, 47, 849–861, 2012 Available from: https://doi.org/10.1007/s00535-012-0624-x
4. [4]. Saberi-Karimian M., Khorasanchi Z., Ghazizadeh H., Tayefi M., Saffar S., Ferns G. A., Ghayour-Mobarhan M.,” Potential value and impact of data mining and machine learning in clinical diagnostics” Critical Reviews in Clinical Laboratory Sciences, 58(4), 275-296, 2021 DOI: 10.1080/10408363.2020.1857681
5. [5]. Park D. J., Park M. W., Lee H., Kim Y. J., Kim Y., Park Y. H., “Development of machine learning model for diagnostic disease prediction based on laboratory tests” Scientific Reports, 11, 7567, 2021 Available from: https://doi.org/10.1038/s41598-021-87171-5
6. [6]. Mostafa F., Hasan E., Williamson M., Khan H., “Statistical machine learning approaches to liver disease prediction” Livers, 1(4), 294-312, 2021 Available from: https://doi.org/10.3390/livers1040023
7. [7]. Ahn J. C., Connell A., Simonetto D. A., Hughes C., Shah V. H., “Application of artificial intelligence for the diagnosis and treatment of liver diseases” Hepatology, 73(6), 2546-2563, 2021 Available from: https://doi.org/10.1002/hep.31603
8. [8]. Chen T., Guestrin C., “XGBoost: A scalable tree boosting system” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, USA, 2016

9. [9]. Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T. Y., “LightGBM: A highly efficient gradient boosting decision tree” Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA, 2017
10. [10]. Duan T., Avati A., Ding D.Y., Thai K. K., Basu S., Ng A., Schuler A.,”NGBoost: Natural gradient boosting for probabilistic prediction“ Proceedings of the 37th International Conference on Machine Learning, Virtual Event, 2020
11. [11]. Abdurrahman G., Sintawati M., “Implementation of XGBoost for classification of parkinson’s disease” 3rd International Conference on Combinatorics, Graph Theory, and Network Topology, East Java, Indonesia, 2019
12. [12]. Paleczek A., Grochala D., Rydosz A., “Artificial breath classification using XGBoost algorithm for diabetes detection” Sensors, 21(12), 4187, 2021 Available from: https://doi.org/10.3390/s21124187
13. [13]. Aydin Z. E., Ozturk Z. K., “XGBoost feature selection on chronic kidney disease diagnosis” Proceedings of the IV International Conference on Data Science and Applications, Virtual Event, 2021
14. [14]. Wang L., Wang X., Chen A., Jin X., Che H., “Prediction of type 2 diabetes risk and its effect evaluation based on the XGBoost model” Healthcare, 8(3), 247, 2020 Available from: https://doi.org/10.3390/healthcare8030247
15. [15]. Ali N., Srivastava D., Tiwari A., Pandey A., Pandey A. K., Sahu A., "Predicting life expectancy of Hepatitis B patients using machine learning" IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, Ballari, India, 2022
16. [16]. Hou F., Cheng Z., Kang L., Zheng W., “Prediction of gestational diabetes based on LightGBM” Proceedings of the 2020 Conference on Artificial Intelligence and Healthcare, Taiyuan, China, 2020
17. [17]. Wang Y., Wang T., “Application of Improved LightGBM Model in Blood Glucose Prediction” Applied Sciences, 10(9), 3227, 2020 Available from: https://doi.org/10.3390/app10093227
18. [18]. Shobana G., Umamaheswari K., “Prediction of liver disease using gradient boost machine learning techniques with feature scaling” 5th International Conference on Computing Methodologies and Communication, Erode, India, 2021
19. [19]. Sinthuja U., Hatti V., Thavamani S., “Analysis and prediction of liver disease for the patients in India using various machine learning algorithms” International Conference on Advances in Data Computing, Communication and Security, Kurukshetra, India, 2021
20. [20]. Rufo D. D., Debelee T. G., Ibenthal A., Negera W. G., “Diagnosis of diabetes mellitus using gradient boosting Machine (LightGBM)” Diagnostics, 11(9), 1714, 2021 Available from: https://doi.org/10.3390/diagnostics11091714
21. [21]. Noh B., Park Y. M., Kwon Y., Choi C. I., Choi B. K., Seo K., Park Y. H., Yang K., Lee S., Ha T., Hyon Y., Yoon M., “Machine learning-based survival rate prediction of Korean hepatocellular carcinoma patients using multi-center data” BMC Gastroenterology, 22, 1-9, 2022 Available from: https://doi.org/10.1186/s12876-022-02182-4
22. [22]. Zhang D., Gong Y., "The comparison of LightGBM and XGBoost coupling factor analysis and prediagnosis of acute liver failure” IEEE Access, 8, 220990-221003, 2020 DOI: 10.1109/ACCESS.2020.3042848
23. [23]. Sengupta D., Mondal S., Basu S., De A. K., Nath S., Pandey A., “Classification of acute liver failure using machine learning algorithms” IEEE International Conference on Electronics, Computing and Communication Technologies, Bangalore, India, 2022
24. [24]. Kumar R., “Acute liver failure dataset”, Available from: https://www.kaggle.com/datasets/rahul121/acute-liver-failure [Accessed 20 December 2022]
25. [25]. Iesu E., Franchi F., Cavicchi F. Z., Pozzebon S., Fontana V., Mendoza M., Nobile L., Scolletta S, Vincent J. L., Creteur J., Taccone F. S., “Acute liver dysfunction after cardiac arrest” PLoS ONE, 13(11), e0206655, 2018 Available from: https://doi.org/10.1371/journal.pone.0206655
26. [26]. Lin J. L., Peng Z. Q., Lai R. K., “Improving pavement anomaly detection using backward feature elimination” 20th International Conference on Business Information Systems, Poznan, Poland, 2017
27. [27]. Misra P., Yadav A. S., “Improving the classification accuracy using recursive feature elimination with cross-validation” International Journal on Emerging Technologies, 11 (3), 659-665, 2020
28. [28]. Mustaqim A. Z., Adi S., Pristyanto Y., Astuti Y., “The effect of recursive feature elimination with cross-validation (RFECV) feature selection algorithm toward classifier performance on credit card fraud detection” International Conference on Artificial Intelligence and Computer Science Technology, Yogyakarta, Indonesia, 2021
29. [29]. Chang Y., Chen X., “Estimation of chronic illness severity based on machine learning methods” Wireless Communications and Mobile Computing, 2021, 1-13, 2021 Available from: https://doi.org/10.1155/2021/1999284
30. [30]. Kern C., Klausch T., Kreuter F., “Tree-based machine learning methods for survey research” Surv Res Methods, 13(1), 73-93, 2019
31. [31]. Sagi O., Rokach L., “Ensemble learning: A survey” WIREs Data Mining Knowl Discov, 8(4), 1-18, 2018 Available from: https://doi.org/10.1002/widm.1249
32. [32]. Mayr A., Binder H., Gefeller O., Schmid M., “The evolution of boosting algorithms. From machine learning to statistical modelling” Methods Inf Med, 53(6), 419-427, 2014
33. [33]. Friedman J. H., “Greedy function approximation: A gradient boosting machine” The Annals of Statistics, 29(5), 1189–1232, 2001
34. [34]. Bentéjac C., Csörgő A., Martínez-Muñoz G., “A comparative analysis of gradient boosting algorithms” Artificial Intelligence Review, 54, 1937–1967, 2021 Available from: https://doi.org/10.1007/s10462-020-09896-5
35. [35]. Kim C., Park T., “Predicting determinants of lifelong learning intention using gradient boosting machine (GBM) with grid search” Sustainability, 14(9), 5256, 2022 Available from: https://doi.org/10.3390/su14095256
36. [36]. Ma X., Sha J., Wang D., Yu Y., Yang Q., Niu X.,” Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning” Electronic Commerce Research and Applications, 31, 24-39, 2018 Available from: https://doi.org/10.1016/j.elerap.2018.08.002
37. [37]. Dalianis H., “Evaluation metrics and evaluation”, Clinical Text Mining, Springer, Cham, Switzerland, 2018 Available from: https://doi.org/10.1007/978-3-319-78503-5_6
38. [38]. Hussain S, Mustafa M. W., Al-Shqeerat K. H. A., Saeed F., Al-rimy B. A. S., “A novel feature-engineered–NGBoost machine-learning framework for fraud detection in electric power consumption data” Sensors, 21(24), 8423, 2021 Available from: https://doi.org/10.3390/s21248423
39. [39]. McNemar Q., “Note on the sampling error of the difference between correlated proportions or percentages” Psychometrika, 12(2), 153–157, 1947 Available from: https://doi.org/10.1007/BF02295996
40. [40]. Prokhorenkova L., Gusev G., Vorobev A., Dorogush A. V., Gulin A., “CatBoost: unbiased boosting with categorical features” NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, Canada, 2018
41. [41]. Han L., Yang T., Pu X., Sun L., Yu B., Xi J., “Alzheimer's disease classification using LightGBM and Euclidean distance map” IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference, Chongqing, China, 2021
42. [42]. Zheng P., Yu Z., Li L., Liu S., Lou Y., Hao X., Yu P., Lei M., Qi Q., Wang Z., Gao F., Zhang Y., Li Y., “Predicting blood concentration of tacrolimus in patients with autoimmune diseases using machine learning techniques based on real-world evidence” Front. Pharmacol, 12, 727245, 2021 DOI: 10.3389/fphar.2021.727245
43. [43]. Muzumdar P., Basyal G. P., Vyas P., “An empirical comparison of machine learning models for student’s mental health illness assessment” Asian Journal of Computer and Information Systems, 10(1), 1-10, 2022 Available from: https://www.ajouronline.com/index.php/AJCIS/article/view/6882
44. [44]. Kim E., Han K. S., Cheong T., Lee S. W., Eun J., Kim S. J., “Analysis on benefits and costs of machine learning-based early hospitalization prediction” IEEE Access, 10, 32479-32493, 2022 DOI: 10.1109/ACCESS.2022.3160742