Kalp Yetmezliği Hastalarında Kritik Parametre Seçimi ve Sağkalım Modeli Geliştirilmesi

Öz

Kardiyovasküler hastalıklar dünya çapında en fazla ölüme neden olan hastalıklar arasındadır. Kalp yetmezliği de sık karşılaşılan hastalıklardan biridir ve hastanın taşıdığı risk seviyesine göre ölüm oranları değişiklik göstermektedir. Ölüm oranlarındaki bu belirgin farklılık, hangi hastaların daha kötü prognoza sahip olduğunu tahmin edebilen ve daha yoğun tıbbi tedaviden ve/veya sol ventriküler destek cihazlarından ve kalp nakli tedavilerinden daha fazla yararlanabilecek olan risk grubunu belirleyen yöntemlerin geliştirilmesinin ihtiyaç olduğunu ortaya çıkarmıştır. Çalışma kapsamında kalp yetmezliği bulunan 299 hastanın verileri ve Cox, RSF ve GSB yöntemleri kullanılarak sağkalım modelleri geliştirilmiştir. Ayrıca iki farklı yöntem kullanılarak kalp yetmezliği hastalarının sağkalım modelinin geliştirilmesinde kritik rol oynayan parametreler belirlenmiştir. Veri setindeki tüm parametreler yerine belirlenen bu parametreler kullanılarak bir model oluşturulduğunda daha yüksek başarı elde edilmiştir ve elde edile bu sonuç aynı veri setini kullanan başka çalışmaların sonuçlarında da daha iyidir. Sonuç olarak seçilen parametre seti ve RSF yöntemi kullanılarak kalp yetmezliği hastaları için yüksek doğrulukla tahmin yapabilen bir sağkalım modeli geliştirilmiştir.

Anahtar Kelimeler

• Kalp yetmezliği
• Sağkalım analizi
• Cox
• RSF
• GBS

Critical Parameter Selection and Survival Model Development for Heart Failure Patients

Öz

Cardiovascular diseases are among the diseases that cause the most deaths worldwide. Heart failure is also one of the most common diseases, and mortality rates vary according to the patient’s risk level. This distinct difference in mortality revealed the need to develop methods that could predict which patients have a worse prognosis and identify the risk group that would benefit more from intensive medical treatment and/or left ventricular assist devices and heart transplant treatments. In this study, survival models were developed using the dataset of 299 heart failure patients and Cox, Random Survival Forest, and Gradient Boosting Survival. Two different approaches are also used to determine the critical parameters in developing the survival model for heart failure patients. When a model is created using these parameters instead of all parameters in the dataset, higher success has been achieved, and this result is also better than the other studies using the same dataset. In conclusion, a survival model that can predict with high accuracy was developed for heart failure patients using the selected parameter set and Random Survival Forest.

Anahtar Kelimeler

• Heart failure
• Survival analysis
• Cox
• Random survival forest
• Gradient boosting survival

Kaynakça

1. 1. Cardiovascular diseases. https://www.who.int/health-topics/cardiovascular-diseases#tab=tab_1 (accessed Feb. 08, 2021).
2. 2. Ho, K., Pinsky, J., Kannel, W., Levy, D., 1993. The Epidemiology of Heart Failure: The Framingham Study. Journal of the American College of Cardiology. 22(4), 6-42. 6A-13A. 10.1016/0735-1097(93)90455-A.
3. 3. The SOLVD Investigators, 1992. Effect of Enalapril on Mortality and the Development of Heart Failure in Asymptomatic Patients with Reduced Left Ventricular Ejection Fractions, New England Journal of Medicine, 327(10), 685–691, doi:10.1056/NEJM199209033271003.
4. 4. Yusuf, S., 1991. Effect of Enalapril on Survival in Patients with Reduced Left Ventricular Ejection Fractions and Congestive Heart Failure,” New England Journal of Medicine, 325(5), 293–302, doi:10.1056/NEJM199108013250501.
5. 5. Swedberg, K., Kjekshus, J., 1988. Effects of Enalapril on Mortality in Severe Congestive Heart Failure: Results of the Cooperative North Scandinavian Enalapril Survival Study (CONSENSUS), The American Journal of Cardiology, 62(2), 60A-66A, doi: 10.1016/S0002-9149(88)80087-0.
6. 6. Lee, D.S., Austin, P.C., Rouleau, J.L., Liu, P.P., Naimark, D., Tu, J.V., 2003. Predicting Mortality Among Patients Hospitalized for Heart Failure: Derivation and Validation of a Clinical Model, Journal of the American Medical Association, 290(19), 2581–2587. doi: 10.1001/jama.290.19.2581.
7. 7. Aaronson, K.D., Cowger, J., 2012. Heart Failure Prognostic Models Why Bother?, Circulation: Heart Failure, Lippincott Williams & Wilkins Hagerstown, MD, 5(1), 6–9. doi: 10.1161/CIRCHEARTFAILURE.111.965848.
8. 8. Levy, W.C., Mozaffarian, D., Linker, D.T., Sutradhar, S.C., Anker, S.D., Cropp, A.B., Anand, I., Maggioni, A., Burton, P., Sullivan, M.D., Pitt, B., Poole-Wilson, P.A., Mann, D.L., Packer, M., 2006. The Seattle Heart Failure Model: Prediction of Survival in Heart Failure. Circulation, 113(11),1424-1433. doi.org/10.1161/CIRCULATIONAHA.105.584102.

9. 9. Brophy, J.M., Dagenais, G.R., McSherry, F., Williford, W., Yusuf, S., 2004. A Multivariate Model for Predicting Mortality in Patients with Heart Failure and Systolic Dysfunction, the American Journal of Medicine, 116(5), 300-304, doi.org/10.1016/j.amjmed.2003.09.035.
10. 10. Ahmad, T., Munir, A., Bhatti, S.H., Aftab, M., Raza, M.A., 2017. Survival Analysis of Heart Failure Patients: A case study. PLoS ONE 12(7), e0181001, doi: 10.1371/journal.pone.0181001.
11. 11. Kaplan, E.L., Meier, P., 1958. Non-parametric Estimation from Incomplete Observations, Journal of the American Statistical Association, 53(282), 457–481, doi: 10.1080/01621459.1958.10501452.
12. 12. Collett, D., 2003. Modelling Survival Data in Medical Research, 2nd ed. Boca Raton, Fla. : Chapman & Hall/CRC, 391.
13. 13. Chicco, D., Jurman, G., 2020. Machine Learning can Predict Survival of Patients with Heart Failure from Serum Creatinine and Ejection Fraction Alone, BMC Medical Informatics and Decision Making, 20(1), 16, doi: 10.1186/s12911-020-1023-5.
14. 14. Zahid, F.M., Ramzan, S., Faisal, S., Hussain, I., 2019. Gender Based Survival Prediction Models for Heart Failure Patients: A Case Study in Pakistan, PLOS ONE, 14(2), doi:10.1371/journal.pone.0210602.
15. 15. Oladimeji, O.O., Oladimeji, O., 2020. Predicting Survival of Heart Failure Patients Using Classification Algorithms, JITCE (Journal of Information Technology and Computer Engineering), 4(02), 90–94, doi: 10.25077/jitce.4.02.90-94.2020.
16. 16. Rahayu, S., Jaya Purnama, J., Baroqah Pohan, A., Septia Nugraha, F., Nurdiani, S., Hadianti, S., 2020. Prediction of Survival of Heart Failure Patients Using Random Forest, 16(2), 255-260. doi: 10.33480/PILAR.V16I2.1665.
17. 17. Erdas, C.B., Olcer, D., 2020. A Machine Learning-Based Approach to Detect Survival of Heart Failure Patients, 1–4, doi: 10.1109/tiptekno50054.2020.9299320.
18. 18. Le, M.T., Thanh Vo, M., Mai, L., Dao, S.V.T., 2020. Predicting Heart Failure Using Deep Neural Network, in International Conference on Advanced Technologies for Communications, 221–225, doi:10.1109/ ATC50776.2020.9255445.
19. 19. Kucukakcali, Z., Cicek, I.B., Guldogan, E., Colak, C., 2020. Assessment of Associative Classification Approach for Predicting Mortality by Heart Failure, The Journal of Cognitive Systems, 5(2), 41–45, Accessed: Feb. 07, 2021. [Online]. Available: http://dergipark.gov.tr/jcs.
20. 20. Chicco, D., Jurman, G., 2020. Survival Prediction of Patients with Sepsis from Age, Sex, and Septic Episode Number Alone, Scientific Reports, 10(1), 1–12, doi: 10.1038/s41598-020-73558-3.
21. 21. Raphael, C., Briscoe, C., Davies, J., Whinnett, Z.I., Manisty, C., Sutton, R., Mayet, J., Francis, D.P., 2007. Limitations of the New York Heart Association Functional Classification System and Self-reported Walking Distances in Chronic Heart Failure, Heart, 93(4), 476–482, doi:10.1136/hrt.2006.089656.
22. 22. Deep Learning for Survival Analysis. https://humboldtwi.github.io/blog/research/information_systems_1920/group2_survivalanalysis/ (accessed Feb. 10, 2021).
23. 23. Cox, D.R., 1972. Regression Models and Life- Tables, Journal of the Royal Statistical Society: Series B (Methodological), 34(2), 187–202, doi: 10.1111/j.2517-6161.1972.tb00899.x.
24. 24. Ishwaran, H., Kogalur, U.B., Blackstone, E.H., Lauer, M.S., 2008. Random Survival Forests, Annals of Applied Statistics, 2(3), 841–860, doi: 10.1214/08-AOAS169.
25. 25. Friedman, J.H., 2001. Greedy Function Approximation: a Gradient Boosting Machine, The Annals of Statistics, 29(5), 1189–1232, Accessed: Feb. 05, 2021. [Online].
26. 26. Uno, H., Cai, T., Pencina, M.J., D’agostino, R.B., Wei, L.J., 2011. On the C-statistics for Evaluating Overall Adequacy of Risk Prediction Procedures with Censored Survival Data, Statistics in Medicine, 30(10), 1105-1117. doi: 10.1002/sim.4154.