CHARACTERIZATION OF MORTALITY PREDICTION: AN ENSEMBLE LEARNING ANALYSIS USING THE MIMIC-III DATASET

Abstract

Applications that employ medical data are directly impacted by the classification of imbalanced data. It is vital due to the nature of classification and solutions about medical data. The purpose of this article is to identify a machine learning model that may be successfully applied in the medical field to reduce the number of mortality and optimize the efficiency of hospital resources. For this reason, it is thought that the better the performance of the ML model, the more a different perspective will be gained on the problems in today's medicine. Therefore, in the study, Weighted Random Forest (WRF) and Balanced Random Forest (BRF) which are ensemble machine learning (ML) methods for imbalanced data were implemented to identify the performance of the algorithms for mortality determination from open-source MIMIC-III dataset by using vital signs, comorbidities, and laboratory variables with demographic characteristic information. To evaluate the performance of WRF and BRF, a Random Forest Classifier (RFC) was also implemented to investigate the power of developed models for imbalanced data. In addition, the features used in the ML methods were separated into three groups to explore the impact of the vital signs, comorbidities, and laboratory variables with demographic characteristics separately on mortality identification. In addition to previous applications on UCI datasets, the present study revealed that the BRF method for imbalanced medical data provides high performance in determining the majority and minority classes of the data by using vital signs and laboratory variables with demographic characteristics.

Keywords

• MIMIC-III
• Random Forest
• Weighted Random Forest
• Balanced Random Forest
• Ensemble Learning

References

1. [1] Hanson III, C. W., & Marshall, B. E. (2001). Artificial intelligence applications in the intensive care unit. Critical care medicine, 29(2), 427-435.
2. [2] Yang, W., Zou, H., Wang, M., Zhang, Q., Li, S., & Liang, H. (2023). Mortality prediction among ICU inpatients based on MIMIC-III database results from the conditional medical generative adversarial network. Heliyon, 9(2).
3. [3] Dybowski, R., Gant, V., Weller, P., & Chang, R. (1996). Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm. The Lancet, 347(9009), 1146-1150.
4. [4] Gortzis, L. G., Sakellaropoulos, F., Ilias, I., Stamoulis, K., & Dimopoulou, I. (2008). Predicting ICU survival: a meta-level approach. BMC health services research, 8, 1-8.
5. [5] Karun, K. M., Puranik, A., Lintu, M. K., & Deepthy, M. S. (2023). Risk factors of pneumonia among elderly with robust Poisson regression-A study on mimic III data. Biomedicine, 43(02), 696-700.
6. [6] Data, M. C., & Pirracchio, R. (2016). Mortality prediction in the icu based on mimic-ii results from the super icu learner algorithm (sicula) project. Secondary Analysis of Electronic Health Records, 295-313.
7. [7] Eya, J., Ejikem, M., Ogamba, C., & Ogamba, C. M. (2022). Admission and Mortality Patterns in Intensive Care Delivery at Enugu State University of Science and Technology Teaching Hospital: A Three-Year Retrospective Study. Cureus, 14(7).
8. [8] Aydin, Z. E., & Ozturk, Z. K. (2021). Prediction Length of Stay in Intensive Care Unit in the Presence of Missing Data. Artificial Intelligence Theory and Applications, 1(2), 48-53.

9. [9] Liu, J., Wu, J., Liu, S., Li, M., Hu, K. & Li, K. (2021) Predicting mortality of patients with acute kidney injury in the ICU using XGBoost model. PLoS One, 16(2). doi: 10.1371/journal.pone.0246306
10. [10] Leung, W. K., Cheung, K. S., Li, B., et al. (2021) Applications of machine learning models in the prediction of gastric cancer risk in patients after Helicobacter pylori eradication. Aliment Pharmacol Ther, 53 (8), 864– 872.
11. [11] Pang, X., Forrest, C. B., Lê-Scherban, F., Masino, A. J. (2021) Prediction of early childhood obesity with machine learning and electronic health record data. International Journal of Medical Informatics. 150, 104454. https://doi.org/10.1016/j.ijmedinf.2021.104454.
12. [12] Silahtaroglu, G., & Canbolat, Z. N. (2020). An early prediction and diagnosis of sepsis in intensive care units: An unsupervised machine learning model. Mugla Journal of Science and Technology, 6(1), 32-40.
13. [13] Poucke, S. V., Zhang, Z., Schmitz, M., Vukicevic, M., Laenen, M. V., Celi, L. A., & Deyne, C. D. (2016). Scalable predictive analysis in critically ill patients using a visual open data analysis platform. PloS one, 11(1), e0145791
14. [14] Churpek, M. M., Yuen, T. C., Winslow, C., Meltzer, D. O., Kattan, M. W., & Edelson, D. P. (2016). Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards. Critical care medicine, 44(2), 368.
15. [15] Xia, F., Zhang, J., Meng, S., Qiu, H., & Guo, F. (2021). Association of frailty with the risk of mortality and resource utilization in elderly patients in intensive care units: a meta-analysis. Frontiers in Medicine, 8, 637446.
16. [16] Dybowski, R., Gant, V., Weller, P., & Chang, R. (1996). Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm. The Lancet, 347(9009), 1146-1150.
17. [17] Kim, S., Kim, W., & Park, R. W. (2011). A comparison of intensive care unit mortality prediction models through the use of data mining techniques. Healthcare informatics research, 17(4), 232-243.
18. [18] Lin, W., Wu, Z., Lin, L., Wen, A., & Li, J. (2017). An ensemble random forest algorithm for insurance big data analysis. Ieee access, 5, 16568-16575.
19. [19] Yalcin Kuzu, S. (2023). Random Forest Based Multiclass Classification Approach for Highly Skewed Particle Data. Journal of Scientific Computing, 95(1), 21.
20. [20] Johnson, A., Pollard, T., & Mark, R. (2019). MIMIC-III Clinical Database Demo (version 1.4). PhysioNet. https://doi.org/10.13026/C2HM2Q.
21. [21] Scheunert, G., Heinonen, O., Hardeman, R., Lapicki, A., Gubbins, M., & Bowman, R. M. (2016). A review of high magnetic moment thin films for microscale and nanotechnology applications. Applied Physics Reviews, 3(1).
22. [22] Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM computing surveys (CSUR), 41(3), 1-58.
23. [23] Salo, F., Injadat, M., Nassif, A. B., Shami, A., & Essex, A. (2018). Data mining techniques in intrusion detection systems: A systematic literature review. IEEE Access, 6, 56046-56058.
24. [24] Krawczyk, B., Galar, M., Jeleń, Ł., & Herrera, F. (2016). Evolutionary undersampling boosting for imbalanced classification of breast cancer malignancy. Applied Soft Computing, 38, 714-726.
25. [25] Vuttipittayamongkol, P., & Elyan, E. (2020). Improved overlap-based undersampling for imbalanced dataset classification with application to epilepsy and parkinson’s disease. International journal of neural systems, 30(08), 2050043.
26. [26] Elyan, E., Jamieson, L., & Ali-Gombe, A. (2020). Deep learning for symbols detection and classification in engineering drawings. Neural networks, 129, 91-102.
27. [27] Zhang, X., Zhuang, Y., Wang, W., & Pedrycz, W. (2016). Transfer boosting with synthetic instances for class imbalanced object recognition. IEEE transactions on cybernetics, 48(1), 357-370.
28. [28] Tabakoglu, N., & Volkan, I. N. A. L. (2021). Evaluation of Basic Parameters for Prediction of ICU Mortality. Journal of Critical and Intensive Care, 12(2), 47.
29. [29] Altun, G. T., Arslantas, M. K., Dincer, P. C., Arslantas, R., & Kararmazf, A. (2022). Prognostic value of the lactate–albumin difference for predicting in-hospital mortality in critically ill patients with sepsis. Marmara Medical Journal, 35(1), 61-66.
30. [30] Harutyunyan, H., Khachatrian, H.D., Kale, C., Ver Steeg,G., Galstyan, A.,(2019). “Multitask learning and benchmarking with clinical time series data,” Sci. Data, vol. 6, no. 1, p. 96.
31. [31] Saeed, M., Villarroel, M., Reisner, A. T., Clifford, G., Lehman, L. W., Moody, G., ... & Mark, R. G. (2011). Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II): a public-access intensive care unit database. Critical care medicine, 39(5), 952.
32. [32] Vincent, J. L., Moreno, R., Takala, J., Willatts, S., De Mendonça, A., Bruining, H., ... & Thijs, L. G. (1996). The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure: On behalf of the Working Group on Sepsis-Related Problems of the European Society of Intensive Care Medicine (see contributors to the project in the appendix).
33. [33] LaFaro, R. J., Pothula, S., Kubal, K. P., Inchiosa, M. E., Pothula, V. M., Yuan, S. C., ... & Inchiosa Jr, M. A. (2015). Neural network prediction of ICU length of stay following cardiac surgery based on pre-incision variables. PLoS One, 10(12), e0145395.
34. [34] Ahmad, R. (2021). The role of digital technology and artificial intelligence in diagnosing medical images: a systematic review. Open Journal of Radiology, 11(01), 19.
35. [35] Aduszkiewicz, A., Ali, Y., Andronov, E., Antićić, T., Antoniou, N., Baatar, B., ... & Wojtaszek-Szwarc, A. (2017). Two-particle correlations in azimuthal angle and pseudorapidity in inelastic p+ p interactions at the CERN Super Proton Synchrotron. The European Physical Journal C, 77, 1-15.
36. [36] Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
37. [37] Trzciński, T., Graczykowski, Ł., Glinka, M., & ALICE Collaboration. (2020). Using random forest classifier for particle identification in the ALICE experiment. In Information Technology, Systems Research, and Computational Physics 3 (pp. 3-17). Springer International Publishing. [38] Yalcin Kuzu, S. (2022). J/ψ production with machine learning at the LHC. The European Physical Journal Plus, 137(3), 392.
38. [39] Chen, C., Liaw, A., & Breiman, L. (2004). Using random forest to learn imbalanced data. University of California, Berkeley, 110(1-12), 24.
39. [40] Agusta, Z. P. (2019). Modified balanced random forest for improving imbalanced data prediction. International Journal of Advances in Intelligent Informatics, 5(1), 58-65.
40. [41] Khalilia, M., Chakraborty, S., & Popescu, M. (2011). Predicting disease risks from highly imbalanced data using random forest. BMC medical informatics and decision making, 11, 1-13.
41. [42] Amin, M., & Ali, A. (2018). Performance evaluation of supervised machine learning classifiers for predicting healthcare operational decisions. Wavy AI Research Foundation: Lahore, Pakistan, 90.
42. [43] Fonarow, G. C., Adams, K. F., Abraham, W. T., Yancy, C. W., Boscardin, W. J., & ADHERE Scientific Advisory Committee. (2005). Risk stratification for in-hospital mortality in acutely decompensated heart failure: classification and regression tree analysis. Jama, 293(5), 572-580.
43. [44] Peterson PN, Rumsfeld JS, Liang L, et al. A validated risk score for in-hospital mortality in patients with heart failure from the American heart association get with the guidelines program. Circ Cardiovasc Qual Outcomes 2010;3:25–32.
44. [45] Kipnis, E., Ramsingh, D., Bhargava, M., Dincer, E., Cannesson, M., Broccard, A., ... & Thibault, R. (2012). Monitoring in the intensive care. Critical care research and practice, 2012.
45. [46] Wang, N., Gallagher, R., Sze, D., Hales, S., & Tofler, G. (2019). Predictors of frequent readmissions in patients with heart failure. Heart, Lung and Circulation, 28(2), 277-283.
46. [47] Web ref: Zhou, Jingmin et al. (2021), Prediction model of in-hospital mortality in intensive care unit patients with heart failure: machine learning-based, retrospective analysis of the MIMIC-III database, Dryad, Dataset, https://doi.org/10.5061/dryad.0p2ngf1zd
47. [48] Bennett, N. (2021). Enabling External Validation for Machine Learning Applications Using Intensive Care Data (Doctoral dissertation, ETH Zurich).
48. [49] Probst, P., & Boulesteix, A. L. (2017). To tune or not to tune the number of trees in random forest. The Journal of Machine Learning Research, 18(1), 6673-6690.
49. [50] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
50. [51] Narsky, I., Porter, F.C., (2014). Statistical Analysis Techniques in Particle Physics, Almanya:Wiley–VCH.
51. [52] Jeni, L. A., Cohn, J. F., & De La Torre, F. (2013, September). Facing imbalanced data--recommendations for the use of performance metrics. In 2013 Humaine association conference on affective computing and intelligent interaction (pp. 245-251). IEEE.
52. [53] Bauder, R., & Khoshgoftaar, T. (2018, July). Medicare fraud detection using random forest with class imbalanced big data. In 2018 IEEE international conference on information reuse and integration (IRI) (pp. 80-87). IEEE.
53. [54] Müller A. C., Guido, S., (2016). Introduction to Machine Learning with Python, O'Reilly Media Inc., Amerika: Sebastopol Kaliforniya.
54. [55] Ilhan Taskin, Z., Yildirak, K., & Aladag, C. H. (2023). An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection application. Journal of Big Data, 10(1), 38.
55. [56] Zhu, M., Xia, J., Jin, X., Yan, M., Cai, G., Yan, J., & Ning, G. (2018). Class weights random forest algorithm for processing class imbalanced medical data. IEEE Access, 6, 4641-4652.