Machine Learning and Medical Data: Predicting ICU Mortality and Re-admission Risks

Abstract

Intensive care units (ICUs) are divisions where critically ill patients are treated by medical experts. The unmet and vital need for automated clinical decision-making mechanisms is critical to maneuvering the large influx of patients. This became more apparent after the COVID-19 pandemic. Existing studies focus on determining the probability of patients dying in the ICUs and prioritizing patients in dire need. Only a few studies have calculated the patient's probability of returning to the ICUs after discharge. These studies reduce the problem into a binary task of predicting mortality or re-admission only. However, this is unrealistic since both outcomes are highly possible for each patient. In this interdisciplinary study, two main contributions are proposed for the automated clinical decision-making state-of-the-art: (1) using the real-life data collected from thousands of ICU patients by healthcare professionals, three possibilities (recovery, mortality, and returning to the intensive care unit within 30 days) are predicted for patients in intensive care instead of just one possibility. (2) A novel feature extraction approach is proposed by the biomedical expert in our team. Four machine learning algorithms are applied to the finalized feature set to understand the difference between the binary and the multi-class classification problems. Obtained results reach 78% success, proving the possibility of developing better clinical decision-making mechanisms for ICUs.

Keywords

• Clinical decision making
• machine learning
• intensive care units
• mortality prediction
• re-admission prediction

Project Number

FHD-2021-3737

Thanks

This work was supported by the Office of Scientific Research Projects Coordination at Çanakkale Onsekiz Mart University, Grant number: FHD-2021-3737. Neural Stem Cell Institute is not responsible for the statements and results of the paper.

References

1. K. Cooley-Rieders, K. Zheng, Physician documentation matters. Using natural language processing to predict mortality in sepsis, Intelligence-Based Medicine 5 (2021) 100028 7 pages.
2. Y.-W. Lin, Y. Zhou, F. Faghri, M. J. Shaw, R. H. Campbell, Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory, Plos One 14 (7) (2019) e0218942 22 pages.
3. T.C. Sağlık Bakanlığı, Yoğun Bakım Skorlama, https://shgmkalitedb.saglik.gov.tr/TR, 9024/yogun-bakim-skorlama.html, Accessed: 2024-07-28.
4. H. Mumtaz, M. K. Ejaz, M. Tayyab, L. I. Vohra, S. Sapkota, M. Hasan, M. Saqib, APACHE scoring as an indicator of mortality rate in ICU patients: A cohort study, Annals of Medicine and Surgery 85 (3) (2023) 416–421.
5. R. Sarkar, C. Martin, H. Mattie, J. W. Gichoya, D. J. Stone, L. A. Celi, Performance of intensive care unit severity scoring systems across different ethnicities in the USA: A retrospective observational study, The Lancet Digital Health 3 (4) (2021) e241–e249.
6. H. Yang, L. Kuang, F. Xia, Multimodal temporal-clinical note network for mortality prediction, Journal of Biomedical Semantics 12 (2021) 1–14.
7. Centers for Disease Control and Prevention, National Center for Health Statistics, National Vital Statistics System, Provisional Mortality on CDC WONDER Online Database, http://wonder. cdc.gov/mcd-icd10-provisional.html, Accessed: 2024-07-24.
8. B. G. Pijls, S. Jolani, A. Atherley, R. T. Derckx, J. I. Dijkstra, G. H. Franssen, S. Hendriks, A. Richters, A. Venemans-Jellema, S. Zalpuri, M. P. Zeegers, Demographic risk factors for COVID-19 infection, severity, ICU admission and death: A meta-analysis of 59 studies, BMJ Open 11 (1) (2021) e044640 10 pages.

9. S. L. Hyland, M. Faltys, M. H¨user, X. Lyu, T. Gumbsch, C. Esteban, C. Bock, M. Horn, M. Moor, B. Rieck, M. Zimmerman, D. Bodenham, K. Borgwardt, G. R¨atsch, T. M. Merz, Early prediction of circulatory failure in the intensive care unit using machine learning, Nature Medicine 26 (3) (2020) 364–373.
10. A. Mohammed, F. Van Wyk, L. K. Chinthala, A. Khojandi, R. L. Davis, C. M. Coopersmith, R. Kamaleswaran, Temporal differential expression of physiomarkers predicts sepsis in critically ill adults, Shock 56 (1) (2021) 58–64.
11. J. Liu, J. Wu, S. Liu, M. Li, K. Hu, K. Li, Predicting mortality of patients with acute kidney injury in the ICU using XGBoost model, Plos One 16 (2) (2021) e0246306 11 pages.
12. J. Wang, L. Zhou, Y. Zhang, H. Zhang, Y. Xie, Z. Chen, B. Huang, K. Zeng, J. Lei, J. Mai, J. Pan, Y. Chen, J. Wang, Q. Guo, Minimum heart rate and mortality in critically ill myocardial infarction patients: An analysis of the MIMIC-III database, Annals of Translational Medicine 9 (6) (2021) 496 9 pages.
13. Y. Chen, Y. Du, C. Sun, W. Tan, Lactate is associated with increased 30-day mortality in critically ill patients with alcohol use disorder, International Journal of General Medicine 14 (2021) 2741– 2749.
14. Y. Ji, L. Li, Lower serum chloride concentrations are associated with increased risk of mortality in critically ill cirrhotic patients: An analysis of the MIMIC-III database, BMC Gastroenterology 21 (1) (2021) 200–208.
15. H. Yang, L. Kuang, F. Xia, Multimodal temporal-clinical note network for mortality prediction, Journal of Biomedical Semantics 12 (2021) 1–14.
16. S. Upadhyay, A. L. Stephenson, D. G. Smith, Readmission rates and their impact on hospital financial performance: A study of Washington hospitals, INQUIRY: The Journal of Health Care Organization, Provision, and Financing 56 (2019) 1–10.
17. Y.-W. Lin, Y. Zhou, F. Faghri, M. J. Shaw, R. H. Campbell, Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory, Plos One 14 (7) (2019) e0218942 22 pages.
18. M. Jamei, A. Nisnevich, E. Wetchler, S. Sudat, E. Liu, Predicting all-cause risk of 30-day hospital readmission using artificial neural networks, Plos One 12 (7) (2017) e0181173 14 pages.
19. R. Assaf, R. Jayousi, 30-day hospital readmission prediction using MIMIC data, in: 2020 IEEE 14th International Conference on Application of Information and Communication Technologies (AICT), IEEE, 2020, pp. 1–6.
20. U. Bayram, L. Benhiba, Determining a person’s suicide risk by voting on the short-term history of tweets for the clpsych 2021 shared task, in: Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access, 2021, pp. 81–86.
21. U. Bayram, J. Pestian, D. Santel, A. A. Minai, What’s in a word? Detecting partisan affiliation from word use in congressional speeches, in: 2019 International Joint Conference on Neural Networks (IJCNN), IEEE, 2019, pp. 1–8.
22. A. L. Goldberger, L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, H. E. Stanley, PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals, Circulation 101 (23) (2000) e215–e220.
23. A. Johnson, T. Pollard, R. Mark, MIMIC-III clinical database (version 1.4), PhysioNet 10 (2016) 1–2.
24. A. E. Johnson, T. J. Pollard, L. Shen, L.-W. H. Lehman, M. Feng, M. Ghassemi, B. Moody, P. Szolovits, L. Anthony Celi, R. G. Mark, MIMIC-III, a freely accessible critical care database, Scientific Data 3 (1) (2016) 1–9.
25. S. Lesser, S. Zakharkin, C. Louie, M. R. Escobedo, J. Whyte, T. Fulmer, Clinician knowledge and behaviors related to the 4Ms framework of age-friendly health systems, Journal of the American Geriatrics Society 70 (3) (2022) 789–800.
26. F. Zakirov, A. Krasilnikov, Age-related differences in decision-making process in the context of healthy aging, in: BIO Web of Conferences, Vol. 22, EDP Sciences, 2020, pp. 1–6.
27. Y. Zhu, J. Zhang, G. Wang, R. Yao, C. Ren, G. Chen, X. Jin, J. Guo, S. Liu, H. Zheng, Y. Chen, Q. Guo, L. Li, B. Du, X. Xi, W. Li, H. Huang, Y. Li, Q. Yu, Machine learning prediction models for mechanically ventilated patients: Analyses of the MIMIC-III database, Frontiers in medicine 8 (2021) 662340 9 pages.
28. F. Li, H. Xin, J. Zhang, M. Fu, J. Zhou, Z. Lian, Prediction model of in-hospital mortality in intensive care unit patients with heart failure: Machine learning-based, retrospective analysis of the MIMIC-III database, BMJ Open 11 (7) (2021) e044779 17 pages.
29. P. Domingos, A few useful things to know about machine learning, Communications of the ACM 55 (10) (2012) 78–87.
30. U. Bayram, Applying machine learning to online data?: Beware! computational social science requires care, in: Opportunities and Challenges for Computational Social Science Methods, IGI Global, 2022, pp. 100–125.
31. J. Pestian, D. Santel, M. Sorter, U. Bayram, B. Connolly, T. Glauser, M. DelBello, S. Tamang, K. Cohen, A machine learning approach to identifying changes in suicidal language, Suicide and Life-Threatening Behavior 50 (5) (2020) 939–947.
32. T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.
33. G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, T.-Y. Liu, Lightgbm: A highly efficient gradient boosting decision tree, Advances in Neural Information Processing Systems 30 (2017) 3149–3157.
34. T. Akiba, S. Sano, T. Yanase, T. Ohta, M. Koyama, Optuna: A next-generation hyperparameter optimization framework, in: Proceedings of the 25th ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, 2019, pp. 2623–2631.
35. T. Yang, Y. Ying, AUC maximization in the era of big data and AI: A survey, ACM Computing Surveys 55 (8) (2022) 1–37.
36. N. Ding, C. Guo, C. Li, Y. Zhou, X. Chai, An artificial neural networks model for early predicting in-hospital mortality in acute pancreatitis in MIMIC-III , BioMed Research International 2021 (1) (2021) Article ID 6638919 8 pages.
37. A. Pakbin, P. Rafi, N. Hurley, W. Schulz, M. H. Krumholz, J. B. Mortazavi, Prediction of ICU readmissions using data at patient discharge, in: 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC), IEEE, 2018, pp. 4932–4935.