Page 63 - AIH-2-2

Artificial Intelligence in Health Predicting ICU mortality: A stacked ensemble model

ICU: Introducing a deep learning approach in healthcare. doi: 10.1038/s41746-021-00456-x
In: Maglogiannis I, liadis L, Macintyre J, Avlonitis M, 10. Choi MH, Kim D, Choi EJ, et al. Mortality prediction of
Papaleonidas A, editors. IFIP Advances in Information and patients in intensive care units using machine learning
Communication Technology. Vol. 711. Switzerland: Springer algorithms based on electronic health records. Sci
Nature; 2024. p. 17-30. Rep. 2022;12(1):7180.
doi: 10.1007/978-3-031-63211-2_2 doi: 10.1038/s41598-022-11226-4
2. Moreno RP, Metnitz PGH, et al. SAPS 3-From evaluation of 11. Bi S, Chen S, Li J, Gu J. Machine learning-based prediction
the patient to evaluation of the intensive care unit. Part 2: of in-hospital mortality for post cardiovascular surgery
Development of a prognostic model for hospital mortality at patients admitting to intensive care unit: A retrospective
ICU admission. Intensive Care Med. 2005;31(10):1345-1355. observational cohort study based on a large multi-center
doi: 10.1007/s00134-005-2762-6 critical care database. Comput Methods Programs Biomed.
2022;226:107115.
3. Zimmerman JE, Kramer AA, McNair DS, Malila FM.
Acute physiology and chronic health evaluation (APACHE) doi: 10.1016/j.cmpb.2022.107115
IV: Hospital mortality assessment for today’s critically ill 12. Huang B, Liang D, Zou R, et al. Mortality prediction for
patients. Crit Care Med. 2006;34(5):1297-310. patients with acute respiratory distress syndrome based on
machine learning: A population-based study. Ann Transl
doi: 10.1097/01.CCM.0000215112.84523.F0
Med. 2021;9(9):794.
4. Fadja AN, Fraccaroli M, Bizzarri A, Mazzuchelli G,
Lamma E. Neural-symbolic ensemble learning for early- doi: 10.21037/atm-20-6624
stage prediction of critical state of covid-19 patients. Med 13. Chiu CC, Wu CM, Chien TN, Kao LJ, Li C, Jiang HL.
Biol Eng Comput. 2022;60(12):3461-3474. Applying an improved stacking ensemble model to predict
the mortality of ICU patients with heart failure. J Clin Med.
doi: 10.1007/s11517-022-02674-1
2022;11(21):6460.
5. Ho KM, Dobb GJ, Knuiman M, Finn J, Lee KY, Webb doi: 10.3390/jcm11216460
SAR. A comparison of admission and worst 24-hour Acute
Physiology and Chronic Health Evaluation II scores in 14. Yang J, Peng H, Luo Y, Zhu T, Xie L. Explainable ensemble
predicting hospital mortality: A retrospective cohort study. machine learning model for prediction of 28-day mortality
Crit Care. 2005;10(1):R4. risk in patients with sepsis-associated acute kidney injury.
Front Med (Lausanne). 2023;10:1165129.
doi: 10.1186/cc3913
doi: 10.3389/fmed.2023.1165129
6. Falcão ALE, Barros AGA, Bezerra AAM, et al. The
prognostic accuracy evaluation of SAPS 3, SOFA and 15. Chassagnon G, Vakalopoulou M, Battistella E, et al.
APACHE II scores for mortality prediction in the surgical AI-driven quantification, staging and outcome prediction of
ICU: An external validation study and decision-making COVID-19 pneumonia. Med Image Anal. 2021;67:101860.
analysis. Ann Intensive Care. 2019;9(1):18. doi: 10.1016/j.media.2020.101860
doi: 10.1186/s13613-019-0488-9 16. Alabbad DA, Almuhaideb AM, Alsunaidi SJ, et al. Machine
learning model for predicting the length of stay in the
7. Polderman KH, Girbes ARJ, Thijs LG, Strack van intensive care unit for Covid-19 patients in the eastern
Schijndel RJM. Accuracy and reliability of APACHE II province of Saudi Arabia. Inform Med Unlocked. 2022;30.
scoring in two intensive care units problems and pitfalls in
the use of APACHE II and suggestions for improvement. doi: 10.1016/j.imu.2022.100937
Anaesthesia. 2001;56(1):47-50. 17. Alzubaidi L, Zhang J, Humaidi AJ, et al. Review of deep
doi: 10.1046/j.1365-2044.2001.01763.x learning: Concepts, CNN architectures, challenges,
applications, future directions. J Big Data. 2021;8(1):100937.
8. Sedloň P, Kameník L, Škvařil J, Malý M, Táborský M,
Zavoral M. Comparison of the accuracy and correctness doi: 10.1186/s40537-021-00444-8
of mortality estimates for intensive care unit patients in 18. Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG,
internal clinics of the Czech Republic using APACHE II, Badawi O. The eICU collaborative research database, a freely
APACHE IV, SAPS 3 and MPMoIII models. Med Glas available multi-center database for critical care research. Sci
(Zenica). 2016;13(2):82-89. Data. 2018;5:180178.
doi: 10.17392/860-16 doi: 10.1038/sdata.2018.178
9. Subudhi S, Verma A, Patel AB, et al. Comparing machine 19. Bach M, Werner A, Palt M. The proposal of undersampling
learning algorithms for predicting ICU admission and method for learning from imbalanced datasets. Procedia
mortality in COVID-19. NPJ Digit Med. 2021;4(1):87. Comput Sci. 2019;159:125-134.

Volume 2 Issue 2 (2025) 57 doi: 10.36922/aih.4981