Page 58 - AIH-1-3

Artificial Intelligence in Health Predicting mortality in COVID-19 using ML

doi: 10.2307/1403797 doi: 10.1016/j.imu.2022.101023
36. Fitton D. Evaluating Models in Azure Machine Learning 46. Al-Shaikh A, Mahafzah BA, Alshraideh M. Hybrid harmony
(Part 1: Classification). Adatis; 2020. Available from: search algorithm for social network contact tracing of
https://adatis.co.uk/evaluating-models-in-azure- COVID-19. Soft Comput. 2023;27(6):3343-3365.
machine-learning-part-1-classification [Last accessed on
2023 Dec 18]. doi: 10.1007/s00500-021-05948-2
37. Classification: ROC Curve and AUC. Machine Learning. 47. Mandala SK. Unveiling the unborn: Advancing fetal health
Google for Developers. Google Machine Learning Education; classification through machine learning. Artif Intell Health.
2022. Available from: https://developers.google.com/ 2023;1(1):2121.
machine-learning/crash-course/classification/roc-and-auc doi: 10.36922/aih.2121
[Last accessed on 2023 Dec 18]
48. Al-Tawil M, Mahafzah BA, Al Tawil A, Aljarah I. Bio-
38. Josephus BO, Nawir AH, Wijaya E, Moniaga JV, Ohyver M. inspired machine learning approach to type 2 diabetes
Predict mortality in patients infected with COVID-19 virus detection. Symmetry (Basel). 2023;15(3):764.
based on observed characteristics of the patient using
logistic regression. Procedia Comput Sci. 2021;179:871-877. doi: 10.3390/sym15030764
doi: 10.1016/j.procs.2021.01.076 49. Umar BU, Ajao LA, Dogo EM, Ajao FJ, Atama M. Artificial
intelligence model for prediction of cardiovascular disease:
39. Yan L, Zhang HT, Goncalves J, et al. An interpretable
mortality prediction model for COVID-19 patients. Nat An empirical study. Artif Intell Health. 2023;1(1):1746.
Mach Intell. 2020;2(5):283-288. doi: 10.36922/aih.1746
doi: 10.1038/s42256-020-0180-7 50. Chawla NV, Bowyer KW, Hall LO, Philip Kegelmeyer W.
40. Pourhomayoun M, Shakibi M. Predicting mortality risk in SMOTE: Synthetic minority over-sampling technique.
patients with COVID-19 using machine learning to help J Artif Intell Res. 2002;30(2):321-357.
medical decision-making. Smart Health. 2021;20:100178. 51. Rosenblatt F. The perceptron: A probabilistic model for
doi: 10.1016/j.smhl.2020.100178 information storage and organization in the brain. Psychol
Rev. 1958;65(6):386-408.
41. Naseem M, Arshad H, Hashmi SA, Irfan F, Ahmed FS.
Predicting mortality in SARS-COV-2 (COVID-19) positive doi: 10.1037/h0042519
patients in the inpatient setting using a novel deep neural 52. Abuqaddom I, Mahafzah BA, Faris H. Oriented stochastic
network. Int J Med Inform. 2021;154:104556.
loss descent algorithm to train very deep multi-layer neural
doi: 10.1016/j.ijmedinf.2021.104556 networks without vanishing gradients. Knowl Based Syst.
2021;230:107391.
42. Chadaga K, Prabhu S, Umakanth S, et al. COVID-19
mortality prediction among patients using epidemiological doi: 10.1016/j.knosys.2021.107391
parameters: An ensemble machine learning approach. Eng
Sci. 2021;16:221-33. 53. Neural Network Models (supervised); 2021. Available from:
https://scikit-learn.org/stable/modules/neural_networks_
doi: 10.30919/es8d579 supervised.html [Last accessed on 2023 Dec 18].
43. Franklin MR. Mexico COVID-19 Clinical Data; 2019. Available 54. Cover TM, Hart PE. Nearest neighbor pattern classification.
from: https://www.kaggle.com/datasets/marianarfranklin/ IEEE Trans Inf Theory. 1967;13(1):21-27.
mexico-covid19-clinical-data [Last accessed on 2023 Dec 18].
doi: 10.1109/TIT.1967.1053964
44. Rai N, Kaushik N, Kumar D, Raj C, Ali A. Mortality
prediction of COVID-19 patients using soft voting classifier. 55. Kubat M. An Introduction to Machine Learning. Berlin:
Int J Cogn Comput Eng. 2022;3:172-179. Springer; 2017.

doi: 10.1016/j.ijcce.2022.09.001 doi: 10.1007/978-3-319-63913-0
45. Bárcenas R, Fuentes-García R. Risk assessment in COVID- 56. Glossary of Common Terms and API; 2007. Available from:
19 patients: A multiclass classification approach. Inform Med https://scikit-learn.org/stable/glossary.html#term-feature_
Unlocked. 2022;32:101023. importances [Last accessed on 2023 Dec 18].

Volume 1 Issue 3 (2024) 52 doi: 10.36922/aih.2591