Predicting outcomes for patients hospitalized with COVID-19
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1362Keywords:
Explainable, COVID-19 Outcome, Machine LearningAbstract
Objective: This study aims to evaluate the effectiveness of Machine Learning (ML) models in predicting outcomes for patients diagnosed with COVID-19 considering data from medical records and exams. Method: Several ML algorithms and Explainable techniques were investigated on clinical evolution data of patients admitted to the Pedro Ernesto University Hospital (HUPE) during the years 2020 and 2021. Results: The Random Forest model was found to be the most efficient, with an accuracy of 74% in the validation dataset. In addition, techniques based on Explainable Artificial Intelligence show that changes in the number of rods and the prescription of noradrenaline were the variables that had the greatest impact on predicting outcomes. Conclusion: The results encourage healthcare institutions to use methods based on decision support to organize or even prioritize care for their patients
References
Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: Data mining, inference, and prediction. In Springer, chapter 15; 2009.
Quinlan J R. Induction of decision trees. Machine Learning. 1986;1(1):81–106.
Breiman L. Random Forests. Machine Learning. 2001; 45 (1):5–32.
Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD’16, New York, NY, USA. Association for Computing Machinery. 2016; 785–794.
Fukushima K, Miyake S. Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Visual Pattern Recognition. Competition and Cooperation in Neural Nets. Lecture Notes in Biomathematics. v 45. Springer. 1986;267–285.
Haykin S. Redes Neurais. 2ed. Bookman; 2001.
Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R., editors, Advances in Neural Information Processing Systems. Curran Associates, Inc.; v.30; 2017.
Silva AO, Santos BS, Tondato R, Lima RHP. Uso de machine learning para previsão da evolução de casos de srag incluindo casos de COVID-19 considerando variáveis clínicas e demográficas. Trabalho de conclusão de curso. Universidade Tecnológica Federal do Paraná (RIUT); 2021.
Wollenstein-Betech S, Silva AAB, Fleck JL, Cassandras CG, Paschalidis IC. Physiological and socioeconomic characteristics predict COVID-19 mortality and resource utilization in Brazil. PLOS ONE; 2020;15(10):e0240346.
Hu C, Liu Z, Jiang Y, Shi O, Zhang X, Xu K, Suo C, Wang Q, Song Y, Yu K, Mao X, Wu X, Wu M, Shi T, Jiang W, Mu L, Tully DC, Xu L, Jin L, Li S, Tao X, Zhang T, Chen X. Early prediction of mortality risk among patients with severe COVID-19, using machine learning. International Journal of Epidemiology. 2020; 49(6):1918–1929.
Hastie T, tibshirani R. Generalized Additive Models. Chapman & Hall/CRC Monographs on Statistics & Applied Probability. Taylor & Francis; 1990.
Stone M. Cross-Validatory Choice and Assessment of Statistical Predictions". Journal of the Royal Statistical Society, Series B (Methodological). 1974; 36 (2): 111–147.
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research. 2002;16: 321–357.
Goutte C, Gaussier E. A probabilistic interpretation of precision, recall and f-score, with implication for evaluation. In Losada, D. E. and Fernández-Luna, J. M., editors, Advances in Information Retrieval. Springer Berlin Heidelberg. 2005; 345–359.
Liu H, Motoda, H. Perspectives of Feature Selection. Springer US, Boston, MA. 1998; 17-41.
Holanda WD, Silva LC, César Sobrinho AAC. Estratégias Preditivas na Detecção do Agravamento do Quadro Clínico de Pacientes com COVID-19: Uma Revisão de Escopo J. Health Inform. 2021 Outubro-Dezembro; 13(4): 128-32.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
