Prediction of healthcare-associated infections in adult ICU patients using artificial intelligence tools

• Vitor Pires Silva e Souza UFG
• Deborah Silva Alves Fernandes UFG
• Silvana L. V. dos Santos UFG
• Márcio Giovane Cunha Fernandes UEG

DOI: https://doi.org/10.5753/sbcas.2024.2778

Abstract

This article explores the use of artificial intelligence techniques to predict Healthcare-Associated Infections (HAIs). The study, based on data from a reference teaching hospital collected between January and August 2021, investigates which machine learning algorithms are most effective in predicting HAIs. Classification algorithms were used, such as Random Forest, Decision Tree, Gradient Boosting, Adaboost and XGboost. The metric of the area under the ROC curve (Receiver Operating Characteristic) and StratifiedKFold were used to measure the performance of the models. The results for Random Forest, Decision Tree, Adaboost, Gradient Boosting and XGboost were 0.91; 0.78; 0.81; 0.92; and 0.87, respectively. With this information, the study contributes to the development of strategies that reduce the risks associated with hospital infections.

References

Ali, J., Khan, R., Ahmad, N., and Maqsood, I. (2012). Random forests and decision trees. International Journal of Computer Science Issues (IJCSI), 9(5):272.

Assaf, D., Gutman, Y., Neuman, Y., Segal, G., Amit, S., Gefen-Halevi, S., Shilo, N., Epstein, A., Mor-Cohen, R., Biber, A., et al. (2020). Utilization of machine-learning models to accurately predict the risk for critical covid-19. Internal and emergency medicine, 15:1435–1443.

Dixit, R. R. (2022). Predicting fetal health using cardiotocograms: A machine learning approach. Journal of Advanced Analytics in Healthcare Management, 6(1):43–57.

Freire, D. L., de Oliveira, R., Carmelo Filho, J., et al. (2020). Machine learning applied in sars-cov-2 covid 19 screening using clinical analysis parameters. IEEE Latin Am. Trans, 100(1).

Pessoa, S. M. B., Oliveira, B. S. d. S., Santos, W. G. d., Oliveira, A. N. M., Camargo, M. S., Matos, D. L. A. B. d., Silva, M. M. L., Medeiros, C. C. d. Q., Coelho, C. S. d. S., Andrade Neto, J. d. S., et al. (2023). Predição de choque séptico e hipovolêmico em pacientes de unidade de terapia intensiva com o uso de machine learning. Revista Brasileira de Terapia Intensiva, 34:477–483.

Prakash, K. B., Imambi, S. S., Ismail, M., Kumar, T. P., and Pawan, Y. (2020). Analysis, prediction and evaluation of covid-19 datasets using machine learning algorithms. International Journal, 8(5):2199–2204.

Qader, W., M. Ameen, M., and Ahmed, B. (2019). An overview of bag of words;importance, implementation, applications, and challenges. pages 200–204.

Raut, K., Patil, J., Wade, S., and Tinsu, J. (2022). Mental health and personality determination using machine learning. In 2022 7th International Conference on Communication and Electronics Systems (ICCES), pages 1231–1236. IEEE.