EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Use of machine learning to identify protective factors for death from COVID-19 in the ICU: a retrospective study

Lander Dos Santos, Lincoln Luis Silva, Fernando Castilho Pelloso, Vinicius Maia, Constanza Pujals, Deise Helena Borghesan, Maria Dalva Carvalho, Raíssa Bocchi Pedroso, Sandra Marisa Pelloso

PeerJ · 2024

DOI: 10.7717/peerj.17428 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ, 2024. Verfasst von Lander Dos Santos und 8 weiteren Autor:innen. Beteiligte Einrichtung: State University of Maringá, Graduate Program in Health Sciences, Maringá, Paraná, Brazil. Hauptthemen laut MEDLINE: COVID-19, Machine Learning, Intensive Care Units, SARS-CoV-2. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior–Brasil (CAPES), The Coordenação de Aperfeiçoamento de Pessoal de Nível Superior–Brasil (CAPES)–Finance Code 001.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Patients in serious condition due to COVID-19 often require special care in intensive care units (ICUs). This disease has affected over 758 million people and resulted in 6.8 million deaths worldwide. Additionally, the progression of the disease may vary from individual to individual, that is, it is essential to identify the clinical parameters that indicate a good prognosis for the patient. Machine learning (ML) algorithms have been used for analyzing complex medical data and identifying prognostic indicators. However, there is still an urgent need for a model to elucidate the predictors related to patient outcomes. Therefore, this research aimed to verify, through ML, the variables involved in the discharge of patients admitted to the ICU due to COVID-19.

Methods

In this study, 126 variables were collected with information on demography, hospital length stay and outcome, chronic diseases and tumors, comorbidities and risk factors, complications and adverse events, health care, and vital indicators of patients admitted to an ICU in southern Brazil. These variables were filtered and then selected by a ML algorithm known as decision trees to identify the optimal set of variables for predicting patient discharge using logistic regression. Finally, a confusion matrix was performed to evaluate the model’s performance for the selected variables.

Results

Of the 532 patients evaluated, 180 were discharged: female (16.92%), with a central venous catheter (23.68%), with a bladder catheter (26.13%), and with an average of 8.46- and 23.65-days using bladder catheter and submitted to mechanical ventilation, respectively. In addition, the chances of discharge increase by 14% for each additional day in the hospital, by 136% for female patients, 716% when there is no bladder catheter, and 737% when no central venous catheter is used. However, the chances of discharge decrease by 3% for each additional year of age and by 9% for each other day of mechanical ventilation. The performance of the training data presented a balanced accuracy of 0.81, sensitivity of 0.74, specificity of 0.88, and the kappa value was 0.64. The test performance had a balanced accuracy of 0.85, sensitivity 0.75, specificity 0.95, and kappa value of 0.73. The McNemar test found that there were no significant differences in the error rates in the training and test data, suggesting good classification. This work showed that female, the absence of a central venous catheter and bladder catheter, shorter mechanical ventilation, and bladder catheter duration were associated with a greater chance of hospital discharge. These results may help develop measures that lead to a good prognosis for the patient.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

COVID-19Machine LearningIntensive Care UnitsSARS-CoV-2HumansFemaleMaleRetrospective StudiesMiddle AgedBrazilAgedProtective FactorsAdultRisk FactorsPrognosisPatient DischargeLength of Stay

Stichwörter der Autor:innen

COVID-19Critical careEpidemiologyIntensive care unityMachine learning

Autor:innen und Institutionen

  • State University of Maringá, Graduate Program in Health Sciences, Maringá, Paraná, Brazil.
  • Department of Emergency Medicine, Duke University School of Medicine, Durham, NC, United States of America.
  • Department of Medicine, Federal University of Paraná, Curitiba, Paraná, Brazil.
  • Unicesumar, Maringá, Paraná, Brazil.
  • Union of Catholic Colleges of Mato Grosso, Cuiabá, Mato Grosso, Brazil.

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior–Brasil (CAPES)
  • The Coordenação de Aperfeiçoamento de Pessoal de Nível Superior–Brasil (CAPES)–Finance Code 001

Zitieren

APA

Dos Santos, L., Silva, L. L., Pelloso, F. C., Maia, V., Pujals, C., Borghesan, D. H., Carvalho, M. D., Pedroso, R. B., & Pelloso, S. M. (2024). Use of machine learning to identify protective factors for death from COVID-19 in the ICU: a retrospective study. PeerJ. https://doi.org/10.7717/peerj.17428

Vancouver

Dos Santos L, Silva LL, Pelloso FC, Maia V, Pujals C, Borghesan DH, et al. Use of machine learning to identify protective factors for death from COVID-19 in the ICU: a retrospective study. PeerJ. 2024. doi:10.7717/peerj.17428

BibTeX
@article{DosSantos2024,
  author = {Dos Santos, Lander and Silva, Lincoln Luis and Pelloso, Fernando Castilho and Maia, Vinicius and Pujals, Constanza and Borghesan, Deise Helena and Carvalho, Maria Dalva and Pedroso, Raíssa Bocchi and Pelloso, Sandra Marisa},
  title = {Use of machine learning to identify protective factors for death from COVID-19 in the ICU: a retrospective study},
  journal = {PeerJ},
  year = {2024},
  doi = {10.7717/peerj.17428}
}
Kostenlos starten →