Machine learning in predicting respiratory failure in patients with COVID-19 pneumonia?Challenges, strengths, and opportunities in a global health emergency. Ferrari, D., Milic, J., Tonelli, R., Ghinelli, F., Meschiari, M., Volpi, S., Faltoni, M., Franceschi, G., Iadisernia, V., Yaacoub, D., Ciusa, G., Bacca, E., Rogati, C., Tutone, M., Burastero, G., Raimondi, A., Menozzi, M., Franceschini, E., Cuomo, G., Corradi, L., Orlando, G., Santoro, A., Digaetano, M., Puzzolante, C., Carli, F., Borghi, V., Bedini, A., Fantini, R., Tabb�, L., Castaniere, I., Busani, S., Clini, E., Girardis, M., Sarti, M., Cossarizza, A., Mussini, C., Mandreoli, F., Missier, P., & Guaraldi, G. PLOS ONE, 15(11):1–14, 2020.
Machine learning in predicting respiratory failure in patients with COVID-19 pneumonia?Challenges, strengths, and opportunities in a global health emergency [link]Paper  doi  abstract   bibtex   6 downloads  
Aims The aim of this study was to estimate a 48 hour prediction of moderate to severe respiratory failure, requiring mechanical ventilation, in hospitalized patients with COVID-19 pneumonia. Methods This was an observational prospective study that comprised consecutive patients with COVID-19 pneumonia admitted to hospital from 21 February to 6 April 2020. The patients? medical history, demographic, epidemiologic and clinical data were collected in an electronic patient chart. The dataset was used to train predictive models using an established machine learning framework leveraging a hybrid approach where clinical expertise is applied alongside a data-driven analysis. The study outcome was the onset of moderate to severe respiratory failure defined as PaO2/FiO2 ratio \textless150 mmHg in at least one of two consecutive arterial blood gas analyses in the following 48 hours. Shapley Additive exPlanations values were used to quantify the positive or negative impact of each variable included in each model on the predicted outcome. Results A total of 198 patients contributed to generate 1068 usable observations which allowed to build 3 predictive models based respectively on 31-variables signs and symptoms, 39-variables laboratory biomarkers and 91-variables as a composition of the two. A fourth ?boosted mixed model? included 20 variables was selected from the model 3, achieved the best predictive performance (AUC = 0.84) without worsening the FN rate. Its clinical performance was applied in a narrative case report as an example. Conclusion This study developed a machine model with 84% prediction accuracy, which is able to assist clinicians in decision making process and contribute to develop new analytics to improve care at high technology readiness levels.
@article{ferrari_machine_2020,
	title = {Machine learning in predicting respiratory failure in patients with {COVID}-19 pneumonia?{Challenges}, strengths, and opportunities in a global health emergency},
	volume = {15},
	url = {https://doi.org/10.1371/journal.pone.0239172},
	doi = {10.1371/journal.pone.0239172},
	abstract = {Aims The aim of this study was to estimate a 48 hour prediction of moderate to severe respiratory failure, requiring mechanical ventilation, in hospitalized patients with COVID-19 pneumonia. Methods This was an observational prospective study that comprised consecutive patients with COVID-19 pneumonia admitted to hospital from 21 February to 6 April 2020. The patients? medical history, demographic, epidemiologic and clinical data were collected in an electronic patient chart. The dataset was used to train predictive models using an established machine learning framework leveraging a hybrid approach where clinical expertise is applied alongside a data-driven analysis. The study outcome was the onset of moderate to severe respiratory failure defined as PaO2/FiO2 ratio {\textbackslash}textless150 mmHg in at least one of two consecutive arterial blood gas analyses in the following 48 hours. Shapley Additive exPlanations values were used to quantify the positive or negative impact of each variable included in each model on the predicted outcome. Results A total of 198 patients contributed to generate 1068 usable observations which allowed to build 3 predictive models based respectively on 31-variables signs and symptoms, 39-variables laboratory biomarkers and 91-variables as a composition of the two. A fourth ?boosted mixed model? included 20 variables was selected from the model 3, achieved the best predictive performance (AUC = 0.84) without worsening the FN rate. Its clinical performance was applied in a narrative case report as an example. Conclusion This study developed a machine model with 84\% prediction accuracy, which is able to assist clinicians in decision making process and contribute to develop new analytics to improve care at high technology readiness levels.},
	number = {11},
	journal = {PLOS ONE},
	author = {Ferrari, Davide and Milic, Jovana and Tonelli, Roberto and Ghinelli, Francesco and Meschiari, Marianna and Volpi, Sara and Faltoni, Matteo and Franceschi, Giacomo and Iadisernia, Vittorio and Yaacoub, Dina and Ciusa, Giacomo and Bacca, Erica and Rogati, Carlotta and Tutone, Marco and Burastero, Giulia and Raimondi, Alessandro and Menozzi, Marianna and Franceschini, Erica and Cuomo, Gianluca and Corradi, Luca and Orlando, Gabriella and Santoro, Antonella and Digaetano, Margherita and Puzzolante, Cinzia and Carli, Federica and Borghi, Vanni and Bedini, Andrea and Fantini, Riccardo and Tabb�, Luca and Castaniere, Ivana and Busani, Stefano and Clini, Enrico and Girardis, Massimo and Sarti, Mario and Cossarizza, Andrea and Mussini, Cristina and Mandreoli, Federica and Missier, Paolo and Guaraldi, Giovanni},
	year = {2020},
	pages = {1--14},
}
Downloads: 6
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021