Machine learning based predictors for COVID-19 disease severity
Abstract Predictors of the need for intensive care and mechanical ventilation can help healthcare systems in planning for surge capacity for COVID-19. We used socio-demographic data, clinical data, and blood panel profile data at the time of initial presentation to develop machine learning algorithm...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/98e212396cce4319a5ca65c1b2b5d377 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:98e212396cce4319a5ca65c1b2b5d377 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:98e212396cce4319a5ca65c1b2b5d3772021-12-02T13:34:57ZMachine learning based predictors for COVID-19 disease severity10.1038/s41598-021-83967-72045-2322https://doaj.org/article/98e212396cce4319a5ca65c1b2b5d3772021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83967-7https://doaj.org/toc/2045-2322Abstract Predictors of the need for intensive care and mechanical ventilation can help healthcare systems in planning for surge capacity for COVID-19. We used socio-demographic data, clinical data, and blood panel profile data at the time of initial presentation to develop machine learning algorithms for predicting the need for intensive care and mechanical ventilation. Among the algorithms considered, the Random Forest classifier performed the best with $$\text {AUC} = 0.80$$ AUC = 0.80 for predicting ICU need and $$\text {AUC} = 0.82$$ AUC = 0.82 for predicting the need for mechanical ventilation. We also determined the most influential features in making this prediction, and concluded that all three categories of data are important. We determined the relative importance of blood panel profile data and noted that the AUC dropped by 0.12 units when this data was not included, thus indicating that it provided valuable information in predicting disease severity. Finally, we generated RF predictors with a reduced set of five features that retained the performance of the predictors trained on all features. These predictors, which rely only on quantitative data, are less prone to errors and subjectivity.Dhruv PatelVikram KherBhushan DesaiXiaomeng LeiSteven CenNeha NandaAli GholamrezanezhadVinay DuddalwarBino VargheseAssad A OberaiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-7 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Dhruv Patel Vikram Kher Bhushan Desai Xiaomeng Lei Steven Cen Neha Nanda Ali Gholamrezanezhad Vinay Duddalwar Bino Varghese Assad A Oberai Machine learning based predictors for COVID-19 disease severity |
| description |
Abstract Predictors of the need for intensive care and mechanical ventilation can help healthcare systems in planning for surge capacity for COVID-19. We used socio-demographic data, clinical data, and blood panel profile data at the time of initial presentation to develop machine learning algorithms for predicting the need for intensive care and mechanical ventilation. Among the algorithms considered, the Random Forest classifier performed the best with $$\text {AUC} = 0.80$$ AUC = 0.80 for predicting ICU need and $$\text {AUC} = 0.82$$ AUC = 0.82 for predicting the need for mechanical ventilation. We also determined the most influential features in making this prediction, and concluded that all three categories of data are important. We determined the relative importance of blood panel profile data and noted that the AUC dropped by 0.12 units when this data was not included, thus indicating that it provided valuable information in predicting disease severity. Finally, we generated RF predictors with a reduced set of five features that retained the performance of the predictors trained on all features. These predictors, which rely only on quantitative data, are less prone to errors and subjectivity. |
| format |
article |
| author |
Dhruv Patel Vikram Kher Bhushan Desai Xiaomeng Lei Steven Cen Neha Nanda Ali Gholamrezanezhad Vinay Duddalwar Bino Varghese Assad A Oberai |
| author_facet |
Dhruv Patel Vikram Kher Bhushan Desai Xiaomeng Lei Steven Cen Neha Nanda Ali Gholamrezanezhad Vinay Duddalwar Bino Varghese Assad A Oberai |
| author_sort |
Dhruv Patel |
| title |
Machine learning based predictors for COVID-19 disease severity |
| title_short |
Machine learning based predictors for COVID-19 disease severity |
| title_full |
Machine learning based predictors for COVID-19 disease severity |
| title_fullStr |
Machine learning based predictors for COVID-19 disease severity |
| title_full_unstemmed |
Machine learning based predictors for COVID-19 disease severity |
| title_sort |
machine learning based predictors for covid-19 disease severity |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/98e212396cce4319a5ca65c1b2b5d377 |
| work_keys_str_mv |
AT dhruvpatel machinelearningbasedpredictorsforcovid19diseaseseverity AT vikramkher machinelearningbasedpredictorsforcovid19diseaseseverity AT bhushandesai machinelearningbasedpredictorsforcovid19diseaseseverity AT xiaomenglei machinelearningbasedpredictorsforcovid19diseaseseverity AT stevencen machinelearningbasedpredictorsforcovid19diseaseseverity AT nehananda machinelearningbasedpredictorsforcovid19diseaseseverity AT aligholamrezanezhad machinelearningbasedpredictorsforcovid19diseaseseverity AT vinayduddalwar machinelearningbasedpredictorsforcovid19diseaseseverity AT binovarghese machinelearningbasedpredictorsforcovid19diseaseseverity AT assadaoberai machinelearningbasedpredictorsforcovid19diseaseseverity |
| _version_ |
1718392750416592896 |