Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables
Background This study aimed to develop a deep-learning model and a risk-score system using clinical variables to predict intensive care unit (ICU) admission and in-hospital mortality in COVID-19 patients. Methods This retrospective study consisted of 5,766 persons-under-investigation for COVID-19 be...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2020-11-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/10337.pdf |
| _version_ | 1827608897779662848 |
|---|---|
| author | Xiaoran Li Peilin Ge Jocelyn Zhu Haifang Li James Graham Adam Singer Paul S. Richman Tim Q. Duong |
| author_facet | Xiaoran Li Peilin Ge Jocelyn Zhu Haifang Li James Graham Adam Singer Paul S. Richman Tim Q. Duong |
| author_sort | Xiaoran Li |
| collection | DOAJ |
| description | Background This study aimed to develop a deep-learning model and a risk-score system using clinical variables to predict intensive care unit (ICU) admission and in-hospital mortality in COVID-19 patients. Methods This retrospective study consisted of 5,766 persons-under-investigation for COVID-19 between 7 February 2020 and 4 May 2020. Demographics, chronic comorbidities, vital signs, symptoms and laboratory tests at admission were collected. A deep neural network model and a risk-score system were constructed to predict ICU admission and in-hospital mortality. Prediction performance used the receiver operating characteristic area under the curve (AUC). Results The top ICU predictors were procalcitonin, lactate dehydrogenase, C-reactive protein, ferritin and oxygen saturation. The top mortality predictors were age, lactate dehydrogenase, procalcitonin, cardiac troponin, C-reactive protein and oxygen saturation. Age and troponin were unique top predictors for mortality but not ICU admission. The deep-learning model predicted ICU admission and mortality with an AUC of 0.780 (95% CI [0.760–0.785]) and 0.844 (95% CI [0.839–0.848]), respectively. The corresponding risk scores yielded an AUC of 0.728 (95% CI [0.726–0.729]) and 0.848 (95% CI [0.847–0.849]), respectively. Conclusions Deep learning and the resultant risk score have the potential to provide frontline physicians with quantitative tools to stratify patients more effectively in time-sensitive and resource-constrained circumstances. |
| first_indexed | 2024-03-09T07:22:14Z |
| format | Article |
| id | doaj.art-b8991c5d7f0545b6854456af7fa8b5a9 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T07:22:14Z |
| publishDate | 2020-11-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-b8991c5d7f0545b6854456af7fa8b5a92023-12-03T07:15:19ZengPeerJ Inc.PeerJ2167-83592020-11-018e1033710.7717/peerj.10337Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variablesXiaoran Li0Peilin Ge1Jocelyn Zhu2Haifang Li3James Graham4Adam Singer5Paul S. Richman6Tim Q. Duong7Department of Radiology, Renaissance School of Medicine, Stony Brook University, New York, Stony Brook, NY, USADepartment of Radiology, Renaissance School of Medicine, Stony Brook University, New York, Stony Brook, NY, USADepartment of Radiology, Renaissance School of Medicine, Stony Brook University, New York, Stony Brook, NY, USADepartment of Radiology, Renaissance School of Medicine, Stony Brook University, New York, Stony Brook, NY, USADepartment of Radiology, Renaissance School of Medicine, Stony Brook University, New York, Stony Brook, NY, USADepartment of Emergency Medicine, Renaissance School of Medicine, Stony Brook University, New York, Stony Brook, NY, USADepartment of Medicine, Renaissance School of Medicine, Stony Brook University, New York, Stony Brook, NY, USADepartment of Radiology, Albert Einstein College of Medicine, Bronx, NY, USABackground This study aimed to develop a deep-learning model and a risk-score system using clinical variables to predict intensive care unit (ICU) admission and in-hospital mortality in COVID-19 patients. Methods This retrospective study consisted of 5,766 persons-under-investigation for COVID-19 between 7 February 2020 and 4 May 2020. Demographics, chronic comorbidities, vital signs, symptoms and laboratory tests at admission were collected. A deep neural network model and a risk-score system were constructed to predict ICU admission and in-hospital mortality. Prediction performance used the receiver operating characteristic area under the curve (AUC). Results The top ICU predictors were procalcitonin, lactate dehydrogenase, C-reactive protein, ferritin and oxygen saturation. The top mortality predictors were age, lactate dehydrogenase, procalcitonin, cardiac troponin, C-reactive protein and oxygen saturation. Age and troponin were unique top predictors for mortality but not ICU admission. The deep-learning model predicted ICU admission and mortality with an AUC of 0.780 (95% CI [0.760–0.785]) and 0.844 (95% CI [0.839–0.848]), respectively. The corresponding risk scores yielded an AUC of 0.728 (95% CI [0.726–0.729]) and 0.848 (95% CI [0.847–0.849]), respectively. Conclusions Deep learning and the resultant risk score have the potential to provide frontline physicians with quantitative tools to stratify patients more effectively in time-sensitive and resource-constrained circumstances.https://peerj.com/articles/10337.pdfMachine learningCoronavirusPneumoniaSARS-CoV-2Prediction model |
| spellingShingle | Xiaoran Li Peilin Ge Jocelyn Zhu Haifang Li James Graham Adam Singer Paul S. Richman Tim Q. Duong Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables PeerJ Machine learning Coronavirus Pneumonia SARS-CoV-2 Prediction model |
| title | Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables |
| title_full | Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables |
| title_fullStr | Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables |
| title_full_unstemmed | Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables |
| title_short | Deep learning prediction of likelihood of ICU admission and mortality in COVID-19 patients using clinical variables |
| title_sort | deep learning prediction of likelihood of icu admission and mortality in covid 19 patients using clinical variables |
| topic | Machine learning Coronavirus Pneumonia SARS-CoV-2 Prediction model |
| url | https://peerj.com/articles/10337.pdf |
| work_keys_str_mv | AT xiaoranli deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables AT peilinge deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables AT jocelynzhu deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables AT haifangli deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables AT jamesgraham deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables AT adamsinger deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables AT paulsrichman deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables AT timqduong deeplearningpredictionoflikelihoodoficuadmissionandmortalityincovid19patientsusingclinicalvariables |