Predicting mortality of individual COVID-19 patients: A multicenter Dutch cohort
ABSTRACT Objective Develop and validate models that predict mortality of SARS-CoV-2 infected patients admitted to the hospital.Design Retrospective cohort studySetting A multicenter cohort across ten Dutch hospitals including patients from February 27 to June 8 2020.Participants SARS-CoV-2 positive patients (age ≥ 18) admitted to the hospital.Main Outcome Measures 21-day mortality evaluated by the area under the receiver operatory curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The predictive value of age was explored by comparison with age-based rules used in practice and by excluding age from analysis.Results 2273 patients were included, of whom 516 had died or discharged to palliative care within 21 days after admission. Five feature sets, including premorbid, clinical presentation and laboratory & radiology values, were derived from 80 features. Additionally, an ANOVA-based data-driven feature selection selected the ten features with the highest F-values: age, number of home medications, urea nitrogen, lactate dehydrogenase, albumin, oxygen saturation (%), oxygen saturation is measured on room air, oxygen saturation is measured on oxygen therapy, blood gas pH and history of chronic cardiac disease. A linear logistic regression (LR) and non-linear tree-based gradient boosting (XGB) algorithm fitted the data with an AUC of 0.81 (95% confidence interval 0.77 to 0.85) and 0.82 (0.79 to 0.85), respectively, using the ten selected features. Both models outperformed age-based decision rules used in practice (AUC of 0.69, 0.65 to 0.74 for age > 70). Furthermore, performance remained stable when excluding age as predictor (AUC of 0.78, 0.75 to 0.81)Conclusion Both models showed excellent performance and had better test characteristics than age-based decision rules, using ten admission features readily available in Dutch hospitals. The models hold promise to aid decision making during a hospital bed shortage..
| Medienart: |
|
|---|
Preprint| Erscheinungsjahr: |
2020 |
|---|---|
| Erschienen: |
2020 |
| Enthalten in: |
bioRxiv.org - (2020) vom: 30. Dez. Zur Gesamtaufnahme - year:2020 |
|---|
| Sprache: |
Englisch |
|---|
| Links: |
Volltext [kostenfrei] |
|---|
| doi: |
10.1101/2020.10.10.20210591 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
XBI019095015 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | XBI019095015 | ||
| 003 | DE-627 | ||
| 005 | 20230429091816.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 201014s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1101/2020.10.10.20210591 |2 doi | |
| 035 | |a (DE-627)XBI019095015 | ||
| 035 | |a (DE-599)biorXiv10.1101/2020.10.10.20210591 | ||
| 035 | |a (biorXiv)10.1101/2020.10.10.20210591 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | |a 570 |q DE-84 | |
| 100 | 1 | |a Ottenhoff, Maarten C. |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Predicting mortality of individual COVID-19 patients: A multicenter Dutch cohort |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a ABSTRACT Objective Develop and validate models that predict mortality of SARS-CoV-2 infected patients admitted to the hospital.Design Retrospective cohort studySetting A multicenter cohort across ten Dutch hospitals including patients from February 27 to June 8 2020.Participants SARS-CoV-2 positive patients (age ≥ 18) admitted to the hospital.Main Outcome Measures 21-day mortality evaluated by the area under the receiver operatory curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The predictive value of age was explored by comparison with age-based rules used in practice and by excluding age from analysis.Results 2273 patients were included, of whom 516 had died or discharged to palliative care within 21 days after admission. Five feature sets, including premorbid, clinical presentation and laboratory & radiology values, were derived from 80 features. Additionally, an ANOVA-based data-driven feature selection selected the ten features with the highest F-values: age, number of home medications, urea nitrogen, lactate dehydrogenase, albumin, oxygen saturation (%), oxygen saturation is measured on room air, oxygen saturation is measured on oxygen therapy, blood gas pH and history of chronic cardiac disease. A linear logistic regression (LR) and non-linear tree-based gradient boosting (XGB) algorithm fitted the data with an AUC of 0.81 (95% confidence interval 0.77 to 0.85) and 0.82 (0.79 to 0.85), respectively, using the ten selected features. Both models outperformed age-based decision rules used in practice (AUC of 0.69, 0.65 to 0.74 for age > 70). Furthermore, performance remained stable when excluding age as predictor (AUC of 0.78, 0.75 to 0.81)Conclusion Both models showed excellent performance and had better test characteristics than age-based decision rules, using ten admission features readily available in Dutch hospitals. The models hold promise to aid decision making during a hospital bed shortage. | ||
| 700 | 1 | |a Ramos, Lucas L. |e verfasserin |4 aut | |
| 700 | 1 | |a Potters, Wouter |e verfasserin |4 aut | |
| 700 | 1 | |a Janssen, Marcus L.F. |e verfasserin |4 aut | |
| 700 | 1 | |a Hubers, Deborah |e verfasserin |4 aut | |
| 700 | 1 | |a Piña-Fuentes, Dan |e verfasserin |4 aut | |
| 700 | 1 | |a Thomas, Rajat |e verfasserin |4 aut | |
| 700 | 1 | |a van der Horst, Iwan C.C. |e verfasserin |4 aut | |
| 700 | 1 | |a Herff, Christian |e verfasserin |4 aut | |
| 700 | 1 | |a Kubben, Pieter |e verfasserin |4 aut | |
| 700 | 1 | |a Elbers, Paul W.G. |e verfasserin |4 aut | |
| 700 | 1 | |a Marquering, Henk A. |e verfasserin |4 aut | |
| 700 | 1 | |a Welling, Max |e verfasserin |4 aut | |
| 700 | 1 | |a Hu, Shi |e verfasserin |4 aut | |
| 700 | 1 | |a Simsek, Suat |e verfasserin |4 aut | |
| 700 | 1 | |a de Kruif, Martijn D. |e verfasserin |4 aut | |
| 700 | 1 | |a Dormans, Tom |e verfasserin |4 aut | |
| 700 | 1 | |a Fleuren, Lucas M. |e verfasserin |4 aut | |
| 700 | 1 | |a Schinkel, Michiel |e verfasserin |4 aut | |
| 700 | 1 | |a Noordzij, Peter G. |e verfasserin |4 aut | |
| 700 | 1 | |a van den Bergh, Joop P. |e verfasserin |4 aut | |
| 700 | 1 | |a Wyers, Caroline E. |e verfasserin |4 aut | |
| 700 | 1 | |a Buis, David T. B. |e verfasserin |4 aut | |
| 700 | 1 | |a Wiersinga, Joost |e verfasserin |4 aut | |
| 700 | 1 | |a van den Hout, Ella H.C. |e verfasserin |4 aut | |
| 700 | 1 | |a Reidinga, Auke C. |e verfasserin |4 aut | |
| 700 | 1 | |a Rusch, Daisy |e verfasserin |4 aut | |
| 700 | 1 | |a Sigaloff, Kim C.E. |e verfasserin |4 aut | |
| 700 | 1 | |a Douma, Renée |e verfasserin |4 aut | |
| 700 | 1 | |a de Haan, Lianne |e verfasserin |4 aut | |
| 700 | 1 | |a Fridgeirsson, Egill A. |e verfasserin |4 aut | |
| 700 | 1 | |a van den Oever, Niels C. Gritters |e verfasserin |4 aut | |
| 700 | 1 | |a Rennenberg, Roger J.M.W. |e verfasserin |4 aut | |
| 700 | 1 | |a van Wingen, Guido A. |e verfasserin |4 aut | |
| 700 | 1 | |a Aries, Marcel J.H. |e verfasserin |4 aut | |
| 700 | 1 | |a Beudel, Martijn |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t bioRxiv.org |g (2020) vom: 30. Dez. |
| 773 | 1 | 8 | |g year:2020 |g day:30 |g month:12 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1101/2020.10.10.20210591 |z kostenfrei |3 Volltext |
| 912 | |a GBV_XBI | ||
| 912 | |a SSG-OLC-PHA | ||
| 951 | |a AR | ||
| 952 | |j 2020 |b 30 |c 12 | ||
| 953 | |2 045F |a 570 | ||