Early Identification of COVID-19 Infected Patients Who Need ICU Care and its Implications
Corona Virus Disease 2019 (COVID-19) can cause the patients' condition to become serious at some check-point, and thus patients need the intensive care unit (ICU) intervention to survive. The resulted urgent and extensive needs of ICUs posed significant risks to the management of the medical system. Therefore, it is essential to prognostically identify the patient who may be treated in ICU and estimate the length of stay is essential. In this paper, the support vector machine (SVM) with polynomial kernel was used to identify the difference between patients and predict the need for ICU. In predicting the time patients spent in the ICU, we utilized the least absolute shrinkage and selection operator (LASSO) regression model. The variables ranked within the top ten most significant values were chosen and analyzed individually. The model built by machine learning can accurately assess the differences in ICU, ICU admission, length of ICU stay, and MI-mortality in COVID-19 patients toward optimal ICU resource allocation. Our proposed approach can give 1-15 days before they were actually admitted into ICU. We also found that high sensitivity troponin I and hypersensitive C-reactive protein are two critical prognostic factors among the selected factors since they appeared in all prediction tasks with a higher AUC.
Medienart: |
E-Book |
---|
Erscheinungsjahr: |
[2022] |
---|---|
Erschienen: |
S.l.: SSRN ; 2022 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhou, Zhichao [VerfasserIn] |
---|
Links: |
---|
Umfang: |
1 Online-Ressource (9 p) |
---|
doi: |
10.2139/ssrn.3995973 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
181043484X |
---|
LEADER | 01000cam a22002652 4500 | ||
---|---|---|---|
001 | 181043484X | ||
003 | DE-627 | ||
005 | 20230428193653.0 | ||
007 | cr uuu---uuuuu | ||
008 | 220715s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.2139/ssrn.3995973 |2 doi | |
035 | |a (DE-627)181043484X | ||
035 | |a (DE-599)KEP080364160 | ||
035 | |a (ELVSSRN)3995973 | ||
035 | |a (EBP)080364160 | ||
040 | |a DE-627 |b ger |c DE-627 |e rda | ||
041 | |a eng | ||
100 | 1 | |a Zhou, Zhichao |e verfasserin |4 aut | |
245 | 1 | 0 | |a Early Identification of COVID-19 Infected Patients Who Need ICU Care and its Implications |
264 | 1 | |a [S.l.] |b SSRN |c [2022] | |
300 | |a 1 Online-Ressource (9 p) | ||
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
506 | 0 | |a Open Access |e Controlled Vocabulary for Access Rights |u http://purl.org/coar/access_right/c_abf2 |f unrestricted online access | |
520 | |a Corona Virus Disease 2019 (COVID-19) can cause the patients' condition to become serious at some check-point, and thus patients need the intensive care unit (ICU) intervention to survive. The resulted urgent and extensive needs of ICUs posed significant risks to the management of the medical system. Therefore, it is essential to prognostically identify the patient who may be treated in ICU and estimate the length of stay is essential. In this paper, the support vector machine (SVM) with polynomial kernel was used to identify the difference between patients and predict the need for ICU. In predicting the time patients spent in the ICU, we utilized the least absolute shrinkage and selection operator (LASSO) regression model. The variables ranked within the top ten most significant values were chosen and analyzed individually. The model built by machine learning can accurately assess the differences in ICU, ICU admission, length of ICU stay, and MI-mortality in COVID-19 patients toward optimal ICU resource allocation. Our proposed approach can give 1-15 days before they were actually admitted into ICU. We also found that high sensitivity troponin I and hypersensitive C-reactive protein are two critical prognostic factors among the selected factors since they appeared in all prediction tasks with a higher AUC | ||
700 | 1 | |a Dan, TingTing |e verfasserin |4 aut | |
700 | 1 | |a Zhu, Ziwei |e verfasserin |4 aut | |
700 | 1 | |a Li, Yang |e verfasserin |4 aut | |
700 | 1 | |a Chen, Xijie |e verfasserin |4 aut | |
700 | 1 | |a Quan, Wuxiu |e verfasserin |4 aut | |
700 | 1 | |a Huang, Zhuobin |e verfasserin |4 aut | |
700 | 1 | |a Zhu, Lei |e verfasserin |4 aut | |
700 | 1 | |a Zhu, Jijin |e verfasserin |4 aut | |
700 | 1 | |a Wen, Hanchun |e verfasserin |4 aut | |
700 | 1 | |a Cai, Hongmin |e verfasserin |4 aut | |
856 | 4 | 0 | |u https://ssrn.com/abstract=3995973 |m X:ELVSSRN |x Verlag |z kostenfrei |
856 | 4 | 0 | |u https://doi.org/10.2139/ssrn.3995973 |m X:ELVSSRN |x Resolving-System |z kostenfrei |
912 | |a ZDB-33-SFEN | ||
912 | |a ZDB-33-ERN | ||
912 | |a GBV_ILN_26 | ||
912 | |a ISIL_DE-206 | ||
912 | |a SYSFLAG_1 | ||
912 | |a GBV_KXP | ||
912 | |a SSG-OLC-PHA | ||
912 | |a GBV_ILN_60 | ||
912 | |a ISIL_DE-705 | ||
912 | |a GBV_ILN_2403 | ||
912 | |a ISIL_DE-LFER | ||
951 | |a BO | ||
980 | |2 26 |1 01 |x 0206 |b 4174087881 |h OLR-SSRN |y znz |z 29-07-22 | ||
980 | |2 60 |1 01 |x 0705 |b 422043738X |h OA |k Bitte beachten Sie die Nutzungsbedingungen und Copyright-Bestimmungen des Verlages/Herausgebers! |k Freier Download |y z |z 25-11-22 | ||
980 | |2 2403 |1 01 |x DE-LFER |b 4240821738 |c 00 |f --%%-- |d --%%-- |e n |j --%%-- |y l01 |z 23-12-22 | ||
981 | |2 26 |1 01 |x 0206 |r https://doi.org/10.2139/ssrn.3995973 | ||
981 | |2 60 |1 01 |x 0705 |r https://doi.org/10.2139/ssrn.3995973 | ||
981 | |2 2403 |1 01 |x DE-LFER |r https://doi.org/10.2139/ssrn.3995973 | ||
981 | |2 2403 |1 01 |x DE-LFER |r https://ssrn.com/abstract=3995973 | ||
995 | |2 26 |1 01 |x 0206 |a OLR-SSRN | ||
995 | |2 60 |1 01 |x 0705 |a OA |