COVID-19 mortality prediction in the intensive care unit with deep learning based on longitudinal chest X-rays and clinical data
© 2022. The Author(s), under exclusive licence to European Society of Radiology..
OBJECTIVES: We aimed to develop deep learning models using longitudinal chest X-rays (CXRs) and clinical data to predict in-hospital mortality of COVID-19 patients in the intensive care unit (ICU).
METHODS: Six hundred fifty-four patients (212 deceased, 442 alive, 5645 total CXRs) were identified across two institutions. Imaging and clinical data from one institution were used to train five longitudinal transformer-based networks applying five-fold cross-validation. The models were tested on data from the other institution, and pairwise comparisons were used to determine the best-performing models.
RESULTS: A higher proportion of deceased patients had elevated white blood cell count, decreased absolute lymphocyte count, elevated creatine concentration, and incidence of cardiovascular and chronic kidney disease. A model based on pre-ICU CXRs achieved an AUC of 0.632 and an accuracy of 0.593, and a model based on ICU CXRs achieved an AUC of 0.697 and an accuracy of 0.657. A model based on all longitudinal CXRs (both pre-ICU and ICU) achieved an AUC of 0.702 and an accuracy of 0.694. A model based on clinical data alone achieved an AUC of 0.653 and an accuracy of 0.657. The addition of longitudinal imaging to clinical data in a combined model significantly improved performance, reaching an AUC of 0.727 (p = 0.039) and an accuracy of 0.732.
CONCLUSIONS: The addition of longitudinal CXRs to clinical data significantly improves mortality prediction with deep learning for COVID-19 patients in the ICU.
KEY POINTS: • Deep learning was used to predict mortality in COVID-19 ICU patients. • Serial radiographs and clinical data were used. • The models could inform clinical decision-making and resource allocation.
Errataetall: | |
---|---|
Medienart: |
E-Artikel |
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:32 |
---|---|
Enthalten in: |
European radiology - 32(2022), 7 vom: 20. Juli, Seite 4446-4456 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Cheng, Jianhong [VerfasserIn] |
---|
Links: |
---|
Themen: |
Artificial intelligence |
---|
Anmerkungen: |
Date Completed 23.06.2022 Date Revised 23.06.2023 published: Print-Electronic ErratumIn: Eur Radiol. 2022 Mar 23;:. - PMID 35320415 Citation Status MEDLINE |
---|
doi: |
10.1007/s00330-022-08588-8 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM337160562 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM337160562 | ||
003 | DE-627 | ||
005 | 20231225233759.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s00330-022-08588-8 |2 doi | |
028 | 5 | 2 | |a pubmed24n1123.xml |
035 | |a (DE-627)NLM337160562 | ||
035 | |a (NLM)35184218 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Cheng, Jianhong |e verfasserin |4 aut | |
245 | 1 | 0 | |a COVID-19 mortality prediction in the intensive care unit with deep learning based on longitudinal chest X-rays and clinical data |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 23.06.2022 | ||
500 | |a Date Revised 23.06.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a ErratumIn: Eur Radiol. 2022 Mar 23;:. - PMID 35320415 | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2022. The Author(s), under exclusive licence to European Society of Radiology. | ||
520 | |a OBJECTIVES: We aimed to develop deep learning models using longitudinal chest X-rays (CXRs) and clinical data to predict in-hospital mortality of COVID-19 patients in the intensive care unit (ICU) | ||
520 | |a METHODS: Six hundred fifty-four patients (212 deceased, 442 alive, 5645 total CXRs) were identified across two institutions. Imaging and clinical data from one institution were used to train five longitudinal transformer-based networks applying five-fold cross-validation. The models were tested on data from the other institution, and pairwise comparisons were used to determine the best-performing models | ||
520 | |a RESULTS: A higher proportion of deceased patients had elevated white blood cell count, decreased absolute lymphocyte count, elevated creatine concentration, and incidence of cardiovascular and chronic kidney disease. A model based on pre-ICU CXRs achieved an AUC of 0.632 and an accuracy of 0.593, and a model based on ICU CXRs achieved an AUC of 0.697 and an accuracy of 0.657. A model based on all longitudinal CXRs (both pre-ICU and ICU) achieved an AUC of 0.702 and an accuracy of 0.694. A model based on clinical data alone achieved an AUC of 0.653 and an accuracy of 0.657. The addition of longitudinal imaging to clinical data in a combined model significantly improved performance, reaching an AUC of 0.727 (p = 0.039) and an accuracy of 0.732 | ||
520 | |a CONCLUSIONS: The addition of longitudinal CXRs to clinical data significantly improves mortality prediction with deep learning for COVID-19 patients in the ICU | ||
520 | |a KEY POINTS: • Deep learning was used to predict mortality in COVID-19 ICU patients. • Serial radiographs and clinical data were used. • The models could inform clinical decision-making and resource allocation | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Artificial intelligence | |
650 | 4 | |a Coronavirus | |
650 | 4 | |a Hospital mortality | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Prognosis | |
700 | 1 | |a Sollee, John |e verfasserin |4 aut | |
700 | 1 | |a Hsieh, Celina |e verfasserin |4 aut | |
700 | 1 | |a Yue, Hailin |e verfasserin |4 aut | |
700 | 1 | |a Vandal, Nicholas |e verfasserin |4 aut | |
700 | 1 | |a Shanahan, Justin |e verfasserin |4 aut | |
700 | 1 | |a Choi, Ji Whae |e verfasserin |4 aut | |
700 | 1 | |a Tran, Thi My Linh |e verfasserin |4 aut | |
700 | 1 | |a Halsey, Kasey |e verfasserin |4 aut | |
700 | 1 | |a Iheanacho, Franklin |e verfasserin |4 aut | |
700 | 1 | |a Warren, James |e verfasserin |4 aut | |
700 | 1 | |a Ahmed, Abdullah |e verfasserin |4 aut | |
700 | 1 | |a Eickhoff, Carsten |e verfasserin |4 aut | |
700 | 1 | |a Feldman, Michael |e verfasserin |4 aut | |
700 | 1 | |a Mortani Barbosa, Eduardo |c Jr |e verfasserin |4 aut | |
700 | 1 | |a Kamel, Ihab |e verfasserin |4 aut | |
700 | 1 | |a Lin, Cheng Ting |e verfasserin |4 aut | |
700 | 1 | |a Yi, Thomas |e verfasserin |4 aut | |
700 | 1 | |a Healey, Terrance |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Paul |e verfasserin |4 aut | |
700 | 1 | |a Wu, Jing |e verfasserin |4 aut | |
700 | 1 | |a Atalay, Michael |e verfasserin |4 aut | |
700 | 1 | |a Bai, Harrison X |e verfasserin |4 aut | |
700 | 1 | |a Jiao, Zhicheng |e verfasserin |4 aut | |
700 | 1 | |a Wang, Jianxin |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t European radiology |d 1991 |g 32(2022), 7 vom: 20. Juli, Seite 4446-4456 |w (DE-627)NLM087691310 |x 1432-1084 |7 nnns |
773 | 1 | 8 | |g volume:32 |g year:2022 |g number:7 |g day:20 |g month:07 |g pages:4446-4456 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/s00330-022-08588-8 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 32 |j 2022 |e 7 |b 20 |c 07 |h 4446-4456 |