Assess and validate predictive performance of models for in-hospital mortality in COVID-19 patients: A retrospective cohort study in the Netherlands comparing the value of registry data with high-granular electronic health records

被引：5

作者：

Vagliano, Iacopo ^{[1
]}

Schut, Martijn C. ^{[1
]}

Abu-Hanna, Ameen ^{[1
]}

Dongelmans, Dave A. ^{[2
,3
]}

de Lange, Dylan W. ^{[2
,4
]}

Gommers, Diederik ^{[5
]}

Cremer, Olaf L. ^{[6
]}

Bosman, Rob J. ^{[7
]}

Rigter, Sander ^{[8
]}

Wils, Evert-Jan ^{[9
]}

Frenzel, Tim ^{[10
]}

de Jong, Remko ^{[11
]}

Peters, Marco A. A. ^{[12
]}

Kamps, Marlijn J. A. ^{[13
]}

Ramnarain, Dharmanand ^{[14
]}

Nowitzky, Ralph ^{[15
]}

Nooteboom, Fleur G. C. A. ^{[16
]}

de Ruijter, Wouter ^{[17
]}

Urlings-Strop, Louise C. ^{[18
]}

Smit, Ellen G. M. ^{[19
]}

Mehagnoul-Schipper, D. Jannet ^{[20
]}

Dormans, Tom ^{[21
]}

de Jager, Cornelis P. C. ^{[22
]}

Hendriks, Stefaan H. A. ^{[23
]}

Achterberg, Sefanja ^{[24
]}

Oostdijk, Evelien ^{[25
]}

Reidinga, Auke C. ^{[26
]}

Festen-Spanjer, Barbara ^{[27
]}

Brunnekreef, Gert B. ^{[28
]}

Cornet, Alexander D. ^{[29
]}

van den Tempel, Walter ^{[30
]}

Boelens, Age D. ^{[31
]}

Koetsier, Peter ^{[32
]}

Lens, Judith ^{[33
]}

Faber, Harald J. ^{[34
]}

Karakus, A. ^{[35
]}

Entjes, Robert ^{[36
]}

de Jong, Paul ^{[37
]}

Rettig, Thijs C. D. ^{[38
]}

Reuland, M. C. ^{[3
]}

Arbous, Sesmu ^{[39
]}

Fleuren, Lucas M. ^{[40
]}

Dam, Tariq A. ^{[40
]}

Thoral, Patrick J. ^{[40
]}

Lalisang, Robbert C. A. ^{[41
]}

Tonutti, Michele ^{[41
]}

de Bruin, Daan P. ^{[41
]}

Elbers, Paul W. G. ^{[40
]}

de Keizer, Nicolette F. ^{[1
,2
]}

机构：

[1] Univ Amsterdam, Amsterdam Publ Hlth Res Inst, Dept Med Informat, Amsterdam UMC, Meibergdreef 9, NL-1105 AZ Amsterdam, Netherlands

[2] Natl Intens Care Evaluat NICE Fdn, Amsterdam, Netherlands

[3] Univ Amsterdam, Dept Intens Care Med, Amsterdam UMC, Amsterdam, Netherlands

[4] Univ Utrecht, Univ Med Ctr Utrecht, Dept Intens Care Med, Utrecht, Netherlands

[5] Erasmus MC, Dept Intens Care, Rotterdam, Netherlands

[6] UMC Utrecht, Intens Care, Utrecht, Netherlands

[7] OLVG, ICU, Amsterdam, Netherlands

[8] St Antonius Hosp, Dept Anesthesiol & Intens Care, Nieuwegein, Netherlands

[9] Franciscus Gasthuis & Vlietland, Dept Intens Care, Rotterdam, Netherlands

[10] Radboud Univ Nijmegen, Dept Intens Care Med, Med Ctr, Nijmegen, Netherlands

[11] Bovenij Ziekenhuis, Intens Care, Amsterdam, Netherlands

[12] Canisius Wilhelmina Ziekenhuis, Intens Care, Nijmegen, Netherlands

[13] Catharina Ziekenhuis Eindhoven, Intens Care, Eindhoven, Netherlands

[14] ETZ Tilburg, Dept Intens Care, Tilburg, Netherlands

[15] Haga Ziekenhuis, Intens Care, The Hague, Netherlands

[16] Laurentius Ziekenhuis, Intens Care, Roermond, Netherlands

[17] Northwest Clin, Dept Intens Care Med, Alkmaar, Netherlands

[18] Reinier Graaf Gasthuis, Intens Care, Delft, Netherlands

[19] Spaarne Gasthuis, Intens Care, Haarlem En Hoofddorp, Netherlands

[20] VieCuri Med Ctr, Intens Care, Venlo, Netherlands

[21] Zuyderland MC, Intens Care, Heerlen, Netherlands

[22] Jeroen Bosch Ziekenhuis, Dept Intens Care, Den Bosch, Netherlands

[23] Albert Schweitzerziekenhuis, Intens Care, Dordrecht, Netherlands

[24] Haaglanden Med Ctr, ICU, The Hague, Netherlands

[25] Maasstad Ziekenhuis Rotterdam, ICU, Rotterdam, Netherlands

[26] Martiniziekenhuis, BWC, SEH, ICU, Groningen, Netherlands

[27] Ziekenhuis Gelderse Vallei, Intens Care, Ede, Netherlands

[28] Ziekenhuisgrp Twente, Dept Intens Care, Almelo, Netherlands

[29] Med Spectrum Twente, Dept Intens Care, Enschede, Netherlands

[30] Ikazia Ziekenhuis Rotterdam, Dept Intens Care, Rotterdam, Netherlands

[31] Antonius Ziekenhuis Sneek, Anesthesiol, Sneek, Netherlands

[32] Med Ctr Leeuwarden, Intens Care, Leeuwarden, Netherlands

[33] IJsselland Ziekenhuis, ICU, Capelle Aan Den Ijssel, Netherlands

[34] WZA, ICU, Assen, Netherlands

[35] Diakonessenhuis Hosp, Dept Intens Care, Utrecht, Netherlands

[36] Adrz, Dept Intens Care, Goes, Netherlands

[37] Slingeland Ziekenhuis, Dept Anesthesia & Intens Care, Doetinchem, Netherlands

[38] Amphia Ziekenhuis, Dept Anesthesiol Intens Care & Pain Med, Breda, Netherlands

[39] LUMC, Leiden, Netherlands

[40] Vrije Univ, Amsterdam UMC, Amsterdam Med Data Sci, Dept Intens Care Med,Lab Crit Care Computat Intel, Amsterdam, Netherlands

[41] Pacmed, Amsterdam, Netherlands

来源：

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS | 2022年 / 167卷

关键词：

Covid-19 [C01.748.610.763.500; Critical care [E02.760.190; In-hospital mortality; E05.318.308.985.550.400; Prognosis [E01.789; Machine learning [G17.035.250.500; Electronic Health Record; E05.318.308.940.968.625.500; RESOURCE; QUALITY;

D O I：

10.1016/j.ijmedinf.2022.104863

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Purpose: To assess, validate and compare the predictive performance of models for in-hospital mortality of COVID-19 patients admitted to the intensive care unit (ICU) over two different waves of infections. Our models were built with high-granular Electronic Health Records (EHR) data versus less-granular registry data. Methods: Observational study of all COVID-19 patients admitted to 19 Dutch ICUs participating in both the national quality registry National Intensive Care Evaluation (NICE) and the EHR-based Dutch Data Warehouse (hereafter EHR). Multiple models were developed on data from the first 24 h of ICU admissions from February to June 2020 (first COVID-19 wave) and validated on prospective patients admitted to the same ICUs between July and December 2020 (second COVID-19 wave). We assessed model discrimination, calibration, and the degree of relatedness between development and validation population. Coefficients were used to identify relevant risk factors. Results: A total of 1533 patients from the EHR and 1563 from the registry were included. With high granular EHR data, the average AUROC was 0.69 (standard deviation of 0.05) for the internal validation, and the AUROC was 0.75 for the temporal validation. The registry model achieved an average AUROC of 0.76 (standard deviation of 0.05) in the internal validation and 0.77 in the temporal validation. In the EHR data, age, and respiratory-system related variables were the most important risk factors identified. In the NICE registry data, age and chronic respiratory insufficiency were the most important risk factors. Conclusion: In our study, prognostic models built on less-granular but readily-available registry data had similar performance to models built on high-granular EHR data and showed similar transportability to a prospective COVID-19 population. Future research is needed to verify whether this finding can be confirmed for upcoming waves.

引用

页数：11

共 8 条

[1] Predictive Value of CAR for In-Hospital Mortality in Patients with COVID-19 Pneumonia: A Retrospective Cohort Study
Guney, Basak Cakir
Tastan, Yesim Onal
Dogantekin, Betul
Serindag, Zeliha
Yeniceri, Murat
Cicek, Vedat
Kilic, Sahhan
Seker, Mehmet
Cinar, Tufan
Hayiroglu, Mert Ilker
Kaplan, Mustafa
ARCHIVES OF MEDICAL RESEARCH, 2021, 52 (05) : 554 - 560
[2] Relationship Between Platelet Count and In-hospital Mortality in Adult Patients With COVID-19: A Retrospective Cohort Study
Yang, Qilin
Gao, Jun
Zeng, Xiaomei
Chen, Junyu
Wen, Deliang
FRONTIERS IN MEDICINE, 2022, 9
[3] Derivation and external validation of a simple risk score to predict in-hospital mortality in patients hospitalized for COVID-19 A multicenter retrospective cohort study
Mann, Charlotte Z.
Abshire, Chelsea
Yost, Monica
Kaatz, Scott
Swaminathan, Lakshmi
Flanders, Scott A.
Prescott, Hallie C.
Gagnon-Bartsch, Johann A.
MEDICINE, 2021, 100 (40) : E27422
[4] Characteristics, comorbidities, 30-day outcome and in-hospital mortality of patients hospitalised with COVID-19 in a Swiss area - a retrospective cohort study
Charlotte, Pellaud
Gael, Grandmaison
Huua, Thien Hoa Phong Pham
Marine, Baumberger
Guillaume, Carrel
Hatem, Ksouri
Veronique, Erard
Christian, Chuard
Daniels, Hayoz
Govind, Sridharan
SWISS MEDICAL WEEKLY, 2020, 150
[5] Developing a mortality risk prediction model using data of 3663 hospitalized COVID-19 patients: a retrospective cohort study in an Egyptian University Hospital
Kandil, Sahar
Tharwat, Ayman I.
Mohsen, Sherief M.
Eldeeb, Mai
Abdallah, Waleed
Hilal, Amr
Sweed, Hala
Mortada, Mohamed
Arif, Elham
Ahmed, Tarek
Elshafie, Ahmed
Youssef, Tarek
Zaki, Mohamed
El-Gendy, Yasmin
Ebied, Essam
Hamad, Safwat
Habil, Ihab
Dabbous, Hany
El-Said, Amr
Mostafa, Yasser
Girgis, Samia
Mansour, Ossama
El-Anwar, Ali
Omar, Ashraf
Saleh, Ayman
El-Meteini, Mahmoud
BMC PULMONARY MEDICINE, 2023, 23 (01)
[6] Developing a mortality risk prediction model using data of 3663 hospitalized COVID-19 patients: a retrospective cohort study in an Egyptian University Hospital
Sahar Kandil
Ayman I. Tharwat
Sherief M. Mohsen
Mai Eldeeb
Waleed Abdallah
Amr Hilal
Hala Sweed
Mohamed Mortada
Elham Arif
Tarek Ahmed
Ahmed Elshafie
Tarek Youssef
Mohamed Zaki
Yasmin El-Gendy
Essam Ebied
Safwat Hamad
Ihab Habil
Hany Dabbous
Amr El-Said
Yasser Mostafa
Samia Girgis
Ossama Mansour
Ali El-Anwar
Ashraf Omar
Ayman Saleh
Mahmoud El-Meteini
BMC Pulmonary Medicine, 23
[7] Over 60 years of age as an independent prognostic factor of in-hospital mortality among COVID-19 patients: a cohort study in an Iranian high-incidence area
Navayi, M.
Fanoodi, A.
Salmani, F.
Abedi, F.
Shetty, S.
Riahi, S. M.
PUBLIC HEALTH, 2021, 200 : 33 - 38
[8] COVID-19-Related Neuropsychiatric Symptoms in Patients With Alcohol Abuse Conditions During the SARS-CoV-2 Pandemic: A Retrospective Cohort Study Using Real World Data From Electronic Health Records of a Tertiary Hospital
Varela Rodriguez, Carolina
Arias Horcajadas, Francisco
Martin-Arriscado Arroba, Cristina
Combarro Ripoll, Carolina
Juanes Gonzalez, Alba
Esperesate Pajares, Marina
Rodrigo Holgado, Irene
Cadenas Mancenido, Alvaro
Sanchez Rodriguez, Laura
Baselga Penalva, Blanca
Marin, Marta
Rubio, Gabriel
FRONTIERS IN NEUROLOGY, 2021, 12

← 1 →