Your browser doesn't support javascript.
Development of a clinical decision support system for severity risk prediction and triage of COVID-19 patients at hospital admission: an international multicentre study.
Wu, Guangyao; Yang, Pei; Xie, Yuanliang; Woodruff, Henry C; Rao, Xiangang; Guiot, Julien; Frix, Anne-Noelle; Louis, Renaud; Moutschen, Michel; Li, Jiawei; Li, Jing; Yan, Chenggong; Du, Dan; Zhao, Shengchao; Ding, Yi; Liu, Bin; Sun, Wenwu; Albarello, Fabrizio; D'Abramo, Alessandra; Schininà, Vincenzo; Nicastri, Emanuele; Occhipinti, Mariaelena; Barisione, Giovanni; Barisione, Emanuela; Halilaj, Iva; Lovinfosse, Pierre; Wang, Xiang; Wu, Jianlin; Lambin, Philippe.
  • Wu G; The D-Lab, Dept of Precision Medicine, GROW - School for Oncology, Maastricht University Medical Center+, Maastricht, The Netherlands g.wu@maastrichtuniversity.nl.
  • Yang P; Guangyao Wu and Pei Yang are joint first authors.
  • Xie Y; Guangyao Wu and Xiang Wang are co-corresponding authors.
  • Woodruff HC; Dept of Radiology, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China.
  • Rao X; Guangyao Wu and Pei Yang are joint first authors.
  • Guiot J; Dept of Radiology, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China.
  • Frix AN; The D-Lab, Dept of Precision Medicine, GROW - School for Oncology, Maastricht University Medical Center+, Maastricht, The Netherlands.
  • Louis R; Dept of Radiology and Nuclear Medicine, GROW- School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, The Netherlands.
  • Moutschen M; Dept of Ultrasound, The Central Hospital of Huangshi, Huangshi, China.
  • Li J; Dept of Respiratory Medicine, CHU of Liège, Liège, Belgium.
  • Li J; Dept of Respiratory Medicine, CHU of Liège, Liège, Belgium.
  • Yan C; Dept of Respiratory Medicine, CHU of Liège, Liège, Belgium.
  • Du D; Dept of Infectiology, CHU of Liège, Liège, Belgium.
  • Zhao S; Dept of Radiology, China Resources Wuhan Iron and Steel Hospital, Wuhan, China.
  • Ding Y; Dept of Radiology, The Central Hospital of Shaoyang, Shaoyang, China.
  • Liu B; The D-Lab, Dept of Precision Medicine, GROW - School for Oncology, Maastricht University Medical Center+, Maastricht, The Netherlands.
  • Sun W; Dept of Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou, China.
  • Albarello F; Dept of Radiology, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China.
  • D'Abramo A; Dept of Radiology, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China.
  • Schininà V; Dept of Radiology, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China.
  • Nicastri E; Dept of Radiology, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China.
  • Occhipinti M; Dept of Intensive Care Unit, The Central Hospital of Wuhan, Huazhong University of Science and Technology, Wuhan, China.
  • Barisione G; National Institute for Infectious Diseases - IRCCS, Rome, Italy.
  • Barisione E; National Institute for Infectious Diseases - IRCCS, Rome, Italy.
  • Halilaj I; National Institute for Infectious Diseases - IRCCS, Rome, Italy.
  • Lovinfosse P; National Institute for Infectious Diseases - IRCCS, Rome, Italy.
  • Wang X; Dept of Biomedical, Clinical and Experimental Sciences "Mario Serio", University of Florence, Florence, Italy.
  • Wu J; Unit of Respiratory Pathophysiology, Respiratory Diseases and Allergy Clinic, Dept of Internal Medicine and Medical Specialties, University of Genoa, IRCCS Ospedale Policlinico San Martino, Genoa, Italy.
  • Lambin P; Unit of Interventional Pulmonology, IRCCS Ospedale Policlinico San Martino, Genoa, Italy.
Eur Respir J ; 56(2)2020 08.
Article in English | MEDLINE | ID: covidwho-744960
Semantic information from SemMedBD (by NLM)
1. COVID-19 PROCESS_OF Patients
Subject
COVID-19
Predicate
PROCESS_OF
Object
Patients
2. Triage TREATS COVID-19
Subject
Triage
Predicate
TREATS
Object
COVID-19
3. Triage TREATS Patients
Subject
Triage
Predicate
TREATS
Object
Patients
4. Matrix CONVERTS_TO Metric (substance)
Subject
Matrix
Predicate
CONVERTS_TO
Object
Metric (substance)
5. Critical Illness PROCESS_OF Patients
Subject
Critical Illness
Predicate
PROCESS_OF
Object
Patients
6. Borg Category-Ratio 10 Perceived Exertion Score 5 PROCESS_OF Patients
Subject
Borg Category-Ratio 10 Perceived Exertion Score 5
Predicate
PROCESS_OF
Object
Patients
7. COVID-19 PROCESS_OF Patients
Subject
COVID-19
Predicate
PROCESS_OF
Object
Patients
8. Triage TREATS COVID-19
Subject
Triage
Predicate
TREATS
Object
COVID-19
9. Triage TREATS Patients
Subject
Triage
Predicate
TREATS
Object
Patients
10. Matrix CONVERTS_TO Metric (substance)
Subject
Matrix
Predicate
CONVERTS_TO
Object
Metric (substance)
11. Critical Illness PROCESS_OF Patients
Subject
Critical Illness
Predicate
PROCESS_OF
Object
Patients
12. Borg Category-Ratio 10 Perceived Exertion Score 5 PROCESS_OF Patients
Subject
Borg Category-Ratio 10 Perceived Exertion Score 5
Predicate
PROCESS_OF
Object
Patients
ABSTRACT

BACKGROUND:

The outbreak of coronavirus disease 2019 (COVID-19) has globally strained medical resources and caused significant mortality.

OBJECTIVE:

To develop and validate a machine-learning model based on clinical features for severity risk assessment and triage for COVID-19 patients at hospital admission.

METHOD:

725 patients were used to train and validate the model. This included a retrospective cohort from Wuhan, China of 299 hospitalised COVID-19 patients from 23 December 2019 to 13 February 2020, and five cohorts with 426 patients from eight centres in China, Italy and Belgium from 20 February 2020 to 21 March 2020. The main outcome was the onset of severe or critical illness during hospitalisation. Model performances were quantified using the area under the receiver operating characteristic curve (AUC) and metrics derived from the confusion matrix.

RESULTS:

In the retrospective cohort, the median age was 50 years and 137 (45.8%) were male. In the five test cohorts, the median age was 62 years and 236 (55.4%) were male. The model was prospectively validated on five cohorts yielding AUCs ranging from 0.84 to 0.93, with accuracies ranging from 74.4% to 87.5%, sensitivities ranging from 75.0% to 96.9%, and specificities ranging from 55.0% to 88.0%, most of which performed better than the pneumonia severity index. The cut-off values of the low-, medium- and high-risk probabilities were 0.21 and 0.80. The online calculators can be found at www.covid19risk.ai.

CONCLUSION:

The machine-learning model, nomogram and online calculator might be useful to access the onset of severe and critical illness among COVID-19 patients and triage at hospital admission.
Subject(s)

Full text: Available Collection: International databases Database: MEDLINE Main subject: Pneumonia, Viral / Triage / Hospital Mortality / Coronavirus Infections / Machine Learning Type of study: Cohort study / Diagnostic study / Observational study / Prognostic study Limits: Adult / Aged / Female / Humans / Male / Middle aged Country/Region as subject: Asia / Europa Language: English Year: 2020 Document Type: Article Affiliation country: 13993003.01104-2020

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Pneumonia, Viral / Triage / Hospital Mortality / Coronavirus Infections / Machine Learning Type of study: Cohort study / Diagnostic study / Observational study / Prognostic study Limits: Adult / Aged / Female / Humans / Male / Middle aged Country/Region as subject: Asia / Europa Language: English Year: 2020 Document Type: Article Affiliation country: 13993003.01104-2020