Your browser doesn't support javascript.
Prognostication of patients with COVID-19 using artificial intelligence based on chest x-rays and clinical data: a retrospective study.
Jiao, Zhicheng; Choi, Ji Whae; Halsey, Kasey; Tran, Thi My Linh; Hsieh, Ben; Wang, Dongcui; Eweje, Feyisope; Wang, Robin; Chang, Ken; Wu, Jing; Collins, Scott A; Yi, Thomas Y; Delworth, Andrew T; Liu, Tao; Healey, Terrance T; Lu, Shaolei; Wang, Jianxin; Feng, Xue; Atalay, Michael K; Yang, Li; Feldman, Michael; Zhang, Paul J L; Liao, Wei-Hua; Fan, Yong; Bai, Harrison X.
  • Jiao Z; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Choi JW; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Halsey K; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Tran TML; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Hsieh B; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Wang D; Department of Radiology, Xiangya Hospital, Central South University, Changsha, China.
  • Eweje F; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Wang R; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Chang K; Athinoula A Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Boston, MA, USA.
  • Wu J; Department of Radiology, Xiangya Hospital, Central South University, Changsha, China.
  • Collins SA; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Yi TY; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Delworth AT; Department of Computer Science, Brown University, Providence, RI, USA.
  • Liu T; Department of Biostatistics, Brown University, Providence, RI, USA.
  • Healey TT; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Lu S; Department of Pathology and Laboratory Medicine, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Wang J; School of Computer Science and Engineering, Central South University, Changsha, China.
  • Feng X; Carina Medical, Lexington, KY, USA.
  • Atalay MK; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA.
  • Yang L; Department of Neurology, Xiangya Hospital, Central South University, Changsha, China.
  • Feldman M; Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Zhang PJL; Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Liao WH; Department of Radiology, Xiangya Hospital, Central South University, Changsha, China. Electronic address: owenliao@csu.edu.cn.
  • Fan Y; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA. Electronic address: yong.fan@pennmedicine.upenn.edu.
  • Bai HX; Department of Diagnostic Imaging, Rhode Island Hospital and Warren Alpert Medical School of Brown University, Providence, RI, USA. Electronic address: harrison_bai@brown.edu.
Lancet Digit Health ; 3(5): e286-e294, 2021 05.
Article in English | MEDLINE | ID: covidwho-1152741
Semantic information from SemMedBD (by NLM)
1. COVID-19 PROCESS_OF Patients
Subject
COVID-19
Predicate
PROCESS_OF
Object
Patients
2. Hospitals LOCATION_OF Retrospective Studies
Subject
Hospitals
Predicate
LOCATION_OF
Object
Retrospective Studies
3. Reverse Transcriptase Polymerase Chain Reaction METHOD_OF Diagnosis
Subject
Reverse Transcriptase Polymerase Chain Reaction
Predicate
METHOD_OF
Object
Diagnosis
4. Performance PROCESS_OF Patients
Subject
Performance
Predicate
PROCESS_OF
Object
Patients
5. COVID-19 PREDISPOSES Critical Illness
Subject
COVID-19
Predicate
PREDISPOSES
Object
Critical Illness
6. Critical Illness PROCESS_OF Patients
Subject
Critical Illness
Predicate
PROCESS_OF
Object
Patients
7. COVID-19 PROCESS_OF Patients
Subject
COVID-19
Predicate
PROCESS_OF
Object
Patients
8. Hospitals LOCATION_OF Retrospective Studies
Subject
Hospitals
Predicate
LOCATION_OF
Object
Retrospective Studies
9. Reverse Transcriptase Polymerase Chain Reaction METHOD_OF Diagnosis
Subject
Reverse Transcriptase Polymerase Chain Reaction
Predicate
METHOD_OF
Object
Diagnosis
10. Performance PROCESS_OF Patients
Subject
Performance
Predicate
PROCESS_OF
Object
Patients
11. COVID-19 PREDISPOSES Critical Illness
Subject
COVID-19
Predicate
PREDISPOSES
Object
Critical Illness
12. Critical Illness PROCESS_OF Patients
Subject
Critical Illness
Predicate
PROCESS_OF
Object
Patients
ABSTRACT

BACKGROUND:

Chest x-ray is a relatively accessible, inexpensive, fast imaging modality that might be valuable in the prognostication of patients with COVID-19. We aimed to develop and evaluate an artificial intelligence system using chest x-rays and clinical data to predict disease severity and progression in patients with COVID-19.

METHODS:

We did a retrospective study in multiple hospitals in the University of Pennsylvania Health System in Philadelphia, PA, USA, and Brown University affiliated hospitals in Providence, RI, USA. Patients who presented to a hospital in the University of Pennsylvania Health System via the emergency department, with a diagnosis of COVID-19 confirmed by RT-PCR and with an available chest x-ray from their initial presentation or admission, were retrospectively identified and randomly divided into training, validation, and test sets (712). Using the chest x-rays as input to an EfficientNet deep neural network and clinical data, models were trained to predict the binary outcome of disease severity (ie, critical or non-critical). The deep-learning features extracted from the model and clinical data were used to build time-to-event models to predict the risk of disease progression. The models were externally tested on patients who presented to an independent multicentre institution, Brown University affiliated hospitals, and compared with severity scores provided by radiologists.

FINDINGS:

1834 patients who presented via the University of Pennsylvania Health System between March 9 and July 20, 2020, were identified and assigned to the model training (n=1285), validation (n=183), or testing (n=366) sets. 475 patients who presented via the Brown University affiliated hospitals between March 1 and July 18, 2020, were identified for external testing of the models. When chest x-rays were added to clinical data for severity prediction, area under the receiver operating characteristic curve (ROC-AUC) increased from 0·821 (95% CI 0·796-0·828) to 0·846 (0·815-0·852; p<0·0001) on internal testing and 0·731 (0·712-0·738) to 0·792 (0·780-0 ·803; p<0·0001) on external testing. When deep-learning features were added to clinical data for progression prediction, the concordance index (C-index) increased from 0·769 (0·755-0·786) to 0·805 (0·800-0·820; p<0·0001) on internal testing and 0·707 (0·695-0·729) to 0·752 (0·739-0·764; p<0·0001) on external testing. The image and clinical data combined model had significantly better prognostic performance than combined severity scores and clinical data on internal testing (C-index 0·805 vs 0·781; p=0·0002) and external testing (C-index 0·752 vs 0·715; p<0·0001).

INTERPRETATION:

In patients with COVID-19, artificial intelligence based on chest x-rays had better prognostic performance than clinical data or radiologist-derived severity scores. Using artificial intelligence, chest x-rays can augment clinical data in predicting the risk of progression to critical illness in patients with COVID-19.

FUNDING:

Brown University, Amazon Web Services Diagnostic Development Initiative, Radiological Society of North America, National Cancer Institute and National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health.
Subject(s)

Full text: Available Collection: International databases Database: MEDLINE Main subject: Prognosis / Artificial Intelligence / Radiography, Thoracic / COVID-19 Type of study: Observational study / Prognostic study / Randomized controlled trials / Risk factors Limits: Adult / Aged / Female / Humans / Male / Middle aged / Young adult Country/Region as subject: North America Language: English Journal: Lancet Digit Health Year: 2021 Document Type: Article Affiliation country: S2589-7500(21)00039-x

Full text: Available Collection: International databases Database: MEDLINE Main subject: Prognosis / Artificial Intelligence / Radiography, Thoracic / COVID-19 Type of study: Observational study / Prognostic study / Randomized controlled trials / Risk factors Limits: Adult / Aged / Female / Humans / Male / Middle aged / Young adult Country/Region as subject: North America Language: English Journal: Lancet Digit Health Year: 2021 Document Type: Article Affiliation country: S2589-7500(21)00039-x