Warning: file_get_contents(https://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&id=32984796&cmd=llinks): Failed to open stream: HTTP request failed! HTTP/1.1 429 Too Many Requests
in C:\Inetpub\vhosts\kidney.de\httpdocs\pget.php on line 215
Deep learning-based triage and analysis of lesion burden for COVID-19: a retrospective study with external validation #MMPMID32984796
Wang M; Xia C; Huang L; Xu S; Qin C; Liu J; Cao Y; Yu P; Zhu T; Zhu H; Wu C; Zhang R; Chen X; Wang J; Du G; Zhang C; Wang S; Chen K; Liu Z; Xia L; Wang W
Lancet Digit Health 2020[Oct]; 2 (10): e506-e515 PMID32984796show ga
BACKGROUND: Prompt identification of patients suspected to have COVID-19 is crucial for disease control. We aimed to develop a deep learning algorithm on the basis of chest CT for rapid triaging in fever clinics. METHODS: We trained a U-Net-based model on unenhanced chest CT scans obtained from 2447 patients admitted to Tongji Hospital (Wuhan, China) between Feb 1, 2020, and March 3, 2020 (1647 patients with RT-PCR-confirmed COVID-19 and 800 patients without COVID-19) to segment lung opacities and alert cases with COVID-19 imaging manifestations. The ability of artificial intelligence (AI) to triage patients suspected to have COVID-19 was assessed in a large external validation set, which included 2120 retrospectively collected consecutive cases from three fever clinics inside and outside the epidemic centre of Wuhan (Tianyou Hospital [Wuhan, China; area of high COVID-19 prevalence], Xianning Central Hospital [Xianning, China; area of medium COVID-19 prevalence], and The Second Xiangya Hospital [Changsha, China; area of low COVID-19 prevalence]) between Jan 22, 2020, and Feb 14, 2020. To validate the sensitivity of the algorithm in a larger sample of patients with COVID-19, we also included 761 chest CT scans from 722 patients with RT-PCR-confirmed COVID-19 treated in a makeshift hospital (Guanggu Fangcang Hospital, Wuhan, China) between Feb 21, 2020, and March 6, 2020. Additionally, the accuracy of AI was compared with a radiologist panel for the identification of lesion burden increase on pairs of CT scans obtained from 100 patients with COVID-19. FINDINGS: In the external validation set, using radiological reports as the reference standard, AI-aided triage achieved an area under the curve of 0.953 (95% CI 0.949-0.959), with a sensitivity of 0.923 (95% CI 0.914-0.932), specificity of 0.851 (0.842-0.860), a positive predictive value of 0.790 (0.777-0.803), and a negative predictive value of 0.948 (0.941-0.954). AI took a median of 0.55 min (IQR: 0.43-0.63) to flag a positive case, whereas radiologists took a median of 16.21 min (11.67-25.71) to draft a report and 23.06 min (15.67-39.20) to release a report. With regard to the identification of increases in lesion burden, AI achieved a sensitivity of 0.962 (95% CI 0.947-1.000) and a specificity of 0.875 (95 %CI 0.833-0.923). The agreement between AI and the radiologist panel was high (Cohen's kappa coefficient 0.839, 95% CI 0.718-0.940). INTERPRETATION: A deep learning algorithm for triaging patients with suspected COVID-19 at fever clinics was developed and externally validated. Given its high accuracy across populations with varied COVID-19 prevalence, integration of this system into the standard clinical workflow could expedite identification of chest CT scans with imaging indications of COVID-19. FUNDING: Special Project for Emergency of the Science and Technology Department of Hubei Province, China.
free
free
free
Lancet+Digit+Health 2020 ; 2 (10): e506-e515
