《SSRN,2月19日,A Deep Learning Pipeline for Accurate Differential Diagnosis between Novel Coronavirus Pneumonia and Influenza Pneumonia》

  • 来源专题:COVID-19科研动态监测
  • 编译者: zhangmin
  • 发布时间:2020-02-20
  • A Deep Learning Pipeline for Accurate Differential Diagnosis between Novel Coronavirus Pneumonia and Influenza Pneumonia

    31 Pages Posted: 19 Feb 2020

    Min Zhou

    Shanghai Jiao Tong University (SJTU) - Department of Respiratory and Critical Care Medicine

    Yong Chen

    Shanghai Jiao Tong University (SJTU) - Department of Radiology

    Abstract

    Background: In December, 2019, novel coronavirus pneumonia (NCP) exploded and caused an increasing infection cases and deaths globally. However, potential negative results and shortage of the nucleic acid tests fails to meet the clinical demand and urgent need is warranted for accurate differential diagnosis.

  • 原文来源:https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3539663
相关报告
  • 《MedRixv,2月25日,Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT images》

    • 来源专题:COVID-19科研动态监测
    • 编译者:zhangmin
    • 发布时间:2020-02-26
    • Deep learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) with CT images Ying Song, Shuangjia Zheng, Liang Li, Xiang Zhang, Xiaodong Zhang, Ziwang Huang, Jianwen Chen, Huiying Zhao, Yusheng Jie, Ruixuan Wang, Yutian Chong, Jun Shen, Yunfei Zha, Yuedong Yang doi: https://doi.org/10.1101/2020.02.23.20026930 Abstract Background A novel coronavirus (COVID-19) has emerged recently as an acute respiratory syndrome. The outbreak was originally reported in Wuhan, China, but has subsequently been spread world-widely. As the COVID-19 continues to spread rapidly across the world, computed tomography (CT) has become essentially important for fast diagnoses. Thus, it is urgent to develop an accurate computer-aided method to assist clinicians to identify COVID-19-infected patients by CT images. Materials and Methods We collected chest CT scans of 88 patients diagnosed with the COVID-19 from hospitals of two provinces in China, 101 patients infected with bacteria pneumonia, and 86 healthy persons for comparison and modeling. Based on the collected dataset, a deep learning-based CT diagnosis system (DeepPneumonia) was developed to identify patients with COVID-19. *注,本文为预印本论文手稿,是未经同行评审的初步报告,其观点仅供科研同行交流,并不是结论性内容,请使用者谨慎使用.
  • 《SSRN,2月6日,Clinical Course and Outcomes of Critically Ill Patients of 2019 Novel Coronavirus Pneumonia》

    • 来源专题:COVID-19科研动态监测
    • 编译者:xuwenwhlib
    • 发布时间:2020-02-07
    • Clinical Course and Outcomes of Critically Ill Patients of 2019 Novel Coronavirus Pneumonia 19 Pages Posted: 6 Feb 2020 Corresponding Author: You Shang, Ph.D., M.D. Wuhan Union Hospital Wuhan, Hubei CHINA First Author: Xiaobo Yang Abstract Background: An ongoing outbreak of pneumonia associated with the 2019 novel coronavirus (2019-nCoV) started in December 2019, in Wuhan, China. Information on critically ill patients of 2019-nCoV infection is extremely limited. We aimed to describe the clinical course and outcomes of critically ill patients of 2019-nCoV pneumonia. Methods: In this retrospective study, 52 critically ill patients out of 710 patients, who were diagnosed with 2019-nCoV pneumonia in Wuhan Jinyintan Hospital between the onset of the outbreak and January 26, 2020, were investigated. Only patients treated with high flow nasal cannula or mechanical ventilator were included. Patients who were deceased or who had been hospitalized for at least 14 days were considered for the case reviewed. Epidemiological, demographic, clinical and laboratory data were collected and analyzed to explore the differences between survivors and non-survivors. Findings: Of the 52 critically ill patients, the average age was 59.7 ±13.3 years(mean ± standard deviation), 35 (67.3%) were male, 21 (40.4%) had chronic illness, 51 (98.1%) had fever, 35 (67.3%) had ARDS and 37 (71.2%) required mechanical ventilation. The duration from onset of symptoms to radiological diagnosis of pneumonia was 5 [3-7] (median [interquartile range]) days. Thirty-three (57.7%) patients deceased, and the duration from hospital admission to death was 7 [3 - 11] days. Compared with survivors, non-survivors were older (64.7 ± 11.1 years vs 59.7 ± 13.3 years, p = 0.001), received higher fraction of oxygen therapy (0.87 ± 0.16 vs 0.70 ± 0.18, p = 0.004), developed more ARDS (83.3% vs 45.4%, p = 0.007), required more mechanical ventilation (93.3% vs 40.9%, p = 0.003) and were more likely to be on extracorporeal membrane oxygenation (16.7% vs 4.6%, p = 0.06).