Selected article for: "RT PCR detection and SARS RT PCR detection"

Author: Xueyan Mei; Hao-Chih Lee; Kaiyue Diao; Mingqian Huang; Bin Lin; Chenyu Liu; Zongyu Xie; Yixuan Ma; Philip M. Robson; Michael Chung; Adam Bernheim; Venkatesh Mani; Claudia Calcagno; Kunwei Li; Shaolin Li; Hong Shan; Jian Lv; Tongtong Zhao; Junli Xia; Qihua Long; Sharon Steinberger; Adam Jacobi; Timothy Deyer; Marta Luksza; Fang Liu; Brent P. Little; Zahi A. Fayad; Yang Yang
Title: Artificial intelligence for rapid identification of the coronavirus disease 2019 (COVID-19)
  • Document date: 2020_4_17
  • ID: 79tozwzq_3
    Snippet: In our study, our proposed joint AI algorithm combining CT images and clinical history achieved an AUC of 0.92 when applied to a testing set of 279 cases. The AI model performed equally well in sensitivity as compared to a senior chest radiologist (AUC of 0.84), and out-performed a less experienced chest fellow (AUC of 0.73). When the AI model used only CT images or only clinical information the performance was lower (AUC of 0.86, and 0.80, respe.....
    Document: In our study, our proposed joint AI algorithm combining CT images and clinical history achieved an AUC of 0.92 when applied to a testing set of 279 cases. The AI model performed equally well in sensitivity as compared to a senior chest radiologist (AUC of 0.84), and out-performed a less experienced chest fellow (AUC of 0.73). When the AI model used only CT images or only clinical information the performance was lower (AUC of 0.86, and 0.80, respectively). The AI model with clinical information only and the joint AI model also improved the detection of SARS-CoV-2 RT-PCR-positive patients who presented with a normal CT, achieving a detection rate of 64% and 68% respectively, compared to radiologists who rated all such patients as SARS-CoV-2 (-). While the vast majority of suspected patients currently have little option but to wait for RT-PCR test results, All rights reserved. No reuse allowed without permission. author/funder, who has granted medRxiv a license to display the preprint in perpetuity.

    Search related documents:
    Co phrase search for related documents
    • AI model and clinical history: 1, 2
    • AI model and clinical information: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
    • AI model and CT image: 1, 2, 3, 4
    • AI model and detection rate: 1
    • AI model and RT PCR test result: 1
    • AI model and senior chest radiologist: 1
    • AI model and suspect patient: 1
    • AI model and test result: 1
    • AI model and testing set: 1
    • AI model and vast majority: 1
    • auc achieve and CT image: 1, 2, 3
    • auc achieve and detection rate: 1
    • auc achieve and respectively auc: 1
    • auc achieve and testing set: 1