Page 70 - 中国全科医学2022-17
P. 70

http://www.chinagp.net   E-mail:zgqkyx@chinagp.net.cn  ·2115·


                                                                                                 ·论著·


           基于人工智能随访预测肺结节增长的影响因素研究



                         1
                                  2
                 1
                                                   1
                                          1
           吴久纯 ,李甜 ,李晓东 ,卓越 ,张玉娇 ,刘敬禹                        1*                                扫描二维码
                                                                                               查看原文
               【摘要】 背景 肺癌的发病率和死亡率均居世界首位,5 年生存率不到 20%,对于早期肺癌的筛查有多种方式,
           其中人工智能(AI)极大提高了早期肺癌的检出率,但目前仍存在对不典型肺结节如何有效管理以尽早发现早期肺癌
           的问题,探究肺结节增长的影响因素对指导临床管理具有重要意义。目的 探讨 AI 随访肺结节增长的影响因素及临
           床应用价值。方法 回顾性选取 2019 年 4 月就诊于锦州医科大学附属第三医院的 175 例肺结节患者作为研究对象,
           根据 AI 分类分为实性结节组 82 例和磨玻璃结节(GGN)组 93 例。收集研究对象的一般资料,并利用 AI 计算收集肺
           结节相关影像学信息,定期随访以观察不同肺结节的增长情况,应用多因素 Cox 比例风险回归分析探讨肺结节增长的
           影响因素。结果 实性结节组的实性占比、平均 CT 值高于 GGN 组(P<0.001)。多因素 Cox 比例风险回归分析结果
           显示,结节平均直径〔HR=2.185,95%CI(1.079,4.425),P=0.030〕、结节体积〔HR=1.001,95%CI(1.000,1.001),
           P=0.022〕、恶性概率〔HR=2.232,95%CI(1.036,4.806),P=0.040〕及表面征象〔HR=2.125,95%CI(1.006,4.489),
           P=0.048〕是实性结节增长的影响因素;平均直径〔HR=2.458,95%CI(1.053,5.739),P=0.038〕、体积〔HR=1.001,
           95%CI(1.000,1.002),P=0.010〕、实性占比〔HR=1.022,95%CI(1.002,1.041),P=0.030〕、恶性概率〔HR=2.386,
           95%CI(1.174,4.850),P=0.016〕及表面征象〔HR=3.026,95%CI(1.492,6.136),P=0.002〕、平均 CT 值〔HR=1.002,
           95%CI(1.000,1.003),P=0.045〕是 GGN 增长的影响因素。结论 肺结节增长受原始结节大小、平均 CT 值、有无
           表面征象及恶性概率等多种因素影响,建议临床医师结合 AI 计算的肺结节增长影响因素确定有效随访时间,以尽早
           发现肺结节增长并及时采取治疗措施。
               【关键词】 肺结节;人工智能;肺肿瘤;磨玻璃结节;随访;危险因素
               【中图分类号】 R 734.2 【文献标识码】 A DOI:10.12114/j.issn.1007-9572.2022.0005
               吴久纯,李甜,李晓东,等 . 基于人工智能随访预测肺结节增长的影响因素研究[J]. 中国全科医学,2022,25(17):
           2115-2120. [www.chinagp.net]
               WU J C,LI T,LI X D,et al. Inflencing factors for pulmonary nodular growth predicted by artificial intelligence-based
           follow-up[J]. Chinese General Practice,2022,25(17):2115-2120.

           Inflencing Factors for Pulmonary Nodular Growth Predicted by Artificial Intelligence-based Follow-up WU
                                             1
                                   2
                1
                                                          1
                        1
           Jiuchun ,LI Tian ,LI Xiaodong ,ZHUO Yue ,ZHANG Yujiao ,LIU Jingyu 1*
           1.Department of Respiratory and Critical Care Medicine,the Third Affiliated Hospital of Jinzhou Medical University,Jinzhou
           121001,China
           2.Department of Critical Care Medicine,the First Affiliated Hospital of Jinzhou Medical University,Jinzhou 121001,China
           *
           Corresponding author:LIU Jingyu,Professor,Chief physician;E-mail:liujingyu0416@163.com
               【Abstract】 Background Lung cancer ranks first in terms of incidence and mortality rates among cancers,with a 5-year
           survival rate of less than 20%. Many ways have been used to screen for early lung cancer,among which artificial intelligence (AI)
           has greatly improved the detection rate. However,how to use AI technologies to effectively manage atypical lung nodules to timely
           find early lung cancer,and to identify associated factors of lung nodule growth,which is an issue significantly associated with the
           guidance of clinical management of lung nodules. Objective To investigate the influencing factors of pulmonary nodules growth
           identified by AI-based follow-up and relevant clinical value. Methods A total of 175 patients with pulmonary nodules admitted
           to the Third Affiliated Hospital of Jinzhou Medical University in April 2019 were selected for a retrospective study. General clinical
           data,and AI-based analysis of imaging information related to pulmonary nodules was collected. The growth of pulmonary nodules
           〔solid nodules(in 82 cases) and ground-glass nodules(in 93 cases) classified by AI-based analysis〕 were observed by
           regular follow-ups. The influencing factors of pulmonary nodules growth were explored by Cox regression analysis. Results

               基金项目:辽宁省科学技术计划项目(2019JH2/10300046)
               1.121001 辽宁省锦州市,锦州医科大学附属第三医院呼吸与危重症医学科
               2.121001 辽宁省锦州市,锦州医科大学附属第一医院危重症医学科
               *
               通信作者:刘敬禹,教授,主任医师;E-mail:liujingyu0416@163.com
               本文数字出版日期:2022-04-28
   65   66   67   68   69   70   71   72   73   74   75