Prediction of postoperative infection in elderly using deep learning-based analysis: an observational cohort study

Author:

Li Pinhao,Wang Yan,Li Hui,Cheng Baoli,Wu Shuijing,Ye Hui,Ma Daqing,Fang Xiangming,Cao Ying,Gao Hong,Hu Tingju,Lv Jie,Yang Jian,Yang Yang,Zhong Yi,Zhou Jing,Zou Xiaohua,He Miao,Li Xiaoying,Luo Dihuan,Wang Haiying,Yu Tian,Chen Liyong,Wang Lijun,Cai Yunfei,Cao Zhongming,Li Yanling,Lian Jiaxin,Sun Haiyun,Wang Sheng,Wang Zhipeng,Wang Kenru,Zhu Yi,Du Xindan,Fan Hao,Fu Yunbin,Huang Lixia,Huang Yanming,Hwan Haifang,Luo Hong,Qu Pi-Sheng,Tao Fan,Wang Zhen,Wang Guoxiang,Wang Shun,Zhang Yan,Zhang Xiaolin,Chen Chao,Wang Weixing,Liu Zhengyuan,Fan Lihua,Tang Jing,Chen Yijun,Chen Yongjie,Han Yangyang,Huang Changshun,Liang Guojin,Shen Jing,Wang Jun,Yang Qiuhong,Zhen Jungang,Zhou Haidong,Chen Junping,Chen Zhang,Li Xiaoyu,Meng Bo,Ye Haiwang,Zhang Xiaoyan,Bi Yanbing,Cao Jianqiao,Guo Fengying,Lin Hong,Liu Yang,Lv Meng,Shi Pengcai,Song Xiumei,Sun Chuanyu,Sun Yongtao,Wang Yuelan,Wang Shenhui,Zhang Min,Chen Rong,Hou Jiabao,Leng Yan,Meng Qing-tao,Qian Li,Shen Zi-ying,Xia Zhong-yuan,Xue Rui,Zhang Yuan,Zhao Bo,Zhou Xian-jin,Chen Qiang,Guo Huinan,Guo Yongqing,Qi Yuehong,Wang Zhi,Wei Jianfeng,Zhang Weiwei,Zheng Lina,Bao Qi,Chen Yaqiu,Chen Yijiao,Fei Yue,Hu Nianqiang,Hu Xuming,Lei Min,Li Xiaoqin,Lv Xiaocui,Lv Jie,Miao Fangfang,Ouyang Lingling,Qian Lu,Shen Conyu,Sun Yu,Wang Yuting,Wang Dong,Wu Chao,Xu Liyuan,Yuan Jiaqi,Zhang Lina,Zhang Huan,Zhang Yapping,Zhao Jinning,Zhao Chong,Zhao Lei,Zheng Tianzhao,Zhou Dachun,Zhou Haiyan,Zhou Ce,Lu Kaizhi,Zhao Ting,He Changlin,Chen Hong,Chen Shasha,He Jie,Jin Lin,Li Caixia,Pan Yuanming,Shi Yugang,Wen Xiao Hong,Xie Guohao,Zhang Kai,Zhao Bing,Lu Xianfu,Chen Feifei,Liang Qisheng,Lin Xuewu,Ling Yunzhi,Liu Gang,Tao Jing,Yang Lu,Zhou Jialong,Chen Fumei,Cheng Zhonggui,Dai Hanying,Feng Yunlin,Hou Benchao,Gong Haixia,Hu Chun hua,Huang Haijin,Huang Jian,Jiang Zhangjie,Li Mengyuan,Lin Jiamei,Liu Mei,Liu Weicheng,Liu Zhen,Liu Zhiyi,Luo Foquan,Ma Longxian,Min Jia,Shi Xiaoyun,Song Zhiping,Wan Xianwen,Xiong Yingfen,Xu Lin,Yang Shuangjia,Zhang Qin,Zhang Hongyan,Zhang Huaigen,Zhang Xuekang,Zhao Lili,Zhao Weihong,Zhao Weilu,Zhu Xiaoping,Bai Yun,Chen Linbi,Chen Sijia,Dai Qinxue,Geng Wujun,Han Kunyuan,He Xin,Huang Luping,Ji Binbin,Jia Danyun,Jin Shenhui,Li Qianjun,Liang Dongdong,Luo Shan,Lwang Lulu,Mo Yunchang,Pan Yuanyuan,Qi Xinyu,Qian Meizi,Qin Jinling,Ren Yelong,Shi Yiyi,Wang Junlu,Wang Junkai,Wang Leilei,Xie Junjie,Yan Yixiu,Yao Yurui,Zhang Mingxiao,Zhao Jiashi,Zhuang Xiuxiu,Ai Yanqiu,Fang Du,He Long,Huang Ledan,Li Zhisong,Li Huijuan,Li Yetong,Li Liwei,Meng Su,Yuan Yazhuo,Zhang Enman,Zhang Jie,Zhao Shuna,Ji Zhenrong,Pei Ling,Wang Li,Chen Chen,Dong Beibei,Li Jing,Miao Ziqiang,Mu Hongying,Qin Chao,Su Lin,Wen Zhiting,Xie Keliang,Yu Yonghao,Yuan Fang,Hu Xianwen,Zhang Ye,Xiao Wangpin,Zhu Zhipeng,Dai Qingqing,Fu Kaiwen,Hu Rong,Hu Xiaolan,Huang Song,Li Yaqi,Liang Yingping,Yu Shuchun,Guo Zheng,Jing Yan,Tang Na,Jie Wu,Yuan Dajiang,Zhang Ruilin,Zhao Xiaoying,Li Yuhong,Bai Hui-Ping,Liu Chun-Xiao,Liu Fei-Fei,Ren Wei,Wang Xiu-Li,Xu Guan-Jie,Hu Na,Li Bo,Ou Yangwen,Tang Yongzhong,Yao Shanglong,Zhang Shihai,Kong Cui-Cui,Liu Bei,Wang Tianlong,Xiao Wei,Lu Bo,Xia Yanfei,Zhou Jiali,Cai Fang,Chen Pushan,Hu Shuangfei,Wang Hongfa,Jie Wu,Xu Qiong,Hu Liu,Jing Liang,Li Jing,Li Bin,Liu Qiang,Liu Yuejiang,Lu Xinjian,Peng Zhen Dan,Qiu Xiaodong,Ren Quan,Tong Youliang,Wang Zhen,Wang Jin,Wen Yazhou,Wu Qiong,Xia Jiangyan,Xie Jue,Xiong Xiapei,Xu Shixia,Yang Tianqin,Yin Ning,Yuan Jing,Zeng Qiuting,Zhang Baoling,Zheng Kang,Cang Jing,Chen Shiyu,Fang Du,Fan Yu,Fu Shuying,Ge Xiaodong,Guo Baolei,Huang Wenhui,Jiang Linghui,Jiang Xinmei,Jin Lin,Liu Yi,Pan Yan,Ren Yun,Shan Qi,Wang Jiaxing,Wang Fei,Wu Chi,Zhan Xiaoguang,

Abstract

AbstractElderly patients are susceptible to postoperative infections with increased mortality. Analyzing with a deep learning model, the perioperative factors that could predict and/or contribute to postoperative infections may improve the outcome in elderly. This was an observational cohort study with 2014 elderly patients who had elective surgery from 28 hospitals in China from April to June 2014. We aimed to develop and validate deep learning-based predictive models for postoperative infections in the elderly. 1510 patients were randomly assigned to be training dataset for establishing deep learning-based models, and 504 patients were used to validate the effectiveness of these models. The conventional model predicted postoperative infections was 0.728 (95% CI 0.688–0.768) with the sensitivity of 66.2% (95% CI 58.2–73.6) and specificity of 66.8% (95% CI 64.6–68.9). The deep learning model including risk factors relevant to baseline clinical characteristics predicted postoperative infections was 0.641 (95% CI 0.545–0.737), and sensitivity and specificity were 34.2% (95% CI 19.6–51.4) and 88.8% (95% CI 85.6–91.6), respectively. Including risk factors relevant to baseline variables and surgery, the deep learning model predicted postoperative infections was 0.763 (95% CI 0.681–0.844) with the sensitivity of 63.2% (95% CI 46–78.2) and specificity of 80.5% (95% CI 76.6–84). Our feasibility study indicated that a deep learning model including risk factors for the prediction of postoperative infections can be achieved in elderly. Further study is needed to assess whether this model can be used to guide clinical practice to improve surgical outcomes in elderly.

Publisher

Springer Science and Business Media LLC

Subject

Geriatrics and Gerontology,Aging

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

全球学者库

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"全球学者库"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前全球学者库共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2023 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3