基于多模态深度学习的新型冠状病毒肺炎重症转化风险预测  

Multimodal deep learning for predicting COVID-19 patients at high-risk for serious illness

作　　者：李仕康 李卓 徐瑞卿 严晓峰[1] 李建华 吕亮 宋玉燕[1] 孙强中 李同心[1] 钱斓兰 张英[1] Li Shikang;Li Zhuo;Xu Ruiqing;Yan Xiaofeng;Li Jianhua;Lyu Liang;Song Yuyan;Sun Qiangzhong;Li Tongxin;Qian Lanlan;Zhang Ying(Chongqing Public Health Center Medical Treatment,Chongqing,400036,China;School of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;Department of Computer Science,University of Sheffield,Sheffield UK S102TN;Chongqing Chengyou Health Management Co.Ltd.,Chongqing 400042,China)

机构地区：[1]重庆市公共卫生医疗救治中心,重庆400036 [2]重庆邮电大学计算机科学与技术学院,重庆400065 [3]英国谢菲尔德大学计算机科学系,英国谢菲尔德S102TN [4]重庆诚友健康管理有限公司,重庆400042

出　　处：《新发传染病电子杂志》2021年第2期133-137,共5页Electronic Journal of Emerging Infectious Diseases

基　　金：重庆市技术创新与应用发展专项重点项目(cstc2020jscx-fyzxX0023)。

摘　　要：目的利用深度学习和大数据的技术来识别潜在新型冠状病毒肺炎重症转化高风险患者,帮助医生及时制订有针对性的救治方案。方法收集整理2020年1月24日到2020年2月16日在重庆市公共卫生医疗救治中心收治的216例新型冠状病毒肺炎患者的全病程多模态(即不同类型)的数据,构建了基于多模态深度学习的评估预测模型,对患者当前的病情严重程度进行评估,并对轻症患者发生重症转化的风险进行预测。结果该模型对患者当前状态的病情评估准确度高于95%,对轻症患者发展成为重症患者的预测准确度高于90%。结论基于多模态深度学习模型比传统线性回归模型预测更准确。同时利用多模态诊疗数据能够对新型冠状病毒肺炎重症转化风险进行准确预测。Objective Using deep learning and big data technology to identify potential high-risk patients with severe conversion of COVID-19,we aim to build a deep learning model so as to identify potential high-risk patients and help doctors make timely individualized treatment plan.Methods From 24 January,2020 to 16 February,2020,216 cases of COVID-19 patients’many modalities data from Chongqing Public Health Center were collected.We build a novel deep learning model for assessing patients’current condition and predicting those who are at high risk for developing severe illness.Results Extensive experimental results show that our model can achieve the over 95%and 90%accuracies for assessment and prediction,respectively.Conclusion The multimodal deep learning model outperforms conventional linear regression model.Meanwhile,Multimodal data can accurately predict the risk of severe transformation of COVID-19.

关 键 词：新型冠状病毒肺炎 病情评估及预测 深度学习 多模态数据融合 

分 类 号：R563.1[医药卫生—呼吸系统]