华南预防医学 ›› 2023, Vol. 49 ›› Issue (1): 32-36.doi: 10.12183/j.scjpm.2023.0032

• 论著 • 上一篇    下一篇

广东省基层医生对人工智能辅助诊疗技术的应用意愿分析

万东华1, 江金女1, 潘波2, 梁华3, 吴琳3, 何志辉1, 陈燕铭3   

  1. 1.广东省疾病预防控制中心 广东省公共卫生研究院,广东 广州 511430;
    2.广东省疾病预防控制中心, 广东 广州 511430;
    3.中山大学附属第三医院, 广东 广州 511430
  • 收稿日期:2022-12-05 发布日期:2023-04-03
  • 通讯作者: 何志辉,E-mail: 651173682@qq.com;陈燕铭,E-mail: 1211587508@qq.com
  • 作者简介:万东华(1992—),男,硕士研究生,医师,研究方向为疾病预防与控制;江金女(1983—),女,硕士研究生,主管医师,研究方向为公共卫生
  • 基金资助:
    广州市重点领域研发计划项目(202007040003)

Application willingness of artificial intelligence-assisted diagnosis and treatment technology among primary care physicians in Guangdong Province

WAN Dong-hua1, JIANG Jin-nu1, PAN Bo2, LIANG Hua3, WU Lin3, HE Zhi-hui1, CHEN Yan-ming3   

  1. 1. Guangdong Provincial Institute of Public Health, Guangdong Provincial Center for Disease Control and Prevention, Guangzhou 511430, China;
    2. Guangdong Provincial Center for Disease Control and Prevention, Guangzhou 511430, China;
    3. The Third Affiliated Hospital, Sun Yat-sen University, Guangzhou 511430, China
  • Received:2022-12-05 Published:2023-04-03

摘要: 目的 探讨广东省基层医生对人工智能(artificial intelligence,AI)辅助诊疗技术的应用意愿及其影响因素。方法 采用方便抽样方法选取广东省的基层医生为研究对象,对其人口学特征以及AI辅助诊疗技术应用意愿进行问卷调查。拟合结构方程模型分析基层医生对AI辅助诊疗技术应用意愿的影响因素。结果 纳入广东省基层医生3 490名,平均年龄(32.99±15.89)岁,男性1 815名(52.01%)。基层医生支持AI辅助诊疗技术服务患者、认为AI可促进医疗技术进步和高精尖医疗技术普及、愿意尝试使用或继续使用AI辅助诊疗技术为患者提供服务的同意率分别为82.15%、78.83%、78.45%。结构方程模型结果显示,感知有用性、感知满意度、感知服务质量、感知信息质量以及较高学历对基层医生应用AI辅助诊疗技术产生正向影响,标化路径系数分别为0.354、0.268、0.121、0.270、0.035(P<0.05或P<0.01);较高职称对基层医生应用AI辅助诊疗技术产生负向影响,标化路径系数为-0.045(P<0.01)。结论 广东省基层医生对AI辅助诊疗技术的应用意愿总体较高,感知有用性、感知满意度、感知信息质量、感知服务质量、学历、职称是基层医生应用AI辅助诊疗技术的影响因素。

关键词: 基层医生, 人工智能, 辅助诊疗, 意愿, 结构方程模型

Abstract: Objective To explore the application willingness of artificial intelligence (AI)-assisted diagnosis and treatment technology and its influencing factors among primary care physicians in Guangdong Province. Methods Primary care physicians in Guangdong Province were selected by convenient sampling method to conduct a questionnaire survey on their demographic characteristics and willingness to apply AI-assisted diagnosis and treatment technology. The structural equation modeling was fitted to analyze the influencing factors of primary care physicians' willingness to apply AI-assisted diagnosis and treatment technology. Results A total of 3 490 primary care physicians from Guangdong Province were included, with an average age of (32.99±15.89) years, and 1 815 were male (52.01%). The consent rates of primary care physicians who supported AI-assisted diagnosis and treatment technology to serve patients, believed that AI could promote the progress of medical technology and the popularization of advanced and sophisticated medical technology, and were willing to try or continue to use AI-assisted diagnosis and treatment technology to provide services for patients was 82.15%, 78.83%, and 78.45% respectively. The results of structural equation modeling showed that perceived usefulness, perceived satisfaction, perceived service quality, perceived information quality, and a higher education level had a positive impact on the willingness of primary care physicians to apply AI-assisted diagnosis and treatment technology, and the standardized path coefficients were 0.354, 0.268, 0.121, 0.270, and 0.035 respectively (P<0.05 or P<0.01). The higher professional title had a negative impact on the willingness of primary care physicians to apply AI-assisted diagnosis and treatment technology, and the standardized path coefficient was -0.045 (P<0.01). Conclusions Primary care physicians' willingness to apply AI-assisted diagnosis and treatment technology is generally high in Guangdong Province. Perceived usefulness, perceived satisfaction, perceived information quality, perceived service quality, education level, and professional title are the influencing factors of primary care physicians' willingness to apply AI-assisted diagnosis and treatment technology.

Key words: Primary care physician, Artificial intelligence, Assisted diagnosis and treatment, Willingness, Structural equation modeling

中图分类号: 

  • R192.3