Huang Wennuo, Li Yuanzhe, Bao Zhuqing, Ye Jing, Xia Wei, Lv Yan, Lu Jiahui, Wang Chao, Zhu Xi
Department of Radiology, Northern Jiangsu People's Hospital Affiliated to Yangzhou University, Yangzhou, Jiangsu, 225002, People's Republic of China.
Department of CT/MRI, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian, 362000, People's Republic of China.
J Multidiscip Healthc. 2024 Jul 4;17:3109-3119. doi: 10.2147/JMDH.S451301. eCollection 2024.
This study aimed to investigate the knowledge, attitudes, and practice (KAP) of radiologists regarding artificial intelligence (AI) in medical imaging in the southeast of China.
This cross-sectional study was conducted among radiologists in the Jiangsu, Zhejiang, and Fujian regions from October to December 2022. A self-administered questionnaire was used to collect demographic data and assess the KAP of participants towards AI in medical imaging. A structural equation model (SEM) was used to analyze the relationships between KAP.
The study included 452 valid questionnaires. The mean knowledge score was 9.01±4.87, the attitude score was 48.96±4.90, and 75.22% of participants actively engaged in AI-related practices. Having a master's degree or above (OR=1.877, P=0.024), 5-10 years of radiology experience (OR=3.481, P=0.010), AI diagnosis-related training (OR=2.915, P<0.001), and engaging in AI diagnosis-related research (OR=3.178, P<0.001) were associated with sufficient knowledge. Participants with a junior college degree (OR=2.139, P=0.028), 5-10 years of radiology experience (OR=2.462, P=0.047), and AI diagnosis-related training (OR=2.264, P<0.001) were associated with a positive attitude. Higher knowledge scores (OR=5.240, P<0.001), an associate senior professional title (OR=4.267, P=0.026), 5-10 years of radiology experience (OR=0.344, P=0.044), utilizing AI diagnosis (OR=3.643, P=0.001), and engaging in AI diagnosis-related research (OR=6.382, P<0.001) were associated with proactive practice. The SEM showed that knowledge had a direct effect on attitude (β=0.481, P<0.001) and practice (β=0.412, P<0.001), and attitude had a direct effect on practice (β=0.135, P<0.001).
Radiologists in southeastern China hold a favorable outlook on AI-assisted medical imaging, showing solid understanding and enthusiasm for its adoption, despite half lacking relevant training. There is a need for more AI diagnosis-related training, an efficient standardized AI database for medical imaging, and active promotion of AI-assisted imaging in clinical practice. Further research with larger sample sizes and more regions is necessary.
本研究旨在调查中国东南部放射科医生在医学影像中对人工智能（AI）的知识、态度和实践情况。
本横断面研究于2022年10月至12月在江苏、浙江和福建地区的放射科医生中进行。采用自填式问卷收集人口统计学数据，并评估参与者对医学影像中AI的知识、态度和实践情况。使用结构方程模型（SEM）分析知识、态度和实践之间的关系。
本研究共纳入452份有效问卷。知识得分的平均值为9.01±4.87，态度得分为48.96±4.90，75.22%的参与者积极参与与AI相关的实践。拥有硕士及以上学位（OR=1.877，P=0.024）、5-10年放射科工作经验（OR=3.481，P=0.010）、接受过AI诊断相关培训（OR=2.915，P<0.001）以及从事AI诊断相关研究（OR=3.178，P<0.001）与具备充足知识相关。大专学历（OR=2.139，P=0.028）、5-10年放射科工作经验（OR=2.462，P=0.047）以及接受过AI诊断相关培训（OR=2.264，P<0.001）的参与者态度较为积极。知识得分较高（OR=5.240，P<0.001）、副高级专业职称（OR=4.267，P=0.026）、5-10年放射科工作经验（OR=0.344，P=0.044）、使用AI诊断（OR=3.643，P=0.001）以及从事AI诊断相关研究（OR=6.382，P<0.001）与积极实践相关。SEM显示，知识对态度（β=0.481，P<0.001）和实践（β=0.412，P<0.001）有直接影响，态度对实践也有直接影响（β=0.135，P<0.0..01）。
中国东南部的放射科医生对AI辅助医学影像持积极态度，尽管一半的人缺乏相关培训，但他们对其应用表现出扎实的理解和热情。需要更多的AI诊断相关培训、一个高效的医学影像标准化AI数据库，并在临床实践中积极推广AI辅助影像。有必要进行更大样本量和更多地区的进一步研究。
