Subjects: Medicine, Pharmacy >> Preventive Medicine and Hygienics submitted time 2023-11-01 Cooperative journals: 《中国全科医学》
Abstract： With the wide application of artificial intelligence（AI）in the medical field，more and more AI#2;based clinical decision support systems have been applied in the clinical diagnosis，screening，and other fields. Early clinical evaluation is important for evaluating the clinical performance，safety，and human factors of AI-based clinical decision support systems，and laying the foundation for large-scale trials. However，the transparency and integrity of the clinical reports need to be improved. The Developmental and Exploratory Clinical Investigations of Decision support systems driven by Artificial Intelligence（DECIDE-AI）was officially published online in May 2022. Based on this guideline and relative literature，this paper explores the transparent reporting of early-stage clinical evaluation of AI-based decision support systems，in order to help developers and researchers of AI-based clinical decision support system better understand and apply the relevant guidelines，and improve the reporting transparency of early clinical evaluation of AI-based clinical decision support systems.
Subjects: Medicine, Pharmacy >> Preventive Medicine and Hygienics submitted time 2023-11-01 Cooperative journals: 《中国全科医学》
LAI, Honghao
GUO, Jihua
YOU, Liangzhen
WANG, Jiabo
LIU, Cunzhi
LIU, Yue
LIU, Baoli
SUN, Xin
LI, Hui
YANG, Zhongqi
JI, Guang
ZHAO, Linhua
ZHAO, Hui
SHANG, Hongcai
ZENG, Fang
WEI, Xu
ZHANG, Xiaoxiao
GE, Long
Abstract： Background The effective evaluation of scientific and technological achievements in traditional Chinese medicine（TCM） is of great significance in promoting the innovative development of TCM. Previous evaluations of scientific and technological achievements in TCM often used a generalized evaluation method，leading to problems such as inappropriate indicators and limited dimensions，which is not conducive to reflecting the multiple values of achievements in a scientific and comprehensive way. Consequently，there is an urgent need to establish categorized and multi-dimensional evaluation index system for the evaluation of scientific and technological achievements in TCM in the new period. Objective To establish a scientific，categorized，reliable and comprehensive evaluation index system that reflects the principles of TCM and highlights its unique advantages aiming at the scientific and technological achievements in TCM，in accordance with the contemporary requirements for scientific and technological evaluation in China. Methods This study began in November 2022 and was completed in May 2023. A preliminary index framework was developed through literature review and focus group discussions. Delphi expert consultation was then conducted over two rounds to determine the evaluation indexes and points. The hierarchical analysis method was used to calculate the weight of each index. Results The final evaluation index system of scientific and technological achievements in TCM clinical research comprised 10 threshold indicators，4 primary indicators，17 secondary indicators，and 17 evaluation points. After testing，the positive coefficient of experts in both rounds of Delphi method implementation was 100%，the authority coefficient was 0.94 and 0.93，respectively. The Kendall's W consistency test for each level of indicators yielded two-tailed significance（P<0.05），indicated high levels of expert positivity and authority，strong consistency of expert opinion，and reliable consulting results. Conclusion This study constructs a scientific，reasonable，reliable and easy-to-operate evaluation index system for scientific and technological achievements in TCM clinical research. The indexes cover a wide range with highly differentiated weights and TCM characteristics，which is conducive to highlighting the core strengths while comprehensively considering the multiple value of the results. Additionally，the associated evaluation points，enhancing the operationalization of the index system，may potentially serve as a valuable reference for related evaluation activities.
Hits
Hits
Downloads
Comment