Analysis of the current situation and development trend of bone age assessment of children in China based on questionnaires
白凤森 1袁新宇 1马毅民 2杨洋 1闫淯淳 1辛海燕 1程晓光 2胡凌
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 首都儿科研究所附属儿童医院放射科，北京 100020
2. 首都医科大学附属积水潭医院放射科，北京100035
折叠
摘要
目的 基于调查问卷分析国内儿童骨龄评估的现状，特别是人工智能（AI）辅助骨龄评价系统在临床中的应用。 方法 该研究为断面研究。通过文献法和专家访谈法自行定制调查问卷，全卷包括22个问题，通过微信小程序问卷星的形式发布于多个协会医师群，以放射科及儿科医师为主，并委托其在医院内开展调查。汇总并分析各类问题的结果，计数资料的比较采用χ2检验。 结果 共回收有效调查问卷450份，涵盖162所医疗机构，覆盖26个省、自治区、直辖市，其中232份（51.6%）来自87所（53.7%）三级医院，218份（48.4%）来自75所（46.3%）二级医院。调查对象中115人（25.6%）为高级职称，137人（30.4%）为中级职称，198人（44.0%）为初级职称。75.9%（66/87）的三级医疗机构和26.7%（20/75）的二级医疗机构开展了儿童骨龄测量，差异有统计学意义（χ2=39.1，P<0.001）。骨龄评估时以左手腕摄片为主（76.0%，123/162），采用图谱法评估的机构占72.8%（118/162）、计分法的机构占17.9%（29/162）。认为在骨龄评估时应使用AI技术辅助者占98.4%（443/450），但仅有9.3%（15/162）的医疗机构使用AI辅助技术。 结论 目前骨龄评估已经在医疗机构中广泛开展，但存在检查方法不规范、评估标准不统一、评估结果欠精确问题。广大医师对AI技术辅助诊断存在期望，但使用者较少。 Objective Based on the questionnaire, to analyze the current status of children′s bone age assessment in China, especially the application of artificial intelligence (AI)-assisted bone age assessment system in the clinic. Methods This was a cross-sectional study. The questionnaire was adapted by ourselves through the literature method and expert interview method, and the whole volume included 22 questions, which were released in the form of WeChat applet questionnaire star to the physician groups of several associations and entrusted to the radiology and paediatricians with senior titles. The results of the different types of questions were summarised and analyzed, and the chi-square test was used to compare the count data. Results A total of 450 valid questionnaires were collected from 162 medical institutions in 26 provinces and cities and autonomous regions, of which 232 (51.6%) were from 87 (53.7%) tertiary hospitals and 218 (48.4%) from 75 (46.3%) secondary hospitals. Of the respondents, 115 (25.6%) were senior, 137 (30.4%) middle and 198 (44.0%) junior. Child bone age measurement was performed at 75.9% (66/87) of tertiary care organizations and 26.7% (20/75) of secondary care organizations, and the difference was statistically significant (χ2=39.10, P<0.001). Left wrist radiographs were predominantly used for bone age assessment (76.0%, 123/162), with 72.8% (118/162) of sites using the ATLAS method of assessment and 17.9% (29/162) using the scoring method. A total of 98.4% (443/450) of respondents agreed that AI technology should be used to assist in bone age assessment, but only 9.3% (15/162) of healthcare organizations used AI-assisted technology. Conclusion At present, bone age assessment is widely used in medical institutions, but there are problems with non-standardized examination methods, inconsistent assessment standards, and imprecise assessment results. Expectations for AI technology-assisted diagnosis exist among a wide range of physicians, but there are fewer users.
Abstract
Objective Based on the questionnaire, to analyze the current status of children′s bone age assessment in China, especially the application of artificial intelligence (AI)-assisted bone age assessment system in the clinic. Methods This was a cross-sectional study. The questionnaire was adapted by ourselves through the literature method and expert interview method, and the whole volume included 22 questions, which were released in the form of WeChat applet questionnaire star to the physician groups of several associations and entrusted to the radiology and paediatricians with senior titles. The results of the different types of questions were summarised and analyzed, and the chi-square test was used to compare the count data. Results A total of 450 valid questionnaires were collected from 162 medical institutions in 26 provinces and cities and autonomous regions, of which 232 (51.6%) were from 87 (53.7%) tertiary hospitals and 218 (48.4%) from 75 (46.3%) secondary hospitals. Of the respondents, 115 (25.6%) were senior, 137 (30.4%) middle and 198 (44.0%) junior. Child bone age measurement was performed at 75.9% (66/87) of tertiary care organizations and 26.7% (20/75) of secondary care organizations, and the difference was statistically significant (χ2=39.10, P<0.001). Left wrist radiographs were predominantly used for bone age assessment (76.0%, 123/162), with 72.8% (118/162) of sites using the ATLAS method of assessment and 17.9% (29/162) using the scoring method. A total of 98.4% (443/450) of respondents agreed that AI technology should be used to assist in bone age assessment, but only 9.3% (15/162) of healthcare organizations used AI-assisted technology. Conclusion At present, bone age assessment is widely used in medical institutions, but there are problems with non-standardized examination methods, inconsistent assessment standards, and imprecise assessment results. Expectations for AI technology-assisted diagnosis exist among a wide range of physicians, but there are fewer users.
万方数据