首页|ICD编码人工智能审核质控模式的设计与效果研究

ICD编码人工智能审核质控模式的设计与效果研究

扫码查看
目的 设计ICD编码人工智能审核质控模式并进行效果评价,以提高编码准确率.方法 抽取经考核合格的质控人员按照《住院病案首页数据填写质量规范(暂行)》(围卫办医发[2016]24号)和《某院住院病案首页填写和质控规则》,对抽取的人工智能审核模块上线前2021年2月1日-2021年10月31日住院病案首页27 359份,上线后2022月1日-2022年10月31日住院病案首页60 239份编码质量逐份进行质控,对主要诊断及编码漏编、错编、选错等情况进行记录.结果 系统上线后医师填写正确率高于系统上线前(x2=390.596,P<0.05),医师填写各项错误原因错误率明显下降(手术/操作漏填x2=147.13,P<0.05、漏诊断x2=6.50,P<0.05、主要诊断选择错误x2=5.76,P<0.05、诊断填写错误x2=3.88,P<0.05、手术/操作选择错误x2=13.08,P<0.05、多填诊断x2=25.16,P<0.05);编码员编码正确率高于系统上线前(Z2=546.384,P<0.05);编码员各项错误类型错误率明显下降(主诊编码错误x2=571.922,P<0.05、手术/操作编码错误x2=36.1,P<0.05、漏编手术/操作码x2=4.18,P<0.05、漏编码x2=36.05,P<0.05、疾病与编码不符x2=74.05,P<0.05、未合并编码x2=101.78,P<0.05).结论 人工智能ICD编码审核质控模式的实施可实现ICD编码全面实时质控,编码完整性、合理性、正确性获得大大提升,可显著提高编码质控效率和质量.
Design and Effect Study of ICD Coded Artificial Intelligence Audit Quality Control Mode
Objectives To design the ICD coding artificial intelligence audit quality control model and evaluate the effect,so as to improve the coding accuracy.Methods Qualified quality control personnel were selected according to the"Quality Specification for Filling in the Frontt Page Data of Inpatient Medical Records(Interim)"(Health Office Medical[2016]No.24)and"Rules for filling in the front page of Inpatient Medical Records and Quality Control of a Hospital".Before the launch of the extracted artificial intelligence review module,27 359 front pages of inpatient medical records from February 1st,2021 to October 31st,2021,and 60 239 front pages of inpatient medical records from October 1st,2022 to October 31st,2022 were quality-controlled one by one,and the main diagnosis and the situation of missing coding,wrong coding and wrong selection were recorded.Results After the system was launched,the correct rate of doctors'filling in was higher than that before the system was launched(x2=390.596,P<0.05),and the error rate of doctors'filling in the causes of errors decreased significantly(surgery/operation omission x2=147.13,P<0.05,missed diagnosis x2=6.50,P<0.05,major diagnosis selection error x2=5.76,etc.).P<0.05,diagnosis filling error x2=3.88,P<0.05,surgery/operation selection error x2=13.08,P<0.05,multiple diagnosis x2=25.16,P<0.05);The coding accuracy rate of coders was higher than that before the system went online(x2=546.384,P<0.05).The error rate of various error types of coders decreased significantly(main diagnosis code error x2=571.922,P<0.05,surgery/operation code error x2=36.1,P<0.05,missed surgery/operation code x2=4.18,P<0.05,missed code x2=36.05,P<0.05,missed code x2=36.05,P<0.05,disease does not match code x2=74.05,P<0.05,uncombined code x2=101.78,P<0.05).Conclusions The implementation of artificial intelligence ICD code audit quality control mode could realize comprehensive and real-time quality control of ICD code,and the integrity,rationality and correctness of code were greatly improved.It could significantly improve the efficiency and quality of coding quality control.

Disease diagnosis and classificationCodeLogic auditQuality controlArtificial intelligenceQuality control mode

袁素华、李毅莲

展开 >

中山市小榄人民医院病案统计科,广东省,中山市,528415

疾病诊断分类 编码 逻辑审核 质控 人工智能 质控模式

&&

200421113453848

2024

中国病案
中国医院协会

中国病案

CSTPCD
影响因子:1.197
ISSN:1672-2566
年,卷(期):2024.25(10)