A Systematic Review of Research on DRG Payment Abnormal Warning Model
Author information+
Show less
History+
Received
2025-03-04
Issue Date
2025-12-29
Abstract
Objective: In order to solve the problems of DRG abnormal grouping such as upcoding, downcoding and ambiguous cases, a systematic review was carried out on the relevant articles on DRG abnormal grouping models at home and abroad. Methods: The PRISMA framework was used to evaluate the quality of literature and reports, and the research design, overall trends, data sources, input and output variables, evaluation indicators and other aspects of literature models were analyzed. Results: The research design types of the six categories of literature were summarized, and it was found that deep learning methods had developed rapidly in foreign countries since 2020, with significant features such as multi-center data sources, text-based input variables, output variables by type, and high model evaluation performance. Besides, scientific problems, model characteristics and limitations were extracted. Conclusion: There is a lack of research on whole-disease group and high-precision DRG payment abnormal warning models based on electronic medical record text data with deep learning methods. In the future, continuous exploration is needed to develop DRG payment abnormal warning tools based on deep learning of electronic medical record structured and unstructured data, in order to further promote the deepening of DRG payment reform.
A Systematic Review of Research on DRG Payment Abnormal Warning Model[J]. China Health Insurance. 2025, 0(3): 60-67 https://doi.org/10.19546/j.issn.1674-3830.2025.3.007
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] 崔斌,朱兆芳.国家医疗保障疾病诊断相关分组(CHS-DRG)制定与实施的关键环节探讨[J].中国医疗保险,2021(05):47-51. [2] PAGE M J, MOHER D, BOSSUYT P M, et al.PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews[J].BMJ, 2021, 372: n160. [3] 王筱,张朝勇,任雪玲,等.基于决策树模型的手足口病住院患者DRGs分组研究[J].现代预防医学,2023(01):121-126+158. [4] 孙梗钤,卿勇,张眆凯,等.基于决策树和结构方程模型的HIV/AIDS患者CHS-DRG分组效果检验[J].现代预防医学,2023(08):1499-1503. [5] 姜德超,徐凤琴.基于CHAID决策树模型的病例组合方案应用研究[J].中国卫生质量管理,2019(03):37-40. [6] 谢冰珏,佘颖,唐路,等.基于决策树模型的DRG优化分组探索——以新生儿疾病外科组为例[J].卫生经济研究,2023(02):47-51. [7] 权晓雯,王艳,杨圆圆,等.基于分位数回归和决策树模型的跌倒患儿控费组合分析[J].中国卫生经济,2023,42(10):45-49. [8] 高峰,郑二维,张清芝,等.基于决策树模型脑卒中患者住院费用DRG分组实证研究[J].中国卫生经济,2020,39(04):33-35. [9] 翁小瑜,席淑新,方超.基于决策树模型的白内障患者住院费用分组研究[J].中国医院统计,2023,30(05):371-375+380. [10] 李晓雨,李文瑾,田立启.基于CHAID算法的肝癌患者住院费用DRGs分组及超限费用影响因素研究[J].中国社会医学杂志,2023,40(04):497-501. [11] 华恃彬,任晋文,朱佳英.E-CHAID决策模型下骨髓增生异常综合征DRGs分组实际运行效果分析[J].中国医院统计,2024,31(02):124-128+133. [12] 肖静,许琼琼,高月霞,等.基于回归树模型的乳腺癌住院费用病例组合研究[J].中国卫生统计,2016,33(05):789-791+795. [13] 苏勇.基于决策树E-CHAID算法建立股骨颈骨折病例的DRGs分组[J].中国病案,2022,23(10):62-66. [14] 王锦毓,袁波英,杨永挺.基于决策树模型的不同放疗方式对住院费用影响因素分析[J].中国病案,2022,23(03):50-53. [15] 许琼琼,肖静,沈康,等.基于决策树模型食管癌病例组合研究[J].中国卫生统计,2016,33(04):563-566. [16] 程亮亮,李亚茜,段占祺,等.不同粗分组方法建立DRGs模型的差异对比研究[J].中国卫生统计,2017,34(03):404-407. [17] 张生雯,杨少伦,陈永聪.基于决策树模型的脑梗死患者疾病诊断相关分组研究[J].中国慢性病预防与控制,2024,32(07):481-485+492. [18] 彭伊婧,孙琰,余仁强,等.基于决策树模型的早产儿病例住院费用的分组研究[J].中国卫生经济,2023,42(04):30-33. [19] 魏凌云,韩栋,徐金龙,等.妇婴疾病诊断相关分组模型研究[J].长治医学院学报,2015,29(02):116-119. [20] 张蕾,王圣友.基于决策树CHAID算法老年性白内障患者DRGs分组研究[J].中国病案,2019,20(10):55-59. [21] 高月霞,许琼琼,肖静,等.基于回归树模型的肝癌住院费用病例组合研究[J].中国卫生统计,2017,34(05):726-728. [22] 徐偲瑜,郎肖玲,李松阳,等.基于决策树模型的卵巢恶性肿瘤患者住院费用疾病诊断相关分组实证研究[J].实用妇产科杂志,2024,40(04):322-326. [23] 孙菲,韩俊洋,张文倩,等.基于决策树模型的急性心肌梗死病例组合研究[J].中国病案,2021,22(03):75-79. [24] 宁传英,邵慧丽.基于决策树模型急性阑尾炎患者DRGs分组研究[J].中国卫生统计,2018,35(04):584-586. [25] 涂开荣,樊涛,王志芳,等.基于决策树E-CHAID算法的膝关节骨性关节炎患者住院费用DRGs的建立[J].重庆医学,2024,53(19):3029-3033. [26] 霍振昂,董振廷,范军星,等.基于回归树算法的心脏病手术患者住院费用DRGs分组研究[J].中国卫生经济,2017,36(09):32-34. [27] 严肃,黄萍,江华梅,等.基于CHAID算法的急性胰腺炎患者DRGs分组分析[J].中国社会医学杂志,2024,41(03):369-373. [28] 宁传英,邵慧丽.基于决策树模型急性心肌梗死患者DRGs分组研究[J].中国病案,2019,20(08):33-36. [29] 周鹏飞,杨孝光,路强,等.恶性肿瘤术后化疗住院患者DRG分组研究——基于E-CHAID算法[J].卫生经济研究,2023,40(06):35-39+43. [30] 陈婷,姜小明.基于决策树模型的脑梗死患者住院费用及病例组合分析[J].中国病案,2021,22(05):67-69+112. [31] 闫晓婷,任洁,李红霞,等.基于决策树模型HC25病组DRGs细分组及住院费用的影响因素研究[J].安徽医学,2024,45(04):505-510. [32] 黄正正,杨思睿,沈绍武,等.基于中医医院双重诊断的病例相关分组模型研究[J].中国医院,2022,26(12):53-56. [33] 周颖,梁冰,钱静,等.基于结构方程模型的DRG高倍率病例住院费用影响因素分析[J].现代预防医学,2023,50(23):4333-4337+4343. [34] 吴尔律,梁洪彬,罗海琼,等.基于机器学习的DRG分组预测研究[J].信息与电脑(理论版),2023,35(05):22-25. [35] LI G H, POLY T N, LI Y C, et al.Deep DRG: performance of artifcial intelligence model for real-time prediction of diagnosis-telated groups[Z].1-14. [36] SHIN H, LEE J, AN Y, et al.A scoring model to detect abusive medical institutions based on patient classification system: diagnosis-related group and ambulatory patient group[J].Journal of biomedical informatics, 2021. [37] LIU J, CAPURRO D, NGUYEN A, et al.Early prediction of diagnostic-related groups and estimation of hospital cost by processing clinical notes[J].npj digital medicine, 2021, 4(1): 103. [38] SOUZA J, SANTOS J V, CANEDO V B, et al.Importance of coding co-morbidities for APR-DRG assignment: focus on cardiovascular and respiratory diseases:[J].The HIM journal, 2020(1). [39] ANGELOWER S V, DUITAMA M J F, ARIAS-LONDOO J D.Classification of diagnosis-related groups using computational intelligence techniques[C].2020, 000(9247726). [40] FENG Y, LIN S, LIN E J, et al.Identifying candidates for medical coding audits: demonstration of a data driven approach to improve medicare severity diagnosis-related group coding compliance[M].Springer international publishing, 2019: 47-57. [41] GARTNER D, KOLISCH R, NEILL D B, et al.Machine learning approaches for early DRG classification and resource allocation[J].Informs journal on computing, 2015, 27(4): 718-734. [42] WANG H, GAO C, DANTONA C, et al.DRG-LLaMA : tuning LLaMA model to predict diagnosis-related group for hospitalized patients[J].npj digital medicine, 2024, 7(1). [43] LIU S, LIU X, JI W, et al.How can deep learning retrieve the write-missing additional diagnosis from Chinese electronic medical record for DRG[Z].Arxiv, 2023. [44] HE Y, WANG C, ZHANG S, et al.KG-MTT-BERT: knowledge graph enhanced bert for multi-type medical text classification[Z].arXiv preprint arXiv:2210.03970, 2022. [45] LIU X, FANG C, WU C, et al.DRG grouping by machine learning: from expert-oriented to data-based method[J].BMC medical informatics and decision making, 2021, 21(1): 1-11. [46] 卢洪满.基于无监督算法的DRG细分组在编码高套上的应用研究[J].数字通信世界,2022(12):117-119. [47] SUZUKI T, DOI S, SHIMADA G, et al.Auto-selection of DRG codes from discharge summaries by text mining in several hospitals: analysis of difference of discharge summaries.[J].Studies in health technology & informatics, 2010, 160(Pt 2): 1020. [48] 王纯青,陶丽,李培山.病例临床复杂模型的改进及其在DRGs中的应用[J].现代医药卫生,2020,36(12):1933-1935. [49] LIU W, ZHOU P, ZHAO Z, et al.K-BERT: enabling language representation with knowledge graph[J].Proceedings of the AAAI conference on artificial intelligence, 2020, 34(3): 2901-2908. [50] OSTENDORFF M, BOURGONJE P, BERGER M,et al.Enriching BERT with knowledge graph embeddings for document classification[Z].2019.
