Comparative Efficiency Analysis of OECD Health Systems: FDH vs. Machine Learning Approaches with Efficiency Analysis Trees (EAT and RFEAT).

IF 2.5 4区医学 Q3 HEALTH POLICY & SERVICES Cost Effectiveness and Resource Allocation Pub Date : 2025-02-22 DOI:10.1186/s12962-025-00607-x

Yejin Joo

{"title":"Comparative Efficiency Analysis of OECD Health Systems: FDH vs. Machine Learning Approaches with Efficiency Analysis Trees (EAT and RFEAT).","authors":"Yejin Joo","doi":"10.1186/s12962-025-00607-x","DOIUrl":null,"url":null,"abstract":"Background: As health expenditure continues to rise due to income growth, technological advancements, and an aging population, it has become increasingly important to accurately measure and improve the efficiency of health systems. This is because financial resources are limited, and the allocation of resources can significantly influence the quality of health systems and health outcomes.Methods: This study applies machine learning techniques-Efficiency Analysis Trees (EAT) and Random Forest for Efficiency Analysis Trees (RFEAT)-to evaluate the efficiency of health systems in 36 OECD countries, comparing the results with those from the traditional free disposal hull (FDH) method.Results: Analysis shows high discrimination power in the order of RFEAT, EAT, and FDH. The correlation in efficiency rankings shows more than 80% similarity between RFEAT and EAT, while both show less than 80% similarity with FDH. According to RFEAT estimates, the countries with the highest efficiency are South Korea, Switzerland, and Costa Rica, whereas the United States, Lithuania, and Latvia are identified as the least efficient. The group-level analysis reveals that Asian countries, on average, perform more efficiently followed by Oceania, Europe, and the Americas. The groups with higher out-of-pocket healthcare expenditures per capita tend to show slightly better efficiency and the group with the smallest elderly population proportion exhibits the highest average health system efficiency.Conclusion: Traditional methods like FDH are prone to inefficiency underestimation, especially in small samples with multiple variables. This study demonstrates the potential of machine learning approaches like EAT and RFEAT to provide more reliable efficiency estimates. These methods can help policymakers make better resource allocation decisions by mitigating inefficiency underestimation and offering greater discrimination power.","PeriodicalId":47054,"journal":{"name":"Cost Effectiveness and Resource Allocation","volume":"23 1","pages":"4"},"PeriodicalIF":2.5000,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847381/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cost Effectiveness and Resource Allocation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12962-025-00607-x","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"HEALTH POLICY & SERVICES","Score":null,"Total":0}

引用次数: 0

Abstract

Background: As health expenditure continues to rise due to income growth, technological advancements, and an aging population, it has become increasingly important to accurately measure and improve the efficiency of health systems. This is because financial resources are limited, and the allocation of resources can significantly influence the quality of health systems and health outcomes.

Methods: This study applies machine learning techniques-Efficiency Analysis Trees (EAT) and Random Forest for Efficiency Analysis Trees (RFEAT)-to evaluate the efficiency of health systems in 36 OECD countries, comparing the results with those from the traditional free disposal hull (FDH) method.

Results: Analysis shows high discrimination power in the order of RFEAT, EAT, and FDH. The correlation in efficiency rankings shows more than 80% similarity between RFEAT and EAT, while both show less than 80% similarity with FDH. According to RFEAT estimates, the countries with the highest efficiency are South Korea, Switzerland, and Costa Rica, whereas the United States, Lithuania, and Latvia are identified as the least efficient. The group-level analysis reveals that Asian countries, on average, perform more efficiently followed by Oceania, Europe, and the Americas. The groups with higher out-of-pocket healthcare expenditures per capita tend to show slightly better efficiency and the group with the smallest elderly population proportion exhibits the highest average health system efficiency.

Conclusion: Traditional methods like FDH are prone to inefficiency underestimation, especially in small samples with multiple variables. This study demonstrates the potential of machine learning approaches like EAT and RFEAT to provide more reliable efficiency estimates. These methods can help policymakers make better resource allocation decisions by mitigating inefficiency underestimation and offering greater discrimination power.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

经合组织卫生系统的效率比较分析：FDH 与效率分析树（EAT 和 RFEAT）的机器学习方法。

背景：由于收入增长、技术进步和人口老龄化导致卫生支出持续增加，准确衡量和提高卫生系统的效率变得越来越重要。这是因为财政资源有限，而资源的分配可以对卫生系统的质量和卫生结果产生重大影响。方法：本研究应用机器学习技术——效率分析树（EAT）和效率分析树随机森林（RFEAT）——来评估36个经合组织国家卫生系统的效率，并将结果与传统的自由处置船体（FDH）方法进行比较。结果：分析显示，RFEAT、EAT、FDH的鉴别力依次高。效率排名的相关性显示，RFEAT和EAT之间的相似性超过80%，而两者与FDH的相似性均低于80%。根据RFEAT的估计，效率最高的国家是韩国、瑞士和哥斯达黎加，而美国、立陶宛和拉脱维亚被认为是效率最低的。群体层面的分析显示，亚洲国家的平均效率更高，其次是大洋洲、欧洲和美洲。人均自付医疗费用较高的群体往往表现出略好的效率，老年人口比例最小的群体表现出最高的平均卫生系统效率。结论：FDH等传统方法容易出现低效率低估，特别是在多变量的小样本中。这项研究证明了像EAT和RFEAT这样的机器学习方法在提供更可靠的效率估计方面的潜力。这些方法可以通过减轻低效率低估和提供更大的歧视权力，帮助决策者做出更好的资源配置决策。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Cost Effectiveness and Resource Allocation HEALTH POLICY & SERVICES-

CiteScore

3.40

自引率

4.30%

发文量

审稿时长

34 weeks

期刊介绍： Cost Effectiveness and Resource Allocation is an Open Access, peer-reviewed, online journal that considers manuscripts on all aspects of cost-effectiveness analysis, including conceptual or methodological work, economic evaluations, and policy analysis related to resource allocation at a national or international level. Cost Effectiveness and Resource Allocation is aimed at health economists, health services researchers, and policy-makers with an interest in enhancing the flow and transfer of knowledge relating to efficiency in the health sector. Manuscripts are encouraged from researchers based in low- and middle-income countries, with a view to increasing the international economic evidence base for health.