Plesničar Andrej F, Bizjak Nena Bagari, Jazbinšek Pika
Health Insurance Institute of Slovenia, SI 1000 Ljubljana, Slovenia.
Healthcare (Basel). 2025 Jun 18;13(12):1464. doi: 10.3390/healthcare13121464.
Healthcare payment systems face challenges such as fraud and overbilling, which often require costly and resource-intensive detection tools. In response, the utility of simple statistical tests was explored in this study as a practical alternative for identifying irregularities in dermatology service payments within the Health Insurance Institute of Slovenia (HIIS). Ten-year-old anonymized billing data from 30 dermatology providers in Slovenia (with a population of 2 million) were analyzed to evaluate the effectiveness of the proposed methodology while aiming to avoid reputational harm to current providers. The dataset from 2014 included variables such as the "number of services charged", "total number of points charged" (under Slovenia's point-based tariff system at the time), "number of points per examination", "average examination values (EUR)", "number of first examinations", and "total number of first/follow-up examinations". Data credibility was assessed using Benford's Law (for calculating χ values and testing null hypothesis rejection at the 95% level), and Grubbs' test, Hampel's test, and T-test were used to identify outliers. An analysis using Benford's Law revealed significant deviations for the "number of services charged" ( < 0.005), "total number of points charged" ( < 0.01), "number of points per examination" ( < 0.0005), and "average examination values (EUR)" ( < 0.005), suggesting anomalies. Conversely, data on the numbers of "first" ( < 0.7) and "total first/follow-up examinations" ( < 0.3) were found to align with Benford's Law, indicating authenticity. Outlier detection consistently identified two institutions with unusually high values for points per examination and average examination monetary value. Simple statistical tests can effectively identify potential irregularities in healthcare payment data, providing a cost-effective screening method for further investigation. Identifying outlier providers highlights areas needing detailed scrutiny to understand anomaly causes.
医疗支付系统面临欺诈和多收费等挑战，这通常需要成本高昂且资源密集的检测工具。作为回应，本研究探讨了简单统计测试的效用，作为识别斯洛文尼亚健康保险研究所（HIIS）皮肤科服务支付违规行为的一种实用替代方法。分析了来自斯洛文尼亚30家皮肤科供应商（人口200万）的十年匿名计费数据，以评估所提出方法的有效性，同时旨在避免对当前供应商造成声誉损害。2014年的数据集包括“收费服务数量”、“收费总点数”（当时斯洛文尼亚基于点数的收费系统下）、“每次检查的点数”、“平均检查价值（欧元）”、“首次检查数量”以及“首次/随访检查总数”等变量。使用本福特定律评估数据可信度（用于计算χ值并在95%水平测试原假设拒绝情况），并使用格拉布斯检验、汉佩尔检验和t检验来识别异常值。使用本福特定律进行的分析显示，“收费服务数量”（<0.005）、“收费总点数”（<0.01）、“每次检查的点数”（<0.0005）和“平均检查价值（欧元）”（<0.005）存在显著偏差，表明存在异常。相反，“首次”（<0.7）和“首次/随访检查总数”（<0.3）的数据与本福特定律相符，表明数据真实。异常值检测始终识别出两家机构，其每次检查的点数和平均检查货币价值异常高。简单统计测试可以有效识别医疗支付数据中的潜在违规行为，为进一步调查提供一种经济高效的筛选方法。识别出异常供应商突出了需要详细审查以了解异常原因的领域。
