Leusder Maura, Relijveld Sven, Demirtas Derya, Emery Jon, Tew Michelle, Gibbs Peter, Millar Jeremy, White Victoria, Jefford Michael, Franchini Fanny, IJzerman Maarten
Erasmus School of Health Policy and Management, Erasmus University Rotterdam, Rotterdam, the Netherlands.
Industrial Engineering and Business Information Systems, University of Twente, Enschede, the Netherlands.
BMC Med Res Methodol. 2024 Dec 27;24(1):321. doi: 10.1186/s12874-024-02446-5.
The aim of this study is to develop a method we call "cost mining" to unravel cost variation and identify cost drivers by modelling integrated patient pathways from primary care to the palliative care setting. This approach fills an urgent need to quantify financial strains on healthcare systems, particularly for colorectal cancer, which is the most expensive cancer in Australia, and the second most expensive cancer globally.
We developed and published a customized algorithm that dynamically estimates and visualizes the mean, minimum, and total costs of care at the patient level, by aggregating activity-based healthcare system costs (e.g. DRGs) across integrated pathways. This extends traditional process mining approaches by making the resulting process maps actionable and informative and by displaying cost estimates. We demonstrate the method by constructing a unique dataset of colorectal cancer pathways in Victoria, Australia, using records of primary care, diagnosis, hospital admission and chemotherapy, medication, health system costs, and life events to create integrated colorectal cancer patient pathways from 2012 to 2020.
Cost mining with the algorithm enabled exploration of costly integrated pathways, i.e. drilling down in high-cost pathways to discover cost drivers, for 4246 cases covering approx. 4 million care activities. Per-patient CRC pathway costs ranged from $10,379 AUD to $41,643 AUD, and varied significantly per cancer stage such that e.g. chemotherapy costs in one cancer stage are different to the same chemotherapy regimen in a different stage. Admitted episodes were most costly, representing 93.34% or $56.6 M AUD of the total healthcare system costs covered in the sample.
Cost mining can supplement other health economic methods by providing contextual, sequence and timing-related information depicting how patients flow through complex care pathways. This approach can also facilitate health economic studies informing decision-makers on where to target care improvement or to evaluate the consequences of new treatments or care delivery interventions. Through this study we provide an approach for hospitals and policymakers to leverage their health data infrastructure and to enable real time patient level cost mining.
本研究的目的是开发一种我们称为“成本挖掘”的方法，通过对从初级保健到姑息治疗环境的综合患者路径进行建模，来揭示成本差异并确定成本驱动因素。这种方法满足了量化医疗保健系统财务压力的迫切需求，特别是对于结直肠癌而言，结直肠癌是澳大利亚最昂贵的癌症，也是全球第二昂贵的癌症。
我们开发并发布了一种定制算法，该算法通过汇总综合路径中基于活动的医疗保健系统成本（例如疾病诊断相关分组），动态估计并可视化患者层面的护理平均成本、最低成本和总成本。通过使生成的过程图具有可操作性和信息性，并显示成本估计，该算法扩展了传统的过程挖掘方法。我们使用初级保健、诊断、住院和化疗、用药、卫生系统成本以及生活事件记录，构建了澳大利亚维多利亚州独特的结直肠癌路径数据集，以创建2012年至2020年的综合结直肠癌患者路径，从而展示该方法。
使用该算法进行成本挖掘能够探索成本高昂的综合路径，即在高成本路径中深入挖掘以发现成本驱动因素，涉及4246个病例，涵盖约400万次护理活动。每位患者的结直肠癌路径成本从10379澳元到41643澳元不等，并且在不同癌症阶段差异显著，例如一个癌症阶段的化疗成本与不同阶段相同化疗方案的成本不同。住院病例成本最高，占样本中涵盖的总医疗保健系统成本的93.34%或5660万澳元。
成本挖掘可以通过提供描述患者如何在复杂护理路径中流动的背景、顺序和时间相关信息，来补充其他卫生经济方法。这种方法还可以促进卫生经济研究，为决策者提供有关在何处改进护理或评估新治疗或护理提供干预措施后果的信息。通过本研究，我们为医院和政策制定者提供了一种利用其健康数据基础设施并实现实时患者层面成本挖掘的方法。
