Goswami Mohit, Daultani Yash, Paul Sanjoy Kumar, Pratap Saurabh
Operations Management Group, Indian Institute of Management Raipur, Abhanpur, India.
Operations Management Group, Indian Institute of Management Lucknow, Lucknow, India.
Ann Oper Res. 2022 Aug 23:1-40. doi: 10.1007/s10479-022-04914-x.
The current research aims to aid policymakers and healthcare service providers in estimating expected long-term costs of medical treatment, particularly for chronic conditions characterized by disease transition. The study comprised two phases (qualitative and quantitative), in which we developed linear optimization-based mathematical frameworks to ascertain the expected long-term treatment cost per patient considering the integration of various related dimensions such as the progression of the medical condition, the accuracy of medical treatment, treatment decisions at respective severity levels of the medical condition, and randomized/deterministic policies. At the qualitative research stage, we conducted the data collection and validation of various cogent hypotheses acting as inputs to the prescriptive modeling stage. We relied on data collected from 115 different cardio-vascular clinicians to understand the nuances of disease transition and related medical dimensions. The framework developed was implemented in the context of a multi-specialty hospital chain headquartered in the capital city of a state in Eastern India, the results of which have led to some interesting insights. For instance, at the prescriptive modeling stage, though one of our contributions related to the development of a novel medical decision-making framework, we illustrated that the randomized versus deterministic policy seemed more cost-competitive. We also identified that the expected treatment cost was most sensitive to variations in steady-state probability at the "major" as opposed to the "severe" stage of a medical condition, even though the steady-state probability of the "severe" state was less than that of the "major" state.
当前的研究旨在帮助政策制定者和医疗服务提供者估算医疗治疗的预期长期成本，特别是针对以疾病转变为特征的慢性病。该研究包括两个阶段（定性和定量），我们在其中开发了基于线性优化的数学框架，以确定考虑各种相关维度整合的每位患者的预期长期治疗成本，这些维度包括病情进展、医疗治疗的准确性、在病情各个严重程度水平上的治疗决策以及随机/确定性政策。在定性研究阶段，我们进行了数据收集和对各种有说服力的假设的验证，这些假设作为规范性建模阶段的输入。我们依靠从115位不同的心血管临床医生那里收集的数据来了解疾病转变和相关医疗维度的细微差别。所开发的框架是在一家总部位于印度东部某邦首府的多专科医院连锁机构的背景下实施的，其结果带来了一些有趣的见解。例如，在规范性建模阶段，尽管我们的一项贡献涉及开发一种新颖的医疗决策框架，但我们表明随机政策与确定性政策相比似乎更具成本竞争力。我们还发现，预期治疗成本对病情“主要”阶段而非“严重”阶段的稳态概率变化最为敏感，尽管“严重”状态的稳态概率低于“主要”状态。
