Scholarlink

<p>Healthcare systems globally aim to improve population health and ensure equitable care. The COVID-19 pandemic severely strained these systems, while also highlighting the inherent uncertainty in performance data arising from variable socio-cultural factors, mortality rates, and expert estimations. This study addresses the critical challenge of data uncertainty in efficiency evaluation by proposing a novel, non-radial Directional Distance Function (DDF) model that integrates uncertain data and undesirable outputs—a first in the literature for a model-based, non-oriented DDF framework. This model is grounded in uncertainty theory, which offers a mathematically consistent framework for handling belief degrees, distinguishing it from fuzzy-based approaches. The model is converted into a solvable linear programming form using uncertainty theory. We further introduce a new uncertain directional mix-efficiency measure, derived from the integration of the uncertain DDF and Slacks-Based Measure (SBM), to diagnose specific sources of inefficiency. A comprehensive sensitivity analysis defines a stability radius, proving the robustness of efficiency classifications against data variations. The applicability of the proposed methodology is demonstrated through a real-data case study evaluating the efficiency of 30 high- and upper-middle-income countries during the COVID-19 pandemic. The framework provides managers and policymakers with a robust, uncertainty-aware tool for performance assessment and targeted improvement in healthcare and other complex sectors.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel uncertainty-incorporated directional distance function approach for healthcare performance assessment during pandemics

  • 期刊论文

  • 发表日期：

    2026年5月25日

查看全文
  • Shabnam Razavyan,
  • Ghasem Tohidi,
  • Ali Ebrahimnejad

摘要

Healthcare systems globally aim to improve population health and ensure equitable care. The COVID-19 pandemic severely strained these systems, while also highlighting the inherent uncertainty in performance data arising from variable socio-cultural factors, mortality rates, and expert estimations. This study addresses the critical challenge of data uncertainty in efficiency evaluation by proposing a novel, non-radial Directional Distance Function (DDF) model that integrates uncertain data and undesirable outputs—a first in the literature for a model-based, non-oriented DDF framework. This model is grounded in uncertainty theory, which offers a mathematically consistent framework for handling belief degrees, distinguishing it from fuzzy-based approaches. The model is converted into a solvable linear programming form using uncertainty theory. We further introduce a new uncertain directional mix-efficiency measure, derived from the integration of the uncertain DDF and Slacks-Based Measure (SBM), to diagnose specific sources of inefficiency. A comprehensive sensitivity analysis defines a stability radius, proving the robustness of efficiency classifications against data variations. The applicability of the proposed methodology is demonstrated through a real-data case study evaluating the efficiency of 30 high- and upper-middle-income countries during the COVID-19 pandemic. The framework provides managers and policymakers with a robust, uncertainty-aware tool for performance assessment and targeted improvement in healthcare and other complex sectors.