醫療服務品質長期以供給端的結構性指標與機構自評為主要評估依據，較少系統性納入醫療服務接受者於日常數位環境中自發表達的品質感知。借鏡行銷研究領域中消費者情緒指數（consumer sentiment index）與輿情分析（public opinion analysis）的方法，本研究將其延伸至醫療服務情境，以建立病患品質感知之理論化衡量架構，彌補現行醫療品質評估偏重供給端之不足。本研究以 Donabedian 結構－過程－結果（Structure–Process–Outcome， SPO）模型結合 Kano 二維品質模型，建立可同時辨識品質屬性與滿意度非對稱效應之雙維評分構面（Rubric）。並運用大型語言模型（Large Language Model， LLM）代理人，透過結構化提示工程與固定評分規準，將網路評論轉換為標準化之滿意指數（Satisfaction Index， SI）與不滿意指數（Dissatisfaction Index， DI），提供醫療品質改善依據。為驗證本研究架構之可操作性與適用性，本研究以四家分屬不同層級與屬性（醫學中心、區域醫院、公立、私立）之醫院作為示範性案例，檢視其於不同醫療情境下之應用表現。研究發現，不同醫院於 SPO 三個構面呈現差異化的 Kano 品質屬性分布，可作為醫療品質改善與資源配置之參考。本研究提出一套兼具理論基礎、方法透明與病患觀點的醫療品質感知衡量架構，可補充現行以機構治理與醫院評鑑為主之品質管理模式，並填補醫療服務接受者品質感知缺乏系統性衡量工具的研究缺口。;Healthcare service quality has traditionally been evaluated using provider-oriented structural indicators and institutional self-assessments， with limited consideration of patients′ spontaneously expressed quality perceptions in digital environments. Drawing on the methodological traditions of consumer sentiment index and public opinion analysis， this study extends these approaches to the healthcare context to establish a theory-driven framework for measuring patient-perceived healthcare quality， thereby addressing the limitations of conventional provider-centered quality assessment. This study integrates Donabedian′s Structure–Process–Outcome (SPO) model with the Kano two-dimensional quality model to develop a dual-dimensional assessment rubric capable of simultaneously identifying the location of quality issues within the healthcare system and the asymmetric effects of quality attributes on patient satisfaction. Furthermore， Large Language Model (LLM) agents， supported by structured prompt engineering and standardized scoring criteria， are employed to transform online patient reviews into standardized Satisfaction Index (SI) and Dissatisfaction Index (DI) scores， providing evidence for healthcare quality improvement. To demonstrate the operability and applicability of the proposed framework， this study uses four illustrative hospitals representing different organizational levels and ownership types (medical centers and regional hospitals; public and private institutions). The findings indicate that hospitals exhibit distinct distributions of Kano quality attributes across the three SPO dimensions， providing a theoretical basis for prioritizing healthcare quality improvement and resource allocation. This study proposes a patient-centered healthcare quality perception measurement framework that is theoretically grounded， methodologically transparent， and practically applicable. The proposed framework complements existing quality management approaches that primarily emphasize institutional governance and hospital accreditation， while addressing the lack of a systematic theoretical instrument for measuring healthcare quality from the perspective of healthcare recipients.
