Longitudinal Profile and Traceability in Retrieval-Augmented Clinical Decision Support for Sensory Accommodation: a Design Science Study
Abstract
Research Context. Sensory accommodation is a widely adopted therapeutic resource in Autism Spectrum Disorder (ASD) care, and its effectiveness depends on clinical documentation that accumulates across weeks and months rather than on isolated sessions.Scientific and/or Practical Problem. Clinical information systems record sessions episodically, forcing professionals to mentally retain the accumulated sensory trajectory; it is not established whether a decision support system that combines retrieval-augmented generation, a deterministic longitudinal profile and dynamic prompt construction is perceived as acceptable by the specialists who would mediate its use.Proposed Solution and/or Analysis. We propose and evaluate a three-layer clinical decision support architecture - local language models, a curated retrieval layer carrying a deterministic longitudinal profile, and an integration layer for institutional systems - in which every recommendation is traceable both to retrieved evidence and to the longitudinal state that produced it.Related IS Theory. Task-Technology Fit explains why longitudinality is a fit requirement rather than a refinement; the Technology Acceptance Model and UTAUT ground the five acceptability dimensions measured.Research Method. Design Science Research with a two-axis protocol: an automatic baseline of an antecedent template-based system against an expert-curated Gold Standard (ROUGE-L, Clinical Vocabulary Rate and Traceable Recommendation Rate), and…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.