PRISMA: Toward a Normative Information Infrastructure for Responsible Pharmaceutical Knowledge Management

Abstract

Most existing approaches to AI in pharmacy collapse three epistemologically distinct operations into a single technical layer: document preservation, semantic interpretation, and contextual presentation. This conflation is a root cause of recurring fragilities including loss of provenance, interpretive opacity, alert fatigue, and erosion of accountability. This paper proposes the PATOS--Lector--PRISMA (PLP) infrastructure as a normative information architecture for responsible pharmaceutical knowledge management. PATOS preserves regulatory documents with explicit versioning and provenance; Lector implements machine-assisted reading with human curation, producing typed assertions anchored to primary sources; PRISMA delivers contextual presentation through the RPDA framework (Regulatory, Prescription, Dispensing, Administration), refracting the same informational core into distinct professional views. The architecture introduces the Evidence Pack as a formal unit of accountable assertion (versioned, traceable, epistemically bounded, and curatorially validated), with assertions typified by illocutionary force. A worked example traces dipyrone monohydrate across all three layers using real system data. Developed and validated in Brazil's regulatory context, the architecture is grounded in an operational implementation comprising over 16,000 official documents and 38 curated Evidence Packs spanning five reference medications. The proposal is demonstrated as complementary to operational decision support systems, providing infrastructural conditions that current systems lack: documentary anchoring, interpretive transparency, and institutional accountability.

Figures (3)

• Figure 1: Context graph structure illustrating the four validity dimensions for pharmaceutical assertions. Each assertion is valid only under explicitly defined conditions of authority (normative source), scope (clinical domain), population (target group), and clinical context. The example shows the assertion "Dipyrone is indicated for pain and fever" with its specific validity conditions. Qualifier nodes (Evidence Pack, Assertion Type, Epistemic Limits, Curatorial Decision) mediate between the assertion and its contextual dimensions.
• Figure 2: Architectural overview of the PATOS--Lector--PRISMA infrastructure. The bottom layer (PATOS) preserves regulatory and institutional documents with immutability, versioning, and cryptographic checksums. The middle layer (Lector) implements machine-assisted reading, producing Evidence Packs validated by human curators. The top layer (PRISMA) refracts the informational core through the RPDA framework into four contextual views (Regulatory, Prescription, Dispensing, Administration). Solid arrows indicate unidirectional information flow; dashed arrows indicate bidirectional traceability from any assertion back to its source document.
• Figure 3: Comparative analysis of conventional approaches versus the PATOS--Lector--PRISMA architecture across seven key dimensions: document preservation, interpretation, presentation, provenance, error risk, knowledge model, and accountability. The distinction is not additive (more features) but infrastructural: PLP provides foundational conditions that operational systems can exploit without implementing internally.