A Non-Destructive Methodological Framework for Modernizing Legacy Clinical Reporting Systems for AI-Driven Pharmacoinformatics: A SAS Case Study

📅 2026-05-12
📈 Citations: 0
Influential: 0
📄 PDF

career value

153K/year
🤖 AI Summary
Legacy clinical reporting systems hinder AI integration and impede drug development and pharmacovigilance due to opaque outputs and the absence of machine-readable intermediate representations. This work proposes a non-intrusive, metadata-driven framework that bridges legacy components—without modifying their source code—through mapping layers, a typed intermediate representation (IR), and coordinator wrappers, thereby transforming their outputs into structured data suitable for large language models (LLMs) and enabling progressive replacement. Validated on 558 SAS components (373k lines of code), the approach achieves immediate AI readiness in coexistence mode, reduces proprietary code by 92% after optional integration, and demonstrates unit-level consistency exceeding 80% across 11 of 14 report types (mean: 82.7%, peak: 99.2%). Five reports achieved 100% compliance on the CDISCPilot01 benchmark, and the framework successfully enabled LLM-driven automated pharmacovigilance, table summarization, and trial configuration generation.
📝 Abstract
Drug development and pharmacovigilance are frequently bottlenecked by legacy clinical reporting pipelines. These monolithic systems encode regulatory-grade logic but resist AI integration by producing opaque output with no machine-readable intermediate layer. Existing modernization approaches force a choice between full rewrites and incremental refactoring that preserves structural barriers. We present a non-destructive methodological framework achieving AI-driven pharmacoinformatics readiness without altering legacy source code. A metadata layer--comprising a bridge map, a typed Intermediate Representation (IR), and an orchestrator--wraps existing components and re-exposes their outputs as structured data consumable by LLMs. It enables optional incremental consolidation, replacing selected legacy components with metadata-configured core routines while the remainder operates unchanged. Validated on a 558-component SAS reporting library (373,000 lines of code), the framework demonstrated immediate AI-readiness under coexistence mode, yielding machine-readable output. Where consolidation was elected, the modernized core achieved a 92% reduction in proprietary code. Parity validation on 14 report types from a Phase III study achieved cell-level parity of 80% or above on 11 reports (mean 82.7%, best 99.2%). A benchmark using CDISC CDISCPilot01 data achieved 100% parity across 5 reports. LLM experiments confirmed the IR enables automated pharmacovigilance, table summarization, and trial configuration generation. The framework offers a regulation-aware path to AI-integrated clinical reporting, accelerating drug development without interrupting regulatory submissions.
Problem

Research questions and friction points this paper is trying to address.

legacy clinical reporting systems
AI integration
pharmacoinformatics
non-destructive modernization
machine-readable output
Innovation

Methods, ideas, or system contributions that make the work stand out.

non-destructive modernization
Intermediate Representation (IR)
AI-readiness
legacy clinical reporting
pharmacoinformatics
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
AI Data Engineer--LLMs / Agentic Systems
Pfizer
The annual base salary for this position ranges from $106,000.00 to $176,600.00. In addition, this position is eligible for participation in Pfizer’s Global Performance Plan with a bonus target of 15.0% of the base salary and eligibility to participate in our share based long term incentive program. We offer comprehensive and generous benefits and programs to help our colleagues lead healthy lives and to support each of life’s moments. Benefits offered include a 401(k) plan with Pfizer Matching Contributions and an additional Pfizer Retirement Savings Contribution, paid vacation, holiday and personal days, paid caregiver/parental and medical leave, and health benefits to include medical, prescription drug, dental and vision coverage. Learn more at Pfizer Candidate Site – U.S. Benefits | (uscandidates.mypfizerbenefits.com). Pfizer compensation structures and benefit packages are aligned based on the location of hire. The United States salary range provided does not apply to Tampa, FL or any location outside of the United States. Relocation assistance may be available based on business needs and/or eligibility.
United States - Massachusetts - Cambridge
J
Jaime Yan
Harrisburg University of Science and Technology, Harrisburg, PA, USA