From Chaos to Clarity: Schema-Constrained AI for Auditable Biomedical Evidence Extraction from Full-Text PDFs
This addresses the challenge of scalable and auditable evidence extraction for biomedical synthesis, though it appears incremental as it builds on existing document AI approaches with specific constraints for reliability.
The researchers tackled the problem of extracting structured biomedical evidence from complex full-text PDFs by developing a schema-constrained AI system that restricts model inference with typed schemas and controlled vocabularies. The system processed all documents without manual intervention, maintained stable throughput, and improved extraction fidelity for critical variables like assay classification and outcome definitions through iterative schema refinement.
Biomedical evidence synthesis relies on accurate extraction of methodological, laboratory, and outcome variables from full-text research articles, yet these variables are embedded in complex scientific PDFs that make manual abstraction time-consuming and difficult to scale. Existing document AI systems remain limited by OCR errors, long-document fragmentation, constrained throughput, and insufficient auditability for high-stakes synthesis. We present a schema-constrained AI extraction system that transforms full-text biomedical PDFs into structured, analysis-ready records by explicitly restricting model inference through typed schemas, controlled vocabularies, and evidence-gated decisions. Documents are ingested using resume-aware hashing, partitioned into caption-aware page-level chunks, and processed asynchronously under explicit concurrency controls. Chunk-level outputs are deterministically merged into study-level records using conflict-aware consolidation, set-based aggregation, and sentence-level provenance to support traceability and post-hoc audit. Evaluated on a corpus of studies on direct oral anticoagulant level measurement, the pipeline processed all documents without manual intervention, maintained stable throughput under service constraints, and exhibited strong internal consistency across document chunks. Iterative schema refinement substantially improved extraction fidelity for synthesis-critical variables, including assay classification, outcome definitions, follow-up duration, and timing of measurement. These results demonstrate that schema-constrained, provenance-aware extraction enables scalable and auditable transformation of heterogeneous scientific PDFs into structured evidence, aligning modern document AI with the transparency and reliability requirements of biomedical evidence synthesis.