AI Co-Scientist for Knowledge Synthesis in Medical Contexts: A Proof of Concept

TL;DR

This paper introduces an AI co-scientist platform that enhances knowledge synthesis in biomedical research by automating study classification, compliance detection, and thematic analysis, thereby improving scalability, transparency, and reducing research waste.

Contribution

It presents a novel, domain-agnostic AI framework integrating semantic retrieval, knowledge graphs, and NLP models for automated evidence synthesis in biomedical contexts.

Findings

Transformer classifier achieved 95.7% accuracy in study design classification.

Bi-LSTM achieved 87% accuracy in PICOS compliance detection.

Retrieval-augmented generation outperformed non-retrieval methods for structured queries.

Abstract

Research waste in biomedical science is driven by redundant studies, incomplete reporting, and the limited scalability of traditional evidence synthesis workflows. We present an AI co-scientist for scalable and transparent knowledge synthesis based on explicit formalization of Population, Intervention, Comparator, Outcome, and Study design (PICOS). The platform integrates relational storage, vector-based semantic retrieval, and a Neo4j knowledge graph. Evaluation was conducted on dementia-sport and non-communicable disease corpora. Automated PICOS compliance and study design classification from titles and abstracts were performed using a Bidirectional Long Short-Term Memory baseline and a transformer-based multi-task classifier fine-tuned from PubMedBERT. Full-text synthesis employed retrieval-augmented generation with hybrid vector and graph retrieval, while BERTopic was used to identify thematic structure, redundancy, and evidence gaps. The transformer model achieved 95.7% accuracy for study design classification with strong agreement against expert annotations, while the Bi-LSTM achieved 87% accuracy for PICOS compliance detection. Retrieval-augmented generation outperformed non-retrieval generation for queries requiring structured constraints, cross-study integration, and graph-based reasoning, whereas non-retrieval approaches remained competitive for high-level summaries. Topic modeling revealed substantial thematic redundancy and identified underexplored research areas. These results demonstrate that PICOS-aware and explainable natural language processing can improve the scalability, transparency, and efficiency of evidence synthesis. The proposed architecture is domain-agnostic and offers a practical framework for reducing research waste across biomedical disciplines.