An AI-Driven Live Systematic Reviews in the Brain-Heart Interconnectome: Minimizing Research Waste and Advancing Evidence Synthesis
This addresses research waste and synthesis challenges for biomedical researchers in neurology and cardiology, though it is incremental as it adapts existing AI methods to a specific domain.
The authors tackled inefficiencies in evidence synthesis for the Brain-Heart Interconnectome by developing an AI-driven system that integrates automated PICOS detection, semantic search, and graph-based querying, achieving up to 95.7% accuracy in study design classification and reducing research waste through real-time updates.
The Brain-Heart Interconnectome (BHI) combines neurology and cardiology but is hindered by inefficiencies in evidence synthesis, poor adherence to quality standards, and research waste. To address these challenges, we developed an AI-driven system to enhance systematic reviews in the BHI domain. The system integrates automated detection of Population, Intervention, Comparator, Outcome, and Study design (PICOS), semantic search using vector embeddings, graph-based querying, and topic modeling to identify redundancies and underexplored areas. Core components include a Bi-LSTM model achieving 87% accuracy for PICOS compliance, a study design classifier with 95.7% accuracy, and Retrieval-Augmented Generation (RAG) with GPT-3.5, which outperformed GPT-4 for graph-based and topic-driven queries. The system provides real-time updates, reducing research waste through a living database and offering an interactive interface with dashboards and conversational AI. While initially developed for BHI, the system's adaptable architecture enables its application across various biomedical fields, supporting rigorous evidence synthesis, efficient resource allocation, and informed clinical decision-making.