ReviewAid

ReviewAid automates and accelerates full-text screening and structured data extraction in systematic reviews by using large language models to classify articles according to user-defined PICO criteria and extract structured information from full-text publications.

Key Features:

• Multi-provider AI architecture: Supports multiple large language model providers including OpenAI, Anthropic, DeepSeek, Cohere, Z.ai, and local execution via Ollama.
• PICO-based screening: Classifies articles according to Population, Intervention, Comparison, and Outcome criteria defined by the user.
• Customizable data extraction: Extracts structured information from full-text publications based on user-specified parameters.
• Bulletproof Parsing Pipeline: Recovers data from malformed or imperfect AI outputs with broken formatting.
• Hierarchical confidence scoring: Employs a four-tier system to quantify the certainty of AI classification and extraction decisions.

Scientific Applications:

• Systematic review automation: Accelerates evidence synthesis workflows by reducing manual screening workload while maintaining human oversight as a decision-support layer.
• Healthcare literature screening: Applies structured PICO-based methods to identify relevant studies from large bibliographic datasets.

Methodology:

Built on Python and Streamlit; processes full-text publications through large language model API calls with a Bulletproof Parsing Pipeline to handle malformed outputs, validated on over 100 articles.