Patient Recruitment

Patient medical records and trial criteria are analyzed by AI to rapidly identify and match eligible clinical trial participants.

Business impact

• Patient recruitment speed — AI reduces manual screening time by rapidly identifying eligible patients from large datasets
• Trial enrollment rate — Improved matching accuracy increases the number of patients enrolled per trial period
• Operational costs — Automation lowers costs by minimizing manual effort and reducing recruitment delays

Data requirements

• Electronic Health Records (EHRs) (Structured) — Provide structured and unstructured patient medical data for eligibility assessment
• Clinical trial protocols and criteria (Text) — Define inclusion/exclusion rules used by AI to match patients accurately
• Genomic and biomarker data (Numeric) — Enable precision matching based on genetic profiles and molecular markers
• Patient-reported data and language (Text) — Capture patient descriptions to improve natural language matching and eligibility inference

AI methods and techniques

• Predictive AI — Forecast patient eligibility and likelihood of trial adherence to optimize recruitment
• Generative AI — Interpret complex eligibility criteria and patient language for improved matching
• Agentic AI — Automate workflows and support clinical trial tasks including patient engagement
• Symbolic AI — Apply rule-based reasoning to enforce clinical trial inclusion/exclusion logic

AI models and model families

GPT-4o, Llama, Claude, NVIDIA NeMo, Custom Foundation Models

Industries

Real-world evidence

3 documented case studies on record.

Companies using this: AbbVie, Fortrea, IQVIA.