Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching

2026-04-10

AI Summary

Existing clinical trial matching methods often suffer from low recall, insufficient precision, and poor interpretability under complex eligibility constraints. This work proposes SatIR, a scalable constraint-based retrieval framework that uniquely integrates SMT solvers with large language models to translate unstructured inclusion and exclusion criteria into explicit, verifiable formal constraints. By leveraging relational algebra and medical ontologies for efficient reasoning, SatIR enables accurate and interpretable patient-trial matching. Evaluated on a real-world dataset of 59 patients and 3,621 trials, SatIR improves recall of relevant eligible trials by 32%–72% over TrialGPT and increases overall useful trial recall by 22–38 percentage points, achieving each match in just 2.95 seconds.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Preferences

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Clinical trials are central to evidence-based medicine, yet many struggle to meet enrollment targets, despite the availability of over half a million trials listed on ClinicalTrials.gov, which attracts approximately two million users monthly. Existing retrieval techniques, largely based on keyword and embedding-similarity matching between patient profiles and eligibility criteria, often struggle with low recall, low precision, and limited interpretability due to complex constraints. We propose SatIR, a scalable clinical trial retrieval method based on constraint satisfaction, enabling high-precision and interpretable matching of patients to relevant trials. Our approach uses formal methods -- Satisfiability Modulo Theories (SMT) and relational algebra -- to efficiently represent and match key constraints from clinical trials and patient records. Beyond leveraging established medical ontologies and conceptual models, we use Large Language Models (LLMs) to convert informal reasoning regarding ambiguity, implicit clinical assumptions, and incomplete patient records into explicit, precise, controllable, and interpretable formal constraints. Evaluated on 59 patients and 3,621 trials, SatIR outperforms TrialGPT on all three evaluated retrieval objectives. It retrieves 32%-72% more relevant-and-eligible trials per patient, improves recall over the union of useful trials by 22-38 points, and serves more patients with at least one useful trial. Retrieval is fast, requiring 2.95 seconds per patient over 3,621 trials. These results show that SatIR is scalable, effective, and interpretable.

Problem

• clinical trials matching
• information retrieval
• constraint satisfaction
• low recall
• interpretability

Innovation

• Constraint Satisfaction
• Satisfiability Modulo Theories
• Clinical Trial Matching
• Large Language Models
• Interpretable Retrieval