Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries
Computation and LanguageArtificial IntelligenceDigital LibrariesHuman-Computer Interaction
Summary
The authors created an AI tool to help gather and summarize research impact data for scholars, which usually takes staff about 15 hours per person to do by hand. Their AI quickly collected evidence and drafted impact summaries that staff could review and edit, reducing review time to about 14 minutes per scholar. Two reviewers agreed that over 80% of the AI's findings were useful, and the tool performed nearly as well as human searches. This approach helped capture impact information often missed by regular methods and made it possible to handle large groups of scholars more efficiently.
Authors
Mohammad Arvan, Amber E. Osterholt, Bailee Rue, Yuvaneswaren Ramakrishnan Sureshbabu, Krishna Riteshkumar Patel, Rebecca T. Feinstein, Bethany C. Bray, Niranjan S. Karnik
Abstract
Introduction. Clinical and Translational Science Award (CTSA) programs must document their scholars' research impact, but assembling each scholar's record by hand takes staff an estimated 15 hours and does not scale to a full cohort. An artificial intelligence (AI) agent could serve as a tool to gather scholar data across platforms and disciplines. Methods. We built a human-in-the-loop AI agent that assembles a dossier of sourced evidence for each scholar and drafts one-sentence Translational Science Benefits Model (TSBM) impact summaries for staff review. We evaluated it in the impact-reporting workflow of one CTSA hub across 10 career-development (KL2/K12) scholars. Two evaluation staff independently coded all 507 findings as accept, edit, or reject; the primary measure was the unanimous usable rate, defined as the share both accepted or edited. Results. Both reviewers accepted or edited 81.7% of the agent's findings. Reviewers each spent a median of 14 minutes per scholar, replacing an estimated 15 hours of manual assembly. Inter-rater agreement was moderate (Cohen's kappa 0.43 on the usable-versus-reject decision). A profile discovery study found the agent's recall close to human search. The agent's impact evidence spanned all four TSBM domains, and about a third of the reviewed findings fell in non-scholarly categories that routine processes tend to miss. Reviewers rated synthesis accuracy 4.5 and usefulness 4.8 on a 5-point scale. Conclusions. A human-in-the-loop AI agent can serve as the first-pass author of a scholar's impact record, shifting staff from collecting and writing to reviewing, and making cohort-scale impact reporting feasible.