Jamieson Lab

https://ut-real-ai-project-maples.com/ 

MAY-2026: SAIL 2026 — Puerto Rico

Tra Ngo will present "Deploying a Multimodal AI Platform for Automated OSCE Grading in Medical Education" at SAIL 2026, the Symposium on Artificial Intelligence for Learning Health Systems (May 5–8, Río Grande, Puerto Rico).

APR-2026: Innovation Hub Feature and DIMS Contribution

UT Southwestern Center Times Plus featured Andrew Jamieson and the lab's OSCE AI platform in "Innovation Hub helps researchers take discoveries into the real world." The article highlights the platform's commercialization path through the UTSW Innovation Hub, notes UT-REAL expansion to five additional UT System medical schools, and credits the Jamieson team with helping build DIMS, the Hub's Discovery Information Management System for project tracking, investor transparency, and AI-assisted funding search.

APR-2026: Featured in UTSW Scientific Report

Our OSCE grading work is featured in Discovery@UTSW 2026, highlighting how AI replaced 91% of human grading while reducing turnaround from weeks to days. Read the full article

APR-2026: UT-REAL Health AI Grant Awarded

We received a $300,000 UT System grant to scale our AI grading platform across six UT medical schools over 18 months. We will validate AI-human concordance at each site and develop shared governance frameworks for AI in medical education. https://ut-real-ai-project-maples.com/ 

APR-2026: Dallas Innovates AI 75

Andrew Jamieson named to the Dallas Innovates AI 75 for 2026.

APR-2026: PCT International Patent Filed

Our second patent (UTSD 4539) entered the international phase: PCT/US2026/022629, covering automated audio-visual assessment of clinical encounters.

APR-2026: AIMW 2026 Workshop — Seattle

Presenting "From Research to Rollout: Lessons from Deploying AI-Based OSCE Assessment in Production" at AIMW26, April 20.

FEB-2026: AI for GME Program Review — ACGME Annual Educational Conference

Michael Holcomb presented "Leveraging AI: Automating Annual Action Plan Scoring as a Use Case" at the 2026 ACGME Annual Educational Conference ("Meaning in Medicine," San Diego, Feb 20–22). The work — a partnership with UTSW GME leadership (Drs. Scielzo, Green, and Scott) — uses a virtual panel of example-conditioned LLM personas to generate consensus evaluations of 200+ UTSW residency and fellowship program action plans, lifting pass/fail agreement from 46% (zero-shot) to 91% (virtual panel). ACGME Learn course · Video (6 min) · Open-source code.

FEB-2026: Published in JMIR AI

Kang S, Holcomb MJ, Hein D, Shakur AH, Dalton TO, Jamieson AR. "Physical Examination Identification in Medical Education Videos: Zero-Shot Multimodal AI With Temporal Sequence Optimization." JMIR AI. 2025. DOI

JAN-2026: Multimodal Physical Exam Grading Preprint

Kang S, Holcomb MJ, Shakur AH, Hein D, Ngo HT, Schuler H, Jarrett PC, Dalton TO, Jamieson AR. "Automated Assessment of OSCE Physical Exams using Multimodal AI." medRxiv 2026. DOI. Under review.

NOV-2025: AAMC Learn Serve Lead — National Workshop

Michael J. Holcomb and Thomas O. Dalton presented "Beyond Single-Loop Feedback: A Self-Validating LLM System for Medical Student Documentation Assessment" at AAMC Learn Serve Lead 2025 (San Antonio, Nov 1–5).

NOV-2025: UTSW DOCS Symposium

Presented our multimodal OSCE grading work at the UTSW DOCS (Directors of Clinical Skills) Symposium on November 1, 2025.

OCT-2025: Directors of Clinical Skills National Workshop

Shinyoung Kang and Ameer Hamza Shakur presented "Multimodal AI-assisted Assessment: Harnessing OSCEs & LLMs to Promote Precision Education" at the Directors of Clinical Skills national workshop (San Antonio, Oct 1, 2025).

OCT-2025: ROI Paper in Discover Artificial Intelligence

Campbell KK, Holcomb MJ, Vedovato S, Young L, Danuser G, Dalton TO, Jamieson AR, Scott DJ. "Applying state-of-the-art artificial intelligence to grading in simulation-based education: assessment, feedback, and ROI." Discover Artificial Intelligence. 2025. Documents up to 797% ROI versus faculty grading and ~$48K in annual savings across 684 students over four academic years. DOI

SEP-2025: ChangeMedEd 2025 — Chicago

Ameer Hamza Shakur presented "Can AI assess OSCEs? A zero-shot multimodal approach to medical student evaluation" at ChangeMedEd 2025 (Chicago, Sep 11–13).

JUL-2025: UTSW Newsroom and national press syndication

UTSW Newsroom featured our clinical information extraction work in "UTSW builds AI-driven system to improve data collection" (July 28, 2025), syndicated to Newswise and MedicalXpress.

JUL-2025: Featured in STAT News

Our OSCE grading work was profiled by Brittany Trang in STAT News (July 16, 2025) — "An unusual use for AI in medical education" — in the AI Prognosis newsletter.

MAY-2025: Published in npj Digital Medicine

Hein D et al. "Iterative refinement and goal articulation to optimize LLMs for clinical information extraction." npj Digital Medicine 8, 301. 2025.

MAY-2025: Full OSCE Grading From Transcripts

Now grading entire OSCEs — communications and physical exams — from transcripts on a new set of pre-clerkship cases developed by Dr. Dalton.

APR-2025: Multimodal OSCE Preprint

Kang S et al. Automatic Physical Examination Segmentation within OSCE Videos. medRxiv 2025.

NOV-2024: Published in NEJM AI

Jamieson AR et al. Rubrics to Prompts: Assessing Medical Student Post-Encounter Notes with AI. NEJM AI. 2024.

OCT-2024: AI Innovations Challenge — MedBox

The Jamieson Lab's MedBox team — David Hein, Dhvani "Annie" Jain, and Ameer Hamza Shakur — won third place in UTSW's inaugural AI Innovations Challenge. MedBox proposed an institutionally tailored hardware-software platform for automated grading and feedback in medical education, developed in collaboration with the UTSW Simulation Center.

OCT-2024: Production OSCE Grading Complete

Completed another year of AI-powered OSCE note grading at the SimCenter.

OCT-2024: Transcript Analysis Preprint

Shakur AH et al. Large Language Models for Medical OSCE Assessment: A Novel Approach to Transcript Analysis. arXiv. 2024.

MAY-2024: SAIL 2024

Presented Rubrics to Prompts at SAIL 2024, sharing our AI grading pilot deployment at the Simulation Center.

SEPT-2023: Microsoft Azure Credit Grant

Awarded Azure credits from Microsoft's Accelerating Foundation Models Research program for GPT-4 experiments on rubric-based clinical assessment.