Projects & Publications
A living portfolio of active research and pilots, plus the papers, posters, and talks that come out of our work.
01
Education
Designing and piloting a longitudinal AI-in-medicine curriculum across all PGY years of the USF/TGH Family Medicine Residency.
Evaluation
Evaluating ambient AI scribes in primary care: note quality, time savings, clinician satisfaction, and patient outcomes.
Your project?
If you've got a project at the intersection of clinical care and AI, this is the place to start, or to find collaborators for what you're already doing.
Submit a PICO →More projects will appear here as collaborators come on board.
02
Peer-reviewed papers, posters, conference talks, and invited presentations - newest first.
2026
May
Matzinger E, Salvatori C, Szalacha L, Hanna K. Understandability of AI-Generated Patient Handouts Explaining Cardiac Diagnoses. Completed Research Poster (RP26), 2026 STFM Annual Spring Conference. New Orleans, LA. May 2-6, 2026.
Special Recognition Award
2026
STFM
Hanna K, Petrilli J, et al. Building a Competency-Based Readiness Rubric for Ambient Scribe Use Among Family Medicine Interns. STFM National Conference. New Orleans, LA. 2026.
2026
Apr
Aziz R, Stewart S, Liscomb R, Baldwin B, Bailey K, Hanna K. Performance of Large Language Models on Diagnostic Radiology Board-Style Questions: A Comparative Evaluation of GPT-4o, Perplexity AI, and OpenEvidence. South Med J. 2026;119(4):191-194. doi:10.14423/SMJ.0000000000001950. PMID:41999647.
2026
Mar
Armosh M, Armosh KB, Haghighi MB, Hanna KM. The role of patient emotional tone in AI scribe documentation: a comparative analysis using standardized scripts. Poster, USF Health Research Day. March 6, 2026.
2026
Alemayehu K, Konyayev K, Hanna K. Examining the Effects of Varying Accents and Tones on the Accuracy of Transcription in Clinical Settings with Ambient Scribes. Bridge2AI Voice. St Petersburg, FL. 2026.
2025
Nov-Dec
Hanna K. Assembling Your AI Toolkit in Family Medicine. Fam Pract Manag. 2025;32(6):27-29.
2025
Nov
Bryant LH III, Shah P, Templeton J, Hanna K. Large-Language Models Diagnostic Accuracy of Tendon Tears Through Ultrasound Imaging. 16th Annual USF RISE Virtual Student Symposium. Tampa, FL. November 7, 2025.
2025
Aug
Shah P, Boughanem DJ, Templeton JM, Wiranowska M, Hanna K. Comparative Performance of Large Language Models in Muscle Histology Classification Highlights Enhanced Accuracy of ChatGPT-4o in Tissue Identification. Cureus. 2025;17(8):e90103. doi:10.7759/cureus.90103.
2025
Aug
Hanna K. Re: Performance Evaluation of the Generative Pre-Trained Transformer (GPT-4) on the Family Medicine In Training Examination [letter]. J Am Board Fam Med. 2025. doi:10.3122/jabfm.2024.240404R0.
2025
Jul
Shah P, Boughanem DJ, Templeton JM, Wiranowska M, Hanna K. AI-Powered Histology: Evaluating Large Language Model Performance in Muscle Tissue Classification. David A. Paulus, MD Poster Symposium, Florida Medical Society Annual Meeting. Orlando, FL. July 25-27, 2025.
2025
Fam Med
Thomas K, Szalacha L, Hanna K, Anibal J, Petrilli J. Evaluating the Effectiveness of ChatGPT Versus Human Proctors in Grading Medical Students' Post-OSCE Notes. Fam Med. 2025;57(10):727-731. doi:10.22454/FamMed.2025.954255.
2025
Jun
Treanor JT, Templeton JM, Hanna K. Artificial Intelligence in Health Maintenance Recommendations. AI for Healthcare, Exploration, and Advanced Translational Horizons Symposium. USF, Tampa, FL. June 3, 2025.
2025
Jun
Aziz R, Stewart S, Lipscomb R, Hanna K. Performance of Large Language Models on Diagnostic Radiology Board-Style Questions: A Comparative Evaluation of GPT-4o, Perplexity AI, and OpenEvidence. AI Health Symposium. USF, Tampa, FL. June 3, 2025.
2025
Jun
Hayslip N, Hanna K. Man vs. Machine: ChatGPT for Image-Based Cardiology Multiple-Choice Questions. AI for Healthcare, Exploration, and Advanced Translational Horizons Symposium. USF, Tampa, FL. June 2025.
2025
USF
Shah P, Boughanem DJ, Templeton J, Wiranowska M, Hanna K. AI-Powered Histology: Evaluating LLM Performance in Muscle Tissue Classification. Poster, USF Health Research Day. 2025.
2025
Feb
Thomas K, Hanna K, Petrilli J. Grading Medical Students' Post-OSCE Notes: ChatGPT vs. Human Proctors. Poster, USF Health Research Day. February 2025.
First Place · Best Poster in Clinical Research
2024
Oct 25
Tang R, Hanna K. Enhancing Potential Use of Large Language Models in Assisting Physicians with Preanesthetic Testing. USF AIX 2024 Symposium. Tampa, FL. October 25, 2024.
2024
Oct 25
Awad M, Daoud V, Petrilli J, Hanna K. Enhancing clerkship education: Assessing the impact of AI integration on 3rd-year medical students' test scores. Oral Presentation, USF Artificial Intelligence + X Symposium. October 25, 2024.
2024
Oct 20
Tang R, Hanna K. Enhancing Pre-operative Patient Education: Evaluating GPT Model Explanations of Inhaled Anesthetics. ASA 2024. Philadelphia, PA. October 20, 2024.
Citations follow AMA style. New entries are added by emailing Karim with the citation details (use the button above for a pre-filled template).
Whether you have an idea, a question, or a half-finished pilot - we'd rather build it together than separately.
Get involved →