Clinical Focus

  • Surgical Critical Care

Academic Appointments

Professional Education

  • Board Certification: American Board of Surgery, Surgical Critical Care (2025)
  • Board Certification: American Board of Surgery, General Surgery (2024)
  • Fellowship: Brigham and Women's Hospital Dept of Surgery (2024) MA
  • Residency: Kaiser Permanente Los Angeles General Surgery Residency (2023) CA
  • Doctor of Medicine (MD), Oregon Health and Science University, Medicine (2018)

Contact

  • Clinical (Primary)  Stanford Hospital Critical Care Surgery 300 Pasteur Dr Rm H3634 Stanford, CA 94305 (650) 724-2187 (fax)

Additional Clinical Info

Additional Info

  • Other ID(s):
    S0381088
    MalPratt

2025-26 Courses

Stanford Advisees

  • Med Scholar Project Advisor
    Brianna Brasko

All Publications

  • Comparative Evaluation of Large Language Models for Surgical Case Creation. Journal of surgical education Gan, C. Y., Chan, M., Sharma, N., Wang, S., Flynn, L., Melcer, E., Liebert, C., Lin, D. T., Parker, A., Pratt, M. 2026; 83 (9): 104034

    Abstract

    To evaluate and compare the performance of five large language models (LLMs)-ChatGPT-4o (OpenAI), Claude-3.5-sonnet (Anthropic), Gemini-2.0-flash-001 (Google), Llama-3.2 (Meta), and DeepSeek-r1 (DeepSeek) in generating trauma surgery case scenarios for ENTRUST, a virtual simulation platform designed to teach and assess clinical decision-making in surgical trainees.Comparative, experimental analysis using a standardized prompt applied to each LLM alongside surgical reference materials: American Board of Surgery General Surgery trauma entrustable professional activity (EPA) definitions, trauma surgery references, ENTRUST platform description and case template. Outputs were blinded and independently evaluated by content experts. Expert perceptions, quality metrics adapted from HumanELY (relevance, coverage, coherence, and lack of harm), usability, and Flesch-Kincaid Grade Level readability were evaluated.Multi-institutional study.Four board-certified trauma surgeons from multiple U.S. institutions served as content experts.Claude-3.5-sonnet outperformed other LLMs across most metrics, with a significant mean total modified HumanELY score of 52.5/70 (p = 0.04). Gemini-2.0-flash-001 (46.7/70), ChatGPT-4o (45.8/70), and DeepSeek-r1 (45.8/70) performed similarly, while Llama-3.2 scored lowest (39.8/70). Readability analysis showed Flesch-Kincaid Grade Levels ranging from 9.9 to 12.1. Claude required the least editing (22.5%) to make outputs useful, while Llama required the most (66.3%).LLM performance in surgical case generation varies substantially across models. Claude-3.5-sonnet demonstrated superior performance in generating high-quality trauma surgery cases, suggesting that careful selection and optimization of LLMs is crucial for their effective implementation into surgical education. In addition, this study introduces a modified HumanELY framework as a structured, human-based tool that educators can use to evaluate the quality of AI-generated surgical education content.

    View details for DOI 10.1016/j.jsurg.2026.104034

    View details for PubMedID 42364537

  • Resilience Amidst Instability: A Critical First Step in Improving Patient Safety Culture in Conflict-Affected Zones. World journal of surgery Pratt, M. S., Weiser, T. G. 2025

    View details for DOI 10.1002/wjs.12561

    View details for PubMedID 40193206

  • Critical Care of the Abdominal Surgery Patient. The Pharmacist's Expanded Role in Critical Care Medicine. Pratt, M., Lee, G., Panuccio, A., Chowdhury, A., Madenci, K. 2025

    View details for DOI 10.1007/978-3-031-77335-8_25

  • Examining nonmilitary and nongovernmental humanitarian surgical capacity and response in armed conflicts: A scoping review of the recent literature. Surgery Bryce-Alberti, M., Bosché, M., Benavente, R., Chowdhury, A., Steel, L. B., Winslow, K., Bain, P. A., Le, T., Hamzah, R., Ilkhani, S., Pratt, M., Carroll, M., Nunes Campos, L., Anderson, G. A. 2024; 176 (3): 748-756

    Abstract

    Armed conflicts pose a burden on health care services. We sought to assess the surgical capacity and responses of nonmilitary and nongovernmental humanitarian responders in armed conflicts through proxy indicators to identify strategies to address surgical needs.We searched 6 databases for articles/studies from January 1, 2013, to March 10, 2023. We included articles detailing the surgical capacity of nonmilitary, nongovernmental organizations operating in armed conflicts. We defined surgical capacity through indicators including the type and number of surgical procedures; number of operating rooms, surgical beds, surgeons, anesthesiologists, and surgical equipment; and type of anesthesia employed.We screened 2,187 abstracts and 279 full texts and included 30 articles/studies. Our sample covered 23 countries and 17 surgical specialties. Most publications focused on surgical capacity assessment (63.3%, 19/30) and surgical and clinical outcomes (63.3%, 19/30). Most articles/studies reported surgical capacity indicators at the hospital (56.7%, 17/30) and multinational (26.7%, 8/30) levels. The number (86.7%, 26/30) and type (76.7%, 23/30) of surgical procedures performed were the most commonly reported. More than one half of the articles (53.3%, 16/30) described strategies to meet surgical needs in armed conflicts. Most strategies addressed information management (68.8%, 11/16), health workforce (62.5%, 10/16), and service delivery (62.5%, 10/16).This review collated common approaches for strengthening health care services in armed conflicts. Several articles emphasized strategies for improving information management, service delivery, and workforce capacity. Hence, we call for standardization of response protocols and multilevel collaborations to maintain or even scale up surgical capacity in armed conflicts.

    View details for DOI 10.1016/j.surg.2024.05.033

    View details for PubMedID 38955644