MSTR Alumni Spotlight
-
Daniel Hashimoto, MD, MSTR
Current position: Assistant Professor in Surgery and Engineering and Director of the Penn Computer Assisted Surgery and Outcomes Laboratory, University of Pennsylvania, Perelman School of Medicine
Daniel's thesis work was titled, “Striving for Acquisition of Expertise in Surgery: Lessons from High Performance Competitive Industries”. After completing surgical residency and a research fellowship in surgical AI & innovation, he was appointed Assistant Professor in Surgery and Engineering at Penn in 2022 and the director of the Penn Computer Assisted Surgery and Outcomes Laboratory, where he leads a multidisciplinary team of clinicians and computer scientists that aims to leverage computer vision to augment surgical decision-making in the operating room and to provide data-augmented guidance to surgeons during operations to improve patient outcomes and reduce the likelihood of intraoperative adverse events. Although early in his career, his research has impacted clinical care, by his development of multiple computer vision algorithms for the analysis of surgical video. He led international consensus on defining ground truth for the annotation of surgical video and worked to define metrics to assess performance of AI algorithms on surgical tasks. His work has been cited by both the Government Accountability Office and the National Academy of Medicine’s technology assessment on AI in Healthcare as an example of how policy must account for computer vision technologies that guide or influence patient care. He served on the Royal College of Physicians and Surgeons of Canada task force that recommended that digital health literacy be introduced as a new component of the CanMEDS Physician Competency Framework. He is co-founder of the Global Surgical AI Collaborative, a nonprofit that promotes the democratization of surgical care through the intersection of education, innovation, & technology.
Dan's Publication
Hashimoto DA, Rosman G, Witkowski ER, Stafford C, Navarette-Welton AJ, Rattner DW, Lillemoe KD, Rus DL, Meireles OR. Computer Vision Analysis of Intraoperative Video: Automated Recognition of Operative Steps in Laparoscopic Sleeve Gastrectomy. Ann Surg. 2019 Sep;270(3):414-421. doi: 10.1097/SLA.0000000000003460. PMID: 31274652; PMCID: PMC7216040.
This paper explores the use of AI algorithms to identify operative steps in laparoscopic sleeve gastrectomy (LSG). Computer vision, a form of artificial intelligence (AI), allows for quantitative analysis of video by computers for identification of objects and patterns, such as in autonomous driving. We found that AI can extract quantitative surgical data from video with 85.6% accuracy. This suggests operative video could be used as a quantitative data source for research in intraoperative clinical decision support, risk prediction, or outcomes studies.
-
Laura Adang, MD, PhD, MSTR
Current position: Assistant Professor of Child Neurology, University of Pennsylvania Perelman School of Medicine & Children's Hospital of Philadelphia
Laura works on clinical trial readiness for the leukodystrophies, which are neurodegenerative, genetic disorders of the brain. Our work includes biomarker validation, natural history studies, and development of new tools to measure change. She enrolled in the MSTR degree because she felt there was a gap in herability to take my basic science experiences and translate that into a rigorous scientific program focused on clinical trial readiness. Laura shared that the degree has had a "profound impact" on her career, specifically equipping her with a strong foundation in research methodologies and critical thinking, and enabling her to bridge the gap between basic science and clinical application.
Her advice for new students is to "stay engaged and focused! It is too easy to be pulled in many directions, especially as a physician-scientist. Think about what you want to gain from the program and make sure you use all of the amazing resources to reach your goals. Also, take the K writing course!"
Laura is now a course director of an ITMAT Ed program focused on the education and mentorship of research coordinators within our rare disease research consortium. This program, the Predoctoral Preparatory Program or P3, was recently R25 funded through NCATS.
Laura's Publication
Gavazzi F, Vaia Y, Woidill S, Formanowski B, Peixoto de Barcelos I, Sevagamoorthy A, Modesti NB, Charlton L, Cusack SV, Vincent A, D'Aiello R, Jawad A, Galli J, Varesio C, Fazzi E, Orcesi S, Glanzman AM, Lorch S, DeMauro SB, Guez-Barber D, Waldman AT, Vanderver A, Adang LA. Nonverbal Cognitive Skills in Children With Aicardi Goutières Syndrome. Neurology. 2024 Jul 9;103(1):e209541. doi: 10.1212/WNL.0000000000209541. Epub 2024 Jun 10. PMID: 38857477; PMCID: PMC11226315.
This paper underscores the challenges of measuring cognitive skills in populations where children also have difficulty with motor skills. We found that with the right test, many children with a rare genetic disorder (Aicardi Goutières Syndrome) have non-verbal IQs within the normal range. This has important implications on how we can best serve and support our patients at home and school.