Surgical Artificial Intelligence and Innovation Laboratory
News
New Postdoctoral Fellowship Opportunity in Surgical AI at Duke Health System
Join the Surgical Artificial Intelligence and Innovation Laboratory (SAIIL) at Duke Department of Surgery in a groundbreaking project revolutionizing surgery through collaborative AI and surgical video understanding. We seek an enthusiastic postdoctoral candidate with a strong background in machine learning, computer vision, deep learning frameworks, and relevant publications.
This two-year project, with the possibility of extension, offers both computational and clinical aspects, focusing on innovative modeling, ML, and computer vision techniques to transform surgical understanding and assistance. With research and commercialization opportunities, candidates will work with unique datasets, aiming to significantly improve surgical care delivery and quality in various settings.
Surgical Artificial Intelligence and Innovation Laboratory (SAIIL)
The Surgical Artificial Intelligence and Innovation Laboratory (SAIIL) is a multidisciplinary team of surgeons, engineers, and data scientists committed to transforming surgical care delivery. Our team includes surgeons from Duke University, Massachusetts General Hospital, and the University of Cologne, alongside data scientists from Duke University and the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL). Together, we have developed innovative tools to enhance the intraoperative phase of care.
Our primary focus is on using computer vision and artificial intelligence (AI) to conduct real-time, automated analysis of surgical procedures. This technology enables us to automatically analyze and interpret surgical videos as they occur, helping AI learn to assess what is happening during an operation, identify high risks for postoperative complications, and provide surgeons with critical data to make better decisions in the operating room.
While advancements have been made in the surgical research field to analyze preoperative and postoperative risks using claims data and patient registries, studying the intraoperative phase remains challenging.
Research indicates that major intraoperative adverse events, such as accidental damage to the bowel or major blood vessels, occur in approximately 2% of all surgeries. With about 22 million general surgery operations conducted annually in the United States, around 440,000 patients may experience these events yearly. These incidents increase hospital admission costs by 41% and significantly affect patients' quality of life. What could be a one-day hospital stay may extend to a month-long hospitalization, necessitating additional surgeries, extended rehabilitation, and potentially severe life-altering consequences.
Research Vision and Goals
We will help big data realize personalized medicine for surgical patients. We envision a technology-enabled operating room that pulls data from prior operations for real-time clinical decision-making, much like a GPS for surgeons.
We are building technology as the foundation for a worldwide database of surgical cases. A surgeon learns and improves one operation at a time. An AI system can learn from thousands of cases simultaneously. It allows for collecting, analyzing, and sharing quantitative evidence in real-time across multiple surgeons, a “Collective Surgical Consciousness.”
The goals of our research in surgery are to:
Democratize surgical knowledge
Lower costs
Improve outcomes
Reduce morbidity and mortality
Improve Surgeon’s experience