Artificial Intelligence in Medical Robotics

About this research line

In collaboration with ORSI Academy, AIRO explores how AI can support surgeons directly in the operating room during robotic-surgery.

Our work focuses on multimodal systems that combine surgical video with speech and audio, using vision-language models to understand what is happening during a procedure in real time. Moreover, we are interested in leveraging these models in an agentic setting where we want to go beyond analysis and can actively assist in useful, timely ways during the procedure. A key part of this is understanding human intent and designing natural interactions between surgeons and assistant technologies, in order to create truly collaborative systems. This includes real-time voice assistance that allows surgeons to ask context-specific questions, communicate naturally with the system, and receive relevant support without breaking focus during a procedure.

Surgical training is a major part of that vision too: the same AI systems that can assist during an operation can also help surgeons train more effectively by recognizing procedural steps, highlighting critical moments, and offering targeted feedback in a natural and intuitive way. Together with Orsi, we aim to develop tools that match the realities of robotic surgery: reliable, clinically relevant, and designed around the needs of the surgical staff. While the field is still rapidly evolving, we believe these technologies can lead to smarter support in the OR, more personalized training, and ultimately safer and better informed surgical care.

A surgical robot. Copyright 2026 Orsi Academy

Active researchers

Related publications

Surgical phase duration in robot-assisted partial nephrectomy : a surgical data science exploration for clinical relevance

Pieter De Backer, Maria Peraire Lores, Meret Demuynck, Federico Piramide, Jente Simoens, Tim Oosterlinck, Wouter Bogaert, Chi Victor Shan, Karel Van Regemorter, Aube Wastyn, Enrico Checcucci, Charlotte Debbaut, Charles Van Praet, Rui Farinha, Ruben De Groote, Anthony Gallagher, Karel Decaestecker, Alexandre Mottrie

In DIAGNOSTICS 2023

BIBLIO

Abstract

(1) Background: Surgical phases form the basic building blocks for surgical skill assessment, feedback, and teaching. The phase duration itself and its correlation with clinical parameters at diagnosis have not yet been investigated. Novel commercial platforms provide phase indications but have not been assessed for accuracy yet. (2) Methods: We assessed 100 robot-assisted partial nephrectomy videos for phase durations based on previously defined proficiency metrics. We developed an annotation framework and subsequently compared our annotations to an existing commercial solution (Touch Surgery, Medtronic (TM)). We subsequently explored clinical correlations between phase durations and parameters derived from diagnosis and treatment. (3) Results: An objective and uniform phase assessment requires precise definitions derived from an iterative revision process. A comparison to a commercial solution shows large differences in definitions across phases. BMI and the duration of renal tumor identification are positively correlated, as are tumor complexity and both tumor excision and renorrhaphy duration. (4) Conclusions: The surgical phase duration can be correlated with certain clinical outcomes. Further research should investigate whether the retrieved correlations are also clinically meaningful. This requires an increase in dataset sizes and facilitation through intelligent computer vision algorithms. Commercial platforms can facilitate this dataset expansion and help unlock the full potential, provided that the phase annotation details are disclosed.