A machine learning approach to understand surgical performance

S. Sinigaglia, G. Megali, F. Cavallo, O. Tonet, P. Dario, A. Pietrabissa

Research output: Contribution to journalArticlepeer-review


In this paper the Hidden Markov Models (HMMs) are used as a tool for understanding minimally invasive surgical performance and human factors that characterize it In our experiments we studied data concerning the tools positioning during exercises performed on a surgical simulator. By means of Hidden Markov Models theory, we created a model of the "expert surgeon performance" able to evaluate surgical capability and to distinguish expert and novice surgeon performances. By analyzing the trained model and video acquisitions, we show that it is possible to deduce information about features characterizing the surgical expertise.

Original languageEnglish
Pages (from-to)445-447
Number of pages3
JournalInternational journal of computer assisted radiology and surgery
Issue numberSUPPL. 7
Publication statusPublished - Jun 2006


  • Hidden Markov Model
  • Minimally invasive surgery
  • Performance evaluation
  • Surgical simulator
  • Surgical training

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Transplantation


Dive into the research topics of 'A machine learning approach to understand surgical performance'. Together they form a unique fingerprint.

Cite this