You are here: indexactivitiessetsmsq

Surgical process deviation detection


This work was partially supported by French state funds managed by the ANR within the Investissements d'Avenir programme (Labex CAMI) under reference ANR-11-LABX-0004.

General purpose

More than 1 million of adverse events were reported to the U.S. Food and Drug Administration in 2013 with more than 700,000 in the United States. Some of them could be explained by preventable intra-operative adverse events. The objective of this thesis is to detect and explain the appearance of intra-operative adverse event.


Complications are important factors of outcomes in surgery. Postoperative complications have been studied for a long time and can be classified by their seriousness (e.g., the Dindo-Clavien classification [1]). Although they have been defined by the World Health Organization (WHO) more than 10 years ago [2], intra-operative complications have only been recently studied. Intra-operative adverse events are now considered as a real challenge to be addressed. For instance, they concern more than 7% of laparoscopic colorectal procedures [3].

For this project, we focused on rectopexy, an abdominal surgery. Rectopexy is performed to correct anal prolapse by fixing the rectum to the promontory through meshes [4]. Firstly, we modeling the “typical” rectopexy and the deviation from this “ideal” surgery. For this, we chose to use cognitive task analysis with interview of surgeon and observation in the operating room and based on laparoscopic videos. With this work, we were able to describe the “typical” rectopexy with medical vocabulary on different levels of granularity.

Secondly, we tried to detect deviations in a surgical process model and to distinguish the ones due to patient's anatomical particularities from the ones due to intra-operative events. In order to accomplish this, we use a combination of dynamic time warping and a hidden Markov model methods. Finally, we tried to identify patterns to explain and predict the appearance of intra-operative adverse events.


  • Huaulmé A,Voros S, Reche F, Faucheron J-L, Jannin P, Moreau-Gaudry A (2014) Surgical Process Model of laparoscopic rectopexy. In: Proceedings of Surgetica 2014, Chambery, France, pp 239-241
  • Huaulmé, A., Jannin, P., Reche, F., Faucheron, J. L., Moreau-Gaudry, A., & Voros, S. (2020). Offline identification of surgical deviations in laparoscopic rectopexy. Artificial Intelligence in Medicine, 104, 101837.article


  • [1] Dindo D, Demartines N, Clavien PA (2004) Classification of Surgical Complications: A New Proposal With Evaluation in a Cohort of 6336 Patients and Results of a Survey. Annals of Surgery 240(2):205-213, DOI 10.1097/
  • [2] World Healt Organization (2005) WHO draft guidelines for adverse event reporting and learning systems. URL
  • [3] Kirchhoff P, Dincler S, Buchmann P (2008) A Multivariate Analysis of Potential Risk Factors for Intra- and Postoperative Complications in 1316 Elective Laparoscopic Colorectal Procedures:. Annals of Surgery 248(2):259-265, DOI 10.1097/SLA.0b013e31817bbe3a
  • [4] D. Lechaux, Traitement des prolapsus du rectum par abord laparoscopique EMC - Tech. Chir. - Appar. Dig., vol. 2, no. 1, pp. 1-7, Jan. 2007.

Main Collaborators

Main Fundings

inserm rennes1 ltsi