AI in endoscopic transsphenoidal surgery

  • Research type

    Research Study

  • Full title

    The application of Artificial Intelligence to patients undergoing endoscopic transsphenoidal surgery: a single-site prospective feasibility study.

  • IRAS ID

    271696

  • Contact name

    Hani Marcus

  • Contact email

    h.marcus@ucl.ac.uk

  • Sponsor organisation

    University College London

  • Clinicaltrials.gov Identifier

    Z6364106/2019/10/147, Data Protection office

  • Duration of Study in the UK

    3 years, 0 months, 1 days

  • Research summary

    Surgery through the nose, termed “transsphenoidal surgery”, is the treatment of choice for most symptomatic sellar and suprasellar lesions. Endoscopy has allowed the approach to be used for an increasing number of difficult-to-reach lesions.
    However, variations can occur in surgical performance, delivery and approach, potentially resulting in avoidable errors and complications.

    Modern digital tools are designed to support surgical teams in training and in preparation for surgery, streamlining team coordination, efficiency during surgery and postoperatively analytics.

    Digital Surgery™ has developed an artificial intelligence-guided platform (“GoSurgery”), which could support consistent surgical practice and potentially assist in the standardising procedures through process mapping and data analysis.
    The aim of this study is to apply the GoSurgery platform to endoscopic transsphenoidal surgeries performed at the University College London Hospital NHS Foundation Trust to evaluate the feasibility of this platform.

    The platform allows the creation of procedural workflows for surgeons and scrub teams.
    During the operation, workflows are shown on multiple visual display units, with separate content visible for the operating and scrub teams, to support staff through the procedural steps and equipment required for the case. The platform includes encrypted computing equipment that records and automatically anonymises the operation, performs automatic analysis of the procedural steps to drive the displays during the operation and uploads the anonymised surgical video through a secure web-platform.

    The primary objective is to evaluate the feasibility of the GoSurgery platform based upon analysing prospective data including qualitative questionnaires administered to surgeons and scrub nurses, anonymised preoperative clinical data, anonymised surgical video, and postoperative analytics.

    The secondary objectives are: i) to investigate whether the effectiveness and efficiency of surgical teams have changed following the implementation of the platform; ii) to evaluate the efficacy of the platform for educational/training purposes; iii) to utilise the surgical videos and the prospectively collected anonymised data to train the AI algorithm to predict the likely operative course and outcomes of surgery based on pre- and intra-operative data.

  • REC name

    South West - Frenchay Research Ethics Committee

  • REC reference

    21/SW/0027

  • Date of REC Opinion

    4 May 2021

  • REC opinion

    Further Information Favourable Opinion