ORAHS2024
Abstract Submission

69. Digital twin of surgical care assessment and risk evaluation

Contributed abstract in session FB-4: Artificial Intelligence, stream Regular talks.

Friday, 11:00-12:30
Room: Room S3

Authors (first author is the speaker)

1. WANG Yiyu
La loire, Ecole Supérieure des Mines de Saint-Etienne
2. Canan Pehlivan
Industrial Engineering Center, IMT Mines Albi
3. Vincent Augusto
Mines Saint-Etienne

Abstract

In the era of Medicine 4.0, the operating room (OR) is a significant expense in hospitals due to the complexity of surgical procedures, specialized equipment, highly trained staff, and strict regulations.
During surgical procedures, avoidable errors may occur. Our goal is to implement a system to identify these errors and predict the adverse events across different surgical types. We aim to develop a user-friendly and cost-effective digital twin for surgical procedures tailored for individual use, addressing the needs of surgeons.

We initialize our research by the creation of a synthetic database represented by event logs. These event logs serve as input for constructing a surgical workflow framework, enabling error detection and event prediction through process mining and machine learning methods. Subsequently, we simulate the entire surgical process using this framework until successful validation with real-time live usage.

Our research outcomes offer practical applications in the medical field and practical solutions to enhance academic studies, surgical practice, and healthcare management.

Keywords

Status: accepted

Back to the list of papers