ARTIFICIAL INTELLIGENCE ENHANCEMENT OF SURGICAL TECHNOLOGY FOR THE REDUCTION OF HUMAN BEHAVIOUR-RELATED SURGICAL ACCIDENTS

Project Information

BESAFE

Grant agreement ID: 847378

DOI

10.3030/847378

Project closed

EC signature date 16 April 2019

Start date 1 May 2019

End date 30 April 2020

Funded under

• EXCELLENT SCIENCE - Future and Emerging Technologies (FET)

Total cost

€ 100 000,00

EU contribution

€ 100 000,00

Coordinated by

AFFERENT TECHNOLOGIES SL
Spain

Periodic Reporting for period 1 - BESAFE (ARTIFICIAL INTELLIGENCE ENHANCEMENT OF SURGICAL TECHNOLOGY FOR THE REDUCTION OF HUMAN BEHAVIOUR-RELATED SURGICAL ACCIDENTS)

Reporting period: 2019-05-01 to 2020-04-30

Summary of the context and overall objectives of the project

BESAFE explores the use of Artificial Intelligence to minimise the risk inherent to surgical procedures.

The underlying assumption (backed by data) is that the human factor is a major contributor to surgical risk, impacting on the probability of adequate resolution of intra-operative events. In particular the level of training of staff and stress are associated with surgical outcome.

BESAFE builds on FET-Open project IBSEN to use machine learning to enhance existing instra-operative instruments and devices, in order to detect inadequate training or stree-prone behaviour before a surgical accident occurs.

The project included a demonstration task to assess the practicalities of the concept and the development of a business plan including financial forecasts and product development strategy.

A key conclusion of the project is that quantitative automated analysis of the interaction of users with computer or instrument interfaces can indeed infer the level of training and cognitive pressure.
An additional conclusion is that this core concept could lead to a financially viable startup with substantial return for investors, health impact for patients and a time to market of 4 years.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Within BESAFE we performed two core activities.

First we demonstrated with over 100 users that machine learning (real-time or offline automated data analysis) can extract the level of training and user stress from the pattern of use of a computer interface.
This result in itself is extremely interesting in that it can be used in multiple fields. Specifically in surgery, the approach developed in IBSEN/BESAFE can anticipate the outcome of time-constrained tasks, and potential decrease surgical risk.

A second key activity in BESAFE was the development of a business plan.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

BESAFE is focused on exploring the market opportunity and on demonstrating technical viability, rather than performing new R&D.

However, modifying how clinicians interact with instrumentation in the oeprating room can have a tremendous socio-economic impact and more widely impact surgical outcomes.

The project's focus has been on planning towards achieving these outcomes at the technical and financial levels.

Heatmap showing correlations amongst variables, as used for machine learning in BESAFE

logo of the project