KIPeriOP is a research project funded by the German Federal Ministry of Health (BMG) with the aim of improving perioperative risk management and reducing perioperative mortality and permanent damage. Clinical guidelines already support perioperative decision-making and will be complemented in the project by the trustworthy use of artificial intelligence, including the prediction of postoperative risks based on preoperative risk factors. The project consortium combines outstanding clinical, technical, ethical and economic expertise and is led by the University Hospital of Würzburg (clinical coordination) and the Fraunhofer Institute for Digital Medicine MEVIS (technical coordination).

Motivation

Despite medical advances, the mortality rate for surgery has been as high as 0.8 percent for the past ten years. Experts expect that improved risk management before, during and after surgery could reduce mortality and permanent damage. Clinical guidelines support decision-making by defining risk parameters and assessing the risk of harm. This is where the KIPeriOP project comes in, using an AI solution to help make reliable predictions of potential risks during surgery.

Goals and approach

The primary goal of the KIPeriOP project is to develop a digital decision support system (CDS) that improves the prediction and documentation of risk predictions before and after surgery. In this way, users are to be supported in implementing clinical guidelines in practice. The project aims to use AI algorithms to develop reliable and transparent models for predicting impending health damage and the relevant factors. The algorithms are to be validated using data from the participating clinics. In addition to the algorithmic-technical solution, the project will also investigate the extent to which existing guidelines for action can be expanded and innovative solutions for clinical decision support can be integrated into clinical processes and communication with patients.

Outlook for medical practice

A key objective of the project is the concrete improvement of patient-centred care and the optimization of personalized treatment. The project can help to better assess the risk of consequential damage for patients who are about to undergo surgery and to take measures to minimize the risk at an early stage. By investigating ethical, economic and user-specific aspects, the project also makes an important contribution to increasing the acceptance of AI in medicine.