New risk calculator could lead to more successful heart operations
Patients could benefit more from open-heart surgery thanks to a new computer model aimed at helping surgeons better calculate risk and decide if it’s safe to operate.
This project, jointly funded by us and the Alan Turing Institute, will develop a novel platform using machine learning to identify patients most likely to undergo successful surgery.
More than 30,000 adult patients are considered for heart surgery each year in the UK, and risk prediction plays a major role in the decision-making process for doctors and patients alike.
Cardiac Surgery Risk Assessment
Risk assessment before open heart surgery is crucial because of the potential complications that can arise during and after the operation. To calculate a patient’s risk before surgery, cardiac surgeons currently use models such as the EuroSCORE – but this may overestimate the actual risk, in part due to improvements in patient care since the development of the model.
Therefore, people with a good chance of having a successful operation may be considered inoperable and left untreated.
In cases where the risk is predicted to be too high, this may lead to a risk-averse practice, which means that the patient may refuse to have the operation or the surgeon may decide not to undertake the operation.
Today, researchers from the University of Bristol and the University of Oxford are creating a new risk calculator using a large dataset of information regularly collected from all patients undergoing surgery in the UK. United.
Gianni Angelini, BHF Professor of Cardiac Surgery at Bristol Heart Institute, said:
“We will apply the most advanced machine learning algorithms to identify cardiac patients who are likely to undergo successful open heart surgery.
“By adopting current risk prediction models, surgeons in the UK are exposed to an inappropriate and risk-averse practice that denies surgery to sick patients who would benefit from intervention.”
Improved decision making
Professor Metin Avkiran, our Associate Medical Director, said:
“It is essential that the likely risk/benefit ratio is identified as accurately as possible for each patient before proceeding with surgery. A more reliable risk assessment tool would allow a more informed choice to be made between patients receiving or refusing potentially life-saving heart surgery.
“We are investing in innovation and developing new data-driven technologies as we recognize the enormous potential of data science to transform care for the millions of people with heart and circulatory conditions in the UK.”
EuroSCORE was developed using information collected in 1995 from a relatively small number of patients from eight European countries, including the UK.
The British Society for Cardiothoracic Surgery (SCTS) recognizes the urgent need to replace EuroSCORE with a more accurate risk prediction model and has endorsed the project. If successful, SCTS will assess whether to replace EuroSCORE and implement the new model across all cardiac units in the UK.
Support doctors and patients
Chris Holmes, Program Director for Health and Medical Sciences at the Alan Turing Institute and Professor of Biostatistics at Oxford University, said:
“This project has the potential to provide a new, accurate predictive model that could play an important role in supporting healthcare professionals and patients in their decision-making. It should also help healthcare providers monitor surgical performance, perform quality assessment, and understand a patient’s risk so patients can make an informed decision before a major procedure.
We have launched a new campaign, calling for public support to fuel the science that could lead to new treatments and cures for all heart and circulatory diseases.
Help us fuel discoveries that save lives