Global consortium to work on AI-powered personalised care for heart failure
Heart failure affects more than 64 million people worldwide and is the main cause of hospitalisation in those over 65.
With the global prevalence of the condition predicted to increase by almost 50% by the end of this decade, Amsterdam UMC is launching a consortium to look for an AI-powered solution.
The group “has the ambitious objective of developing a model that can predict the likely outcome for each, individual patient based on available data,” said consortium leader and professor of precision medicine at Amsterdam UMC, Folkert Asselbergs. This, he added, “will allow for timely and highly personalised care.”
To build the AI-model the consortium will combine the data of around 900,000 patients from Europe, Africa, and South America.
The alliance, which consists of partners from across the world, will develop algorithms that will facilitate the personalised risk assessment, by combing data from cardiac imaging and biomakers, ECG results, as well as information from the patient records.
Dr Asselbergs said: “Our patient data set provides us a great opportunity to really understand all of the factors that determine the progress of the condition and, thus, assess an individual patient’s risk.
“Moreover, by involving patients and clinical experts through co-creation workshops from the start we ensure that all relevant patient and clinical requirements are taken into account when developing the AI- model to maximize inclusion, accountability, transparency and fairness, well beyond the quality of technical performance required by the current regulatory frameworks.”
Once the AI model has been built, it will also be translated into an easy-to-use tool for clinicians to use for shared decision making with the goal of a general roll out once the project has been completed and the necessary certification obtained.
Artificial intelligence has come in for wide scale criticism of late as even those behind the technology have warned the machine learning could soon outsmart humans. Some scientists have even called for a pause in AI development.
But the team behind this latest AI-powered medical application, say a key aspect of the project will be ensuring it is implemented in a responsible way.
For Dr Asselbergs, this is “crucial” in ensuring that AI is adopted appropriately.
“In order for our model to be usable, it requires continuous engagement from patients, clinicians and data experts. This will only happen if there is trust in the way the data is used,” he said.
To promote this trust, the consortium will also develop mechanisms that will monitor how AI performs after being introduced in a real-world setting.
The five clinical sites involved in this study are in the Netherlands, Spain, Czechia, Peru and Tanzania. The diversity of location will allow thorough testing of the model as well as facilitating the collection of diverse patient data.
This will also include the study of social and ethical issues that may arise from the implementation of AI to assess patient risk.
Dr Asselbergs concluded: “We want to show with this project just how powerful AI can be as a tool in clinical practice, but we also want to do it in a way that is responsible and considers all of the factors that will affect its use.”
