PreCare-ML: Predicting Cardiovascular Events using Machine Learning
We develop AI systems that automatically analyze hospital records to predict individual patients' risk of heart attacks and strokes. This allows hospitals to screen all patients instead of just a selected few, catching more high-risk people who need preventive care. We standardized data across multiple hospitals, built secure AI infrastructure, and created tools to help communicate risks to patients.
Contact: xy
Funding
Federal Ministry of Research, Technology and Space through the ERA PerMed Framework
Description
Cardiovascular diseases are the leading cause of death globally, making early identification of patients at high risk of major adverse cardiovascular events (MACE) crucial. Currently, these patients are identified using clinical prediction models based on risk scores that have several limitations. Firstly, most rule-based scores require manual calculation or additional data entry by physicians, which makes it infeasible to screen all hospitalized patients due to resource constraints. This results in a selection bias, as only a subset of patients are evaluated, leading to many high-risk patients remaining undetected. Secondly, traditionally used risk scores have been developed for specific populations, meaning they do not consider diverse individual risk factors.
An alternative approach is to use predictions based on machine learning (ML) models, which can incorporate a larger number of predictors and account for nonlinearity in data. In particular, these ML models can use electronic health record (EHR) data to estimate MACE risk for individual patients. This combination of ML models and EHR data allows for rapid, automated, and personalized risk prediction that can be applied to large patient groups. However, although numerous such ML models have been developed in recent years, validation is rare, and it is unclear how these models perform in different clinical settings or with different populations.
Considering this, in the PRE-CARE ML project we are working on further developing and extensively evaluating ML models, specifically federated learning (FL) models, that can estimate a patient's MACE risk based on their EHR data. The work is mainly structured in three goals: (i) to validate and improve risk-predicting ML models across different hospital networks and populations, (ii) to integrate ML models into different hospital information systems and evaluate their impact on daily hospital routines, and (iii) to investigate effective risk communication strategies to encourage behavioral changes in patients.
As the different hospitals in our consortium use different hospital information systems, we spent a considerable amount of time on data harmonization, a stage of the project that is now fully completed. This allowed us to evaluate models developed at one hospital on geographically and demographically diverse EHR records from the other partner institutions, but also is a crucial requirement for developing models using FL. The first results of this external evaluation have already been produced and a publication is soon to follow.
Furthermore, we have actively been working on setting up the FL infrastructure for our experiments, primarily using the combination of the NVFLARE and Flower frameworks. After successfully navigating several regulatory and security roadblocks, the consortium now has an established infrastructure on which to run both FL experiments and experiments regarding external evaluation of models.
Finally, regarding the third goal of the project, i.e., the investigation of effective risk communication strategies, we have completed a comprehensive systematic literature review of digital risk communication strategies and have started discussing our findings with physicians and patients at risk of/living with a cardiovascular condition. With these findings, we also developed an online MACE risk calculation service which aims to educate its users on the meaning of their personalized risk calculation and some possible steps they can take towards mitigating this risk. This work was done as part of the ClearRisk Bachelor Project at HPI.