Cardiovascular Digital Health Data Observatory

Cardiovascular, Cardiovascular Diseases, Coronarography, Digital, Health Data, Heart Failure, Observatory

Deep learning, Observatory, Cardiovascular, Health data

The COVID-19 health crisis has led to a drastic decrease in the rate of myocardial infarction without the causes being completely identified. They are probably multiple, but this crisis has confirmed the need for massive health data from different horizons to better assess coronary disease in order to develop precision medicine. This objective is now achievable thanks to the use of tools such as big data and artificial intelligence (AI). Our team is developing algorithms to analyze medical images and identify people at risk of major cardiovascular events. These algorithms which are developed with retrospective data must be validated on prospective data, which is the objective of the Grenoble cardiovascular digital health data observatory. The algorithm that will be validated is currently being created as part of a RIPH 3 study AIDECORO (NCT: 04598997). It is being developed from clinical, biological and imaging data from 600 patients with ST+ infarction and 1000 control patients who have undergone coronary angiography (these data are exported and stored in the PREDIMED health data warehouse via the hospital information system).

This a type 3 study of the Jardé law, involving the human person, It is a study : observational study, prospective, descriptive, monocentric The main objective of the study is to prospectively validate cardiovascular medical image analysis algorithms capable of identifying patients with poor prognostic criteria using artificial intelligence and big data methods. The primary endpoint is the rate of occurrence of death or hospitalization for heart failure during follow-up. The predictive accuracy of the algorithms will be assessed by calculating the sensitivity, specificity, positive predictive value, and negative predictive value on the prospective cohort. Patients who are to undergo coronary angiography during a hospitalization in the cardiology department are prospectively recruited after obtaining their non opposition. The data were collected using the CARDIO Datamart developed by the PREDIMED health data host. The collection of the primary endpoint (death from any cause and hospitalization for heart failure) will be performed by telephone follow-up. The number of subjects needed for this study is 5000 patients. The prospective validation of the algorithm developed retrospectively in the AIDECORO project (coronary image) will make it possible to move towards the last stage of the project, which will consist of evaluating in a randomized study the superiority of precision medicine using this algorithm, allowing for therapeutic escalation or de-escalation according to the predictive risk evaluated by the algorithm in relation to usual management.

No related papers found yet.

None listed