CADHO: Cardiovascular Digital Health Data Observatory
Study Details
Study Description
Brief Summary
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).
Condition or Disease | Intervention/Treatment | Phase |
---|---|---|
|
Detailed Description
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.
Study Design
Outcome Measures
Primary Outcome Measures
- Prospectively validate cardiovascular medical image analysis algorithms capable of identifying patients with poor prognostic criteria using artificial intelligence and big data methods. [Through study completion, an average of 1 year]
The rate of occurrence of death or hospitalization for heart failure during follow-up.
Secondary Outcome Measures
- Evaluate the predictive performance of algorithms to identify patients with persistent anginal symptoms. [12 months]
Seattle Angina Questionnaire summary score to 12 months
- Evaluate the predictive performance of algorithms to identify patients with persistent dyspnea symptoms. [12 months]
Rose Angina Questionnaire to 12 months
- Evaluate the predictive performance of algorithms to identify patients with good disease perception. [12 months]
Seattle Angina Questionnaire to 12 months
- Evaluate the predictive performance of algorithms to identify patients satisfied with their care. [12 months]
Seattle Angina Questionnaire to 12 months
- Evaluate the predictive performance of the algorithms for quality of life at one year. [12 months]
EuroQOL (EQ-5D-5L) to 12 months
- Evaluate the predictive performance of algorithms for healthcare consumption [12 months]
Average annual cost of care to 12 months
- Assessing the prognostic value of frailty in coronary artery disease [Day one]
Dynanometry
- Assessing the prognostic value of environmental influence in coronary artery disease [Day one]
Measurement of air pollutants from the SIRANE dispersion model
Eligibility Criteria
Criteria
Inclusion Criteria:
-
Adult patients who have undergone coronary angiography at CHUGA for whom images are usable.
-
No opposition to participation
Exclusion Criteria:
-
Coronary image not usable
-
Persons referred to in articles L1121-5 to L-1121-8 of the CSP
-
Patients living outside the Rhône Alpes region.
Contacts and Locations
Locations
No locations specified.Sponsors and Collaborators
- University Hospital, Grenoble
Investigators
- Principal Investigator: Gilles Barone-Rochette, CHU Grenoble Alpes
Study Documents (Full-Text)
None provided.More Information
Publications
- Betancur J, Hu LH, Commandeur F, Sharir T, Einstein AJ, Fish MB, Ruddy TD, Kaufmann PA, Sinusas AJ, Miller EJ, Bateman TM, Dorbala S, Di Carli M, Germano G, Otaki Y, Liang JX, Tamarappoo BK, Dey D, Berman DS, Slomka PJ. Deep Learning Analysis of Upright-Supine High-Efficiency SPECT Myocardial Perfusion Imaging for Prediction of Obstructive Coronary Artery Disease: A Multicenter Study. J Nucl Med. 2019 May;60(5):664-670. doi: 10.2967/jnumed.118.213538. Epub 2018 Sep 27.
- Fearon WF, Low AF, Yong AS, McGeoch R, Berry C, Shah MG, Ho MY, Kim HS, Loh JP, Oldroyd KG. Prognostic value of the Index of Microcirculatory Resistance measured after primary percutaneous coronary intervention. Circulation. 2013 Jun 18;127(24):2436-41. doi: 10.1161/CIRCULATIONAHA.112.000298. Epub 2013 May 16.
- González G, Ash SY, Vegas-Sánchez-Ferrero G, Onieva Onieva J, Rahaghi FN, Ross JC, Díaz A, San José Estépar R, Washko GR; COPDGene and ECLIPSE Investigators. Disease Staging and Prognosis in Smokers Using Deep Learning in Chest Computed Tomography. Am J Respir Crit Care Med. 2018 Jan 15;197(2):193-203. doi: 10.1164/rccm.201705-0860OC.
- Krittanawong C, Johnson KW, Rosenson RS, Wang Z, Aydar M, Baber U, Min JK, Tang WHW, Halperin JL, Narayan SM. Deep learning for cardiovascular medicine: a practical primer. Eur Heart J. 2019 Jul 1;40(25):2058-2073. doi: 10.1093/eurheartj/ehz056. Review.
- Lu MT, Ivanov A, Mayrhofer T, Hosny A, Aerts HJWL, Hoffmann U. Deep Learning to Assess Long-term Mortality From Chest Radiographs. JAMA Netw Open. 2019 Jul 3;2(7):e197416. doi: 10.1001/jamanetworkopen.2019.7416.
- Skrede OJ, De Raedt S, Kleppe A, Hveem TS, Liestøl K, Maddison J, Askautrud HA, Pradhan M, Nesheim JA, Albregtsen F, Farstad IN, Domingo E, Church DN, Nesbakken A, Shepherd NA, Tomlinson I, Kerr R, Novelli M, Kerr DJ, Danielsen HE. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet. 2020 Feb 1;395(10221):350-360. doi: 10.1016/S0140-6736(19)32998-8.
- Slama R, Morgenstern V, Cyrys J, Zutavern A, Herbarth O, Wichmann HE, Heinrich J; LISA Study Group. Traffic-related atmospheric pollutants levels during pregnancy and offspring's term birth weight: a study relying on a land-use regression exposure model. Environ Health Perspect. 2007 Sep;115(9):1283-92.
- 38RC21.197