Integrating new algorithms using the genetic variability
Integrating new algorithms using the genetic variability
The project is led by Olivier Cussenot, Professor of Urology and Director of the Center for Research on Prostatic and Urological Pathologies (CeRePP) in Paris.
Duration of the project: 2023-2025
Objectives:
- Integrate genetic markers into the estimation of competitive morbidity and mortality from a database of male cohorts followed for 20 years.
- Define subsets of markers and predictive algorithms useful for causal inference, personalized screening, and interventional prevention.
The goal of this project is to integrate genetic markers into the estimation of competitive morbidity and mortality from a database – the only one of its kind in the world – of three cohorts of men followed for 20 years. Furthermore, the project aims to define subsets of genetic markers and predictive algorithms that could be useful in personalized screening, intervention, and prevention, and to offer insights on useful strategies for causal inference in prostate diseases. This project involves various fields in terms of research and technical collaboration, including oncology, cardiovascular and degenerative diseases, the analysis of genetic factors, and the development of predictive models using, among other things, artificial intelligence and deep learning, risks and socio-environmental factors, and recent developments in precision medicine.
Fields of research / technical cooperation
Cancers, cardiovascular and degenerative diseases, genetic factors, predictive models, risks, socio-environmental factors, artificial intelligence, deep-learning, precision medicine.
Olivier Cussenot
is the Director of the Center for Research on Prostatic and Urological Pathologies (CeRePP) and a visiting professor at Oxford University. He is a urologist, oncologist and geneticist and was professor at Paris-Sorbonne University and Head of the Department of Rrology at the French Assistance Publique des Hôpitaux de Paris (APHP). He is particularly involved in predictive oncology research. He is among the world’s and France’s top 2% of scientists according to the AD scientific index 2023. He has just published a book summarizing his main research conclusions and experience, which has already seen great success among practitioners and patients: “Medical Decision-Making in the Era of Artificial Intelligence.”
The researchers recently published a comprehensive report shedding light on statistical paradoxes and fallacies prevalent in causal epidemiological studies of prostate cancer (Cussenot O, et al. Curr Opin Urol. 2023 PMID: 37555785). Their findings deciphered common errors attributable to confounding factors and misclassifications, revealing the critical significance of incorporating systems biology insights and implementing cross-validations with genetic markers in the realm of causal inference.
Anticipated outcomes will be categorized into three distinct levels using a range of cutting-edge statistical and artificial intelligence tools, including machine learning, boosting algorithms, and structural causal models. These methodologies will help to explore and formulate hypothetical future intervention strategies for prevention.
