Epigenomic and machine learning models to predict pancreatic cancer: development of a new algorithm to integrate clinical, omics, DNA methylation biomarkers and environmental data for early detection of pancreatic cancer in high-risk individuals.
In this project FRRB finances the coordinator: Istituto Europeo di Oncologia IRCCS. The Principal Investigator is Dr. Serena Oliveri.
|
Pathology of interest: |
Pancreatic Cancer |
|
Area of research: |
Oncology |
|
Start date: |
1st April 2022 |
|
End date: |
31st March 2025 |
|
Funding: |
€ 281.800,00 |
|
Project partners: |
- Istituto Europeo di Oncologia IRCCS (IEO) (Italy) - Bellvitge Biomedical Research Institute (IDIBELL) (Spain) - Pomeranian Medical University (PMU) (Poland) - The Oncology Institute "Prof Dr. Ion Chiricuta" (IOCN) (Romania) - Centre Hospitalier Universitaire de Toulouse (CHUT) (France) |
PROJECT SUMMARY
Pancreatic cancer (PC) has the lowest survival rate of all cancers in Europe, with no early detection strategies available.
The IMAGene project will develop, implement and test a comprehensive Cancer Risk Prediction Algorithm (CRPA) to predict PC in high-risk (HR) asymptomatic subjects; it will investigate the potential for DNA methylation biomarkers to improve currently available risk indexes, and validate the feasibility of using liquid biopsies for early detection of cancer in such HR individuals.
A sample of 170 healthy first-degree relatives of PC patients will be recruited, and their epidemiological factors related to PC risks assessed through initial interviews.
Subjects will receive medical and psychological visits, and will undergo screening for germline mutations, DNA methylation profiling plus Whole-body MRI at baseline.
Biostatistical analysis of data will be performed to develop algorithms able to extract risk profiles from biological and imaging data. All subjects will undergo epigenetic follow-ups plus radiological exam at 1 year after baseline. Participants’ lifestyle, epidemiological and psycho-decisional assessment will be performed through a monitoring process over the 3 years of the project.
HR subjects’ lifestyle data will be correlated with DNA methylation profiles. All data collected will feed the supervised machine learning CRPA.
Assuming the risk assessment through CRPA and DNA methylation profiling allows a two or three-fold enrichment in early detection of suspicious cancer in HR individuals (compared to the detection rate of pancreatic cysts with malignant potential observed in non-stratified asymptomatic population, 9.3%), we expect a detection rate of suspicious lesions of 20-25% in the selected population.
A cost-utility and a detailed ethical analysis will be conducted. The IMAGene project will adopt a transnational, multi-level, multidisciplinary and multi-methodological approach to achieve its aims.