ProCoG

BACKGROUND

The aging of the global population is placing increasing pressure on healthcare systems and economies. By 2050, the proportion of people over the age of 60 is expected to reach 22%, accompanied by a significant rise in age-related conditions, particularly neurodegenerative diseases such as Alzheimer’s disease (AD). This disease represents a major public health challenge, with an estimated cost of more than 1% of global GDP. In this context, it is becoming essential to develop strategies for prevention and individualized monitoring, as well as earlier diagnosis, to enable care that is better tailored to each patient’s specific course of the disease.

Alzheimer’s disease is characterized by progressive cognitive decline, the course of which varies greatly from one individual to another. This variability makes it difficult to plan personalized care and poses new challenges for the administration of treatments currently under development. The ProCoG project addresses this issue by leveraging the MEMENTO database, a longitudinal cohort of 2,300 individuals who were initially healthy but reported cognitive complaints. These participants are followed every six months for two years, with clinical, neuropsychological, biological, and brain imaging assessments, as well as questionnaires regarding their lifestyle and social environment.

The goal of the project is to predict changes in cognitive status based on data from neuropsychological assessments. Ultimately, patients are classified into three groups: those who remain cognitively healthy, those who develop mild cognitive impairment, and those who progress to major cognitive impairment, a hallmark of Alzheimer’s disease. The analyses will seek to better characterize these cognitive trajectories using machine learning methods, not only on isolated scores but also on multidimensional cognitive profiles. This integrated approach, which has yet to be fully explored, offers increased potential for individualized prediction. It builds on the team’s solid methodological track record, particularly in graph analysis applied to cognitive data, enabling an understanding of the dynamic relationships between different functions such as memory, language, and executive functions.

---

STUDENT CONTRIBUTION

The student selected for this Master’s 2 research internship will play a central role in carrying out the project. They will begin with an in-depth literature review focusing on both Alzheimer’s disease and predictive analysis approaches applied to longitudinal data. They will then be required to familiarize themselves with the MEMENTO database, particularly the cognitive scores extracted from successive neuropsychological assessments. They will actively participate in the analyses, which will utilize advanced machine learning methods to model changes in cognitive status over a 24-month period.

At the same time, the student will also have the opportunity to engage in additional analyses based on graph theory to explore the interactions between different cognitive dimensions. These analyses will help identify typical cognitive profiles associated with different trajectories and provide a better understanding of the tipping points between a healthy cognitive state and a pathological one. This work is part of a multidisciplinary approach combining cognitive neuroscience, neuropsychology, and data science, and will provide the student with valuable experience on a research project with significant societal and clinical implications.