Abstract #4213

Phenotyping Superagers Using Machine Learning Algorithms on Whole Brain Connectivity Resting-State fMRI Studies

Laiz Laura de Godoy¹, Wenqi Min², Demetrius Ribeiro de Paula³, Adalberto Studart-Neto⁴, Nathan Green⁵, Paula Arantes⁶, Khallil Taverna Chaim⁶, Natália Cristina Moraes⁴, Mônica Sanches Yassuda⁴, Ricardo Nitrini⁴, Claudia da Costa Leite⁶, Andrea Soddu⁷, Sotirios Bisdas⁸, and Jasmina Panovska-Griffiths⁹

¹Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, United States, ²Mathematical Institute, University of Oxford, Oxford, United Kingdom, ³Donders Institute for Brain Cognition and Behavior, Radboud University Medical Centre, Nijmegen, Netherlands, ⁴Department of Neurology, University of Sao Paulo, Sao Paulo, Brazil, ⁵Department of Statistics, University College London, London, United Kingdom, ⁶Department of Radiology and Oncology, University of Sao Paulo, Sao Paulo, Brazil, ⁷Department of Physics and Astronomy, Western Institute for Neuroscience, London, ON, Canada, ⁸Lysholm Department of Neuroradiology, University College London, London, United Kingdom, ⁹The Pandemic Sciences Institute, University of Oxford, Oxford, United Kingdom

Synopsis

Keywords: Aging, fMRI (resting state), Superager; machine learning; memory; networks

Motivation: A significant gap remains in the literature regarding whole-brain functional analyses in superagers.

Goal(s): Identify the key neural networks responsible for superagers' function connectivity abilities, which may contribute to brain resilience.

Approach: We extended our previous work and explored the whole brain connectivity of superagers by using a random forest machine-learning algorithm (RF-MLA).

Results: We confirmed the importance of the salience and default mode networks in classifying superagers and replicated the most discriminative nodes. Exploring the whole-brain connectivity analysis, the RF-MLA determined additional nodes in sensory hubs. This is a new finding and suggests novel avenues for investigating brain resilience.

Impact: Our advanced analytical techniques validate existing findings and give new insights into sensory cortices that may be important for superagers’ comprehending cognitive resilience. This could be helpful to guide future targeted interventions to optimize the efficiency of specific brain regions.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.