Development of an Ensemble Learning-based, Multi-dimensional Sensory Impairment Score to Predict Cognitive Impairment in an Elderly Cohort of Southern Italy

There is now strong scientific literature showing a relationship between sensory loss and cognitive performance and between sensory loss and incident dementia. We take as our starting point that people with hearing, vision, and/or cognitive problems have poorer health outcomes, possibly due to due to common age-related mechanism(s), iatrogenic problems in the health care system (e.g., misdiagnosis), and/or the decay of social networks. With this evidence, our project will provide a better understanding of the relationship between sensory loss and cognitive loss in older adults with or at risk for dementia using objective technologies to measure sensory deficits that refer not only to vision loss, hearing loss, olfaction and taste but also to senses deemed atypical, i.e., nociception. In particular, the project aims:

1. To assess the specific association between different sensory measures (central and peripheral hearing loss, retinal abnormalities measured by OCT, smell and taste objective measures, chronic pain, and proprioception subjective and electrophysiological measures. 2. To develop a multi-dimensional score using sensory features and clinical and lifestyle variables to predict the different types of dementia (Alzheimer's Disease, Fronto-Temporal Dementia, and Vascular Dementia) at different stages (Mild Cognitive impairment and Normal Cognition). 3. To create a connectomic map of the MRI morphologic and dynamic features of the Dementia cases and their relationships with sensorial features, describing the patterns differences in respect to the normal cognition controls.

To achieve the proposed aims, the synergic work of the four units involved in the proposal will be required. Subject assessment will be divided between clinical setting (ICS Maugeri) and population setting (ASL BARI). IRCCS "S. De Bellis" will provide expertise for both design refinement, creation and monitoring of deliverables and milestones, and technological support for sense measurements. Finally, the features extracted in clinical populations afferent to the centers of the Azienda Sanitaria Locale di Bari and the neurological clinics of the ICS Maugeri will be analyzed with innovative methods by the Polytechnic University of Bari using artificial intelligence algorithms based on ensemble learning for the creation of a predictive score for cognitive impairment that takes into account both sensory and clinical aspects and related to lifestyles.