Natural language-based markers for neurodegenerative disease discrimination

A significant increase in neurodegenerative diseases (NDs) in the older adult population of Peru has been observed. Current diagnostic procedures are highly expensive and of little or no access to the majority of the population and in many cases are not standardized or validated. On the other hand, the development of machine learning procedures is becoming increasingly widespread in health and neuroscience research fields, including natural language (NL) analysis. Advances in the development of NL algorithms have had an important impact on the differentiation of patients with different neuropsychiatric pathologies, but their use is still not widespread in NDs. The mechanisms for its implementation, its relatively low cost and its high ecological validity make it a valuable tool for diagnostic support in NDs, especially in contexts such as Peru, where the number of specialists is scarce, there are serious equipment shortages and access to health centers in geographically distant areas is almost impossible. Therefore, we have proposed to validate natural language markers that allow us to differentiate the most frequent NDs in older adults in Arequipa, Peru. We hope to develop robust and highly scalable measures that will allow us to support diagnostic processes in health, as well as the development of tools with a multidisciplinary approach in neuroscience.