Breaking New Ground in Computational Psychiatry: Model-Based Characterization of Forgetting in Healthy Aging and Mild Cognitive Impairment

Abstract

Computational models of memory used in adaptive learning settings trace a learner's memory capacities. However, less work has been done on the implementation of these models in the clinical realm. Current assessment tools lack the reliable, convenient, and repeatable qualities needed to capture the individualized and evolving nature of memory decline. The goal of this project was to predict and track memory decline in subjectively- or mildly cognitively impaired (MCI) individuals by using a model-based, adaptive fact-learning system. Here, we present data demonstrating that these tools can diagnose mild memory impairment with over 80% accuracy after a single 8-minute learning session. These findings provide new insights into the nature and progression of memory decline and may have implications for the early detection and management of Alzheimer's disease and other forms of dementia.

Model-Based Characterization of Forgetting in Children and Across The Lifespan

“…Specifically, children were tested on pairs of novel visual stimuli, while adults were tested with a variety of materials that included both verbal and visual stimuli, and often included relatively unfamiliar but not entirely novel materials (i.e., pairs of country names and associated flags). While Sense et al (2016) and Hake et al (2023) reported that SoF values were not significantly affected by the specific material used, the heterogeneity of stimuli employed here made it impossible for us to systematically assess this.…”

“…Recent applications of this methodology have demonstrated its efficacy in measuring memory function accurately and reliably across a broad demographic spectrum, including young adults (Sense et al 2016), the elderly, and individuals experiencing memory loss, showcasing its potential to detect subtle memory function changes associated with conditions like mild cognitive impairment (Hake et al 2023).…”