AI Machine Learning Model Predicts Level of Cognitive Impairment

Helio.com reports that Catherine Diaz-Asper, PhD, associate professor of psychology at Marymount University, and her colleagues examined the effectiveness of an artificial-intelligence-based machine learning model created from remote speech collection of community-dwelling adults and found that the model predicted the subjects’ level of cognitive impairment with 75% accuracy. This was said to be more accurate than standard screening or human analysis. Their study included 91 native English-speaking individuals who were diagnosed as cognitively healthy but with mild Alzheimer’s disease or with amnestic mild cognitive impairment. All participants were called at their residence and completed a 20-minute interview that was digitally recorded. The researchers analyzed content based on criteria such as speech patterns, autobiographical recall, and others. Predictive accuracy ranged from 75% to 88%. This bested the accuracy of the Mini Mental State Exam (MMSE) (55%) and clinician analysis (49.5%) and Telephone Interview for Cognitive Status (TICS) (45%). (MMSE AND TICS are both well-known dementia/Alzheimer’s screening tools.) Marymount researchers said 40% of clinicians expressed strong interest in adopting the AI-based screening test, while an additional 33% agreed that the tool would be valuable in practice. “Timely recognition and monitoring of early cognitive decline is crucial for Alzheimer’s disease clinical trials to facilitate accurate diagnosis, establish baselines, track disease progression, and measure treatment efficacy,” Diaz-Asper and colleagues wrote. “Combining advances in AI with the convenience of the telephone allows for regular, accurate and unbiased screening and monitoring of early cognitive decline.”