Digital Integrated Cognitive Assessment Accurately Diagnoses Mild Cognitive Impairment and Mild Alzheimer Disease 

As published in Frontiers in Psychiatry  the Integrated Cognitive Assessment (ICA) (Cognetivity Neurosciences, Vancouver, Canada) may have validity for detection and monitoring of mild cognitive impairment (MCI) and mild Alzheimer disease (AD). The ICA is a 5-minute, language-independent cognitive test administered via computer. The ICA uses artificial intelligence (AI) model for improved accuracy in assessing cognitive impairment. 

In this study, 95 healthy volunteers, 80 people with MCI, and 55 people with mild AD took the ICA, the Montreal Cognitive Assessment (MoCA), and Addenbrooke’s Cognitive Examination (ACE) test. The ICA detected MCI with an area under the curve of 81% for MCI and 88% for mild AD. The ICA also had convergent validity with MoCA (Pearson r=0.58, P<.0001) and ACE (r=0.62, P<.0001). Correlation with year of education was lower on the ICA (r=0.17; P=.01) than on the MoCA (r=0.34, P<.0001) or ACE (r=0.41, P<.0001). 

“The diagnostic accuracy of the ICA and its novel use of explainable AI, combined with the power to generalize across other languages and cultures, make it uniquely suitable for cognitive screening across large and diverse populations,” said Dag Aarsland, PhD, King’s College, London, “and in light of the FDA’s recent approval of the disease-modifying drug aducanumab, the need for a device capable of screening a wide population of at-risk individuals has never been higher.”  

Performance of the ICA improved with increased training data and was generalizable among the populations studied after controlling for language, culture and education. These results suggest the ICA has potential to be used for large-scale screening for MCI and mild AD.