An Integrative Multimodal Model for Early Diagnosis of Dementia and Differential Diagnosis of Alzheimer's Disease Using Neuroimaging, Polygenic Risk, and Cognitive Assessments

Researchers developed and validated a multimodal model called MHS-RWD that combines demographic data, cognitive tests, brain MRI imaging, and genetic information to support early diagnosis of dementia and differentiation of Alzheimer's disease from other types of dementia. The model was tested on 1,100 patients from Norwegian memory clinics for early dementia diagnosis and on 788 patients for differential diagnosis of Alzheimer's disease. Results showed that the combined model achieves accuracy of 0.89 in women and 0.84 in men for early dementia diagnosis, and 0.91 in women and 0.83 in men for distinguishing Alzheimer's disease from other dementias. The model outperforms individual predictors used alone and uses data available in routine clinical practice. Results are presented to patients in an understandable form of individualized risk reports.