Does adding MRI and CSF-based biomarkers improve cognitive status classification based on cognitive performance questionnaires?

• Published in: PloS one 2023-05, Vol.18 (5), p.e0285220
• Main Authors: Farina, Mateo P, Saenz, Joseph, Crimmins, Eileen M
• Format: Article
• Language: English
• Subjects: Activities of daily living; Algorithms; Alzheimer Disease - diagnostic imaging; Alzheimer Disease - pathology; Alzheimer's disease; Alzheimers disease; Amyloid beta-Peptides; Analysis; Biological markers; Biology and Life Sciences; Biomarkers; Brain research; Cerebrospinal fluid; Classification; Cognition; Cognitive ability; Cognitive Dysfunction - diagnostic imaging; Cognitive Dysfunction - pathology; Data collection; Dementia; Dementia disorders; Diagnosis; Disease Progression; Evaluation; Humans; Invasiveness; Magnetic Resonance Imaging; Medical imaging; Medicine and Health Sciences; Memory; Modelling; Neurodegenerative diseases; Neuroimaging; Older people; Polls & surveys; Population dynamics; Population studies; Population-based studies; Questionnaires; Regression analysis; Regression models; Research and Analysis Methods; Scanners; tau Proteins
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0285220

Cognitive status classification (e.g. dementia, cognitive impairment without dementia, and normal) based on cognitive performance questionnaires has been widely used in population-based studies, providing insight into the population dynamics of dementia. However, researchers have raised concerns about the accuracy of cognitive assessments. MRI and CSF biomarkers may provide improved classification, but the potential improvement in classification in population-based studies is relatively unknown. Data come from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We examined whether the addition of MRI and CSF biomarkers improved cognitive status classification based on cognitive status questionnaires (MMSE). We estimated several multinomial logistic regression models with different combinations of MMSE and CSF/MRI biomarkers. Based on these models, we also predicted prevalence of each cognitive status category using a model with MMSE only and a model with MMSE + MRI + CSF measures and compared them to diagnosed prevalence. Our analysis showed a slight improvement in variance explained (pseudo-R2) between the model with MMSE only and the model including MMSE and MRI/CSF biomarkers; the pseudo-R2 increased from .401 to .445. Additionally, in evaluating differences in predicted prevalence for each cognitive status, we found a small improvement in the predicted prevalence of cognitively normal individuals between the MMSE only model and the model with MMSE and CSF/MRI biomarkers (3.1% improvement). We found no improvement in the correct prediction of dementia prevalence. MRI and CSF biomarkers, while important for understanding dementia pathology in clinical research, were not found to substantially improve cognitive status classification based on cognitive status performance, which may limit adoption in population-based surveys due to costs, training, and invasiveness associated with their collection.