Background: The cause of cognitive impairment in acutely hospitalized geriatric patients is often unclear. The diagnostic process is challenging but important in order to treat potentially life-threatening etiologies or identify underlying neurodegenerative disease.
Objective: To evaluate the add-on diagnostic value of structural and metabolic neuroimaging in newly manifested cognitive impairment in elderly geriatric inpatients.
Methods: Eighty-one inpatients (55 females, 81.6±5.5 y) without history of cognitive complaints prior to hospitalization were recruited in 10 acute geriatrics clinics. Primary inclusion criterion was a clinical hypothesis of Alzheimer's disease (AD), cerebrovascular disease (CVD), or mixed AD+CVD etiology (MD), which remained uncertain after standard diagnostic workup. Additional procedures performed after enrollment included detailed neuropsychological testing and structural MRI and FDG-PET of the brain. An interdisciplinary expert team established the most probable etiologic diagnosis (non-neurodegenerative, AD, CVD, or MD) integrating all available data. Automatic multimodal classification based on Random Undersampling Boosting was used for rater-independent assessment of the complementary contribution of the additional diagnostic procedures to the etiologic diagnosis.
Results: Automatic 4-class classification based on all diagnostic routine standard procedures combined reproduced the etiologic expert diagnosis in 31% of the patients (p = 0.100, chance level 25%). Highest accuracy by a single modality was achieved by MRI or FDG-PET (both 45%, p≤0.001). Integration of all modalities resulted in 76% accuracy (p≤0.001).
Conclusion: These results indicate substantial improvement of diagnostic accuracy in uncertain de novo cognitive impairment in acutely hospitalized geriatric patients with the integration of structural MRI and brain FDG-PET into the diagnostic process.
Keywords: Cognitive impairment; geriatric inpatients; magnetic resonance imaging; multimodal classification; positron emission tomography.