Integrated algorithm combining plasma biomarkers and cognitive assessments accurately predicts brain ß-amyloid pathology.

ABSTRACT

BACKGROUND: Accurate prediction of cerebral amyloidosis with easily available indicators is urgently needed for diagnosis and treatment of Alzheimer's disease (AD). METHODS: We examined plasma Aß42, Aß40, T-tau, P-tau181, and NfL, with APOE genotypes, cognitive test scores and key demographics in a large Chinese cohort (N = 609, aged 40 to 84 years) covering full AD spectrum. Data-driven integrated computational models were developed to predict brain ß-amyloid (Aß) pathology. RESULTS: Our computational models accurately predict brain Aß positivity (area under the ROC curves (AUC) = 0.94). The results are validated in Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Particularly, the models have the highest prediction power (AUC = 0.97) in mild cognitive impairment (MCI) participants. Three levels of models are designed with different accuracies and complexities. The model which only consists of plasma biomarkers can predict Aß positivity in amnestic MCI (aMCI) patients with AUC = 0.89. Generally the models perform better in participants without comorbidities or family histories. CONCLUSIONS: The innovative integrated models provide opportunity to assess Aß pathology in a non-invasive and cost-effective way, which might facilitate AD-drug development, early screening, clinical diagnosis and prognosis evaluation.

The numbers of people with Alzheimer's disease are increasing. People with Alzheimer's disease have changes in the brain as well as cognitive impairment, which is when a person has difficulty remembering, learning, concentrating, or making decisions. Innovative medicines and new treatments all target people with early Alzheimer's disease. However, the methods used currently to diagnose Alzheimer's disease are expensive and can be unpleasant for patients. We studied Chinese people with no cognitive impairment, some cognitive decline, mild cognitive impairment, Alzheimer's disease and non-Alzheimer's disease dementia. We established a computational model that can predict the changes seen in the brain in people with Alzheimer's disease from information including results of blood and memory tests. This non-invasive and cost-effective approach might improve early identification of those with Alzheimer's disease.