A Conformation Variant of p53 Combined with Machine Learning Identifies Alzheimer Disease in Preclinical and Prodromal Stages

Early diagnosis of Alzheimer's disease (AD) is a crucial starting point in disease management. Blood-based biomarkers could represent a considerable advantage in providing AD-risk information in primary care settings. Here, we report new data for a relatively unknown blood-based biomarker that holds promise for AD diagnosis. We evaluate a p53-misfolding conformation recognized by the antibody 2D3A8, also named Unfolded p53 (U-p53(2D3A8+)), in 375 plasma samples derived from InveCe.Ab and PharmaCog/E-ADNI longitudinal studies. A machine learning approach is used to combine U-p53(2D3A8+) plasma levels with Mini-Mental State Examination (MMSE) and apolipoprotein E epsilon-4 (APOE epsilon 4) and is able to predict AD likelihood risk in InveCe.Ab with an overall 86.67% agreement with clinical diagnosis. These algorithms also accurately classify (AUC = 0.92) A beta(+)-amnestic Mild Cognitive Impairment (aMCI) patients who will develop AD in PharmaCog/E-ADNI, where subjects were stratified according to Cerebrospinal fluid (CSF) AD markers (A beta 42 and p-Tau). Results support U-p53(2D3A8+) plasma level as a promising additional candidate blood-based biomarker for AD.

Automated summary

Early diagnosis of Alzheimer's disease is crucial in disease management. Blood-based biomarkers, such as U-p53(2D3A8+), show promise as additional candidate biomarkers for AD diagnosis. Machine learning algorithms combining U-p53(2D3A8+) plasma levels with other markers can accurately predict AD likelihood risk and classify patients with aMCI who will develop AD.