Machine learning on combined neuroimaging and plasma biomarkers for triaging participants of secondary prevention trials in Alzheimer’s disease

Abstract

Listen

Translate article

AbstractBackgroundPlasma biomarkers have demonstrated excellent agreement with established markers of amyloid‐β (Aβ) positivity (PET and CSF) to identify patients with symptomatic AD. However, their predictive capacity in cognitively unimpaired (CU) individuals is lower. In this work, we aimed at assessing whether structural MRI features could improve the capacity of machine learning algorithms applied to plasma biomarkers to identify Aβ positive CU individuals.MethodWe included 344 CU individuals from the ALFA+ study, with available T1w MRI, Aβ PET and plasma measurements for p‐tau181, p‐tau231, and GFAP. We determined the capacity to predict Aβ+ according to PET visual read of plasma biomarkers in combination with clinical data (age, sex, education, MMSE, and APOE genotype) and MRI‐derived measurements. We trained Random Forest classifiers with clinical, clinical and plasma, clinical and MRI; and clinical, plasma and MRI data. The MRI‐selected measurements consisted of Jack’s AD‐signature and the two features best predictive of Aβ+: left‐lat‐inf‐ventricle and left caudal‐anterior‐cingulate as determined with Freesurfer 6.0. We conducted ROC and Precision‐Recall analyses and calculated savings as the percentage difference of costs between standard trial recruitment and a triaging step with the different classifiers. The threshold for positivity prediction was chosen to maximize savings and the precision‐recall ratio. We computed ROC‐AUC, PPV, sensitivity and savings as metrics for the comparison.ResultsThe mean centiloid values of Aβ+ subjects (13.66%) and Aβ‐ were 33.73 and ‐1.82, respectively (Table 1). ROC‐AUCs for the classifiers to detect Aβ+ was 0.723 for clinical information; 0.861 for clinical and plasma measurements; 0.711 for clinical and MRI; and 0.871 for clinical, plasma and MRI. Savings associated with the best classifier (clinical + plasma + MRI) would translate in savings (95%CI) of 52.8% (49.0, 56.3) in recruitment costs. See Figure 1 for all the metrics’ results.ConclusionMachine learning algorithms on plasma biomarkers achieved a high accuracy on predicting a positive visual read on amyloid PET scans in cognitively unimpaired individuals. MRI biomarkers marginally improved the predictive capacity. Used as a triaging method, such an algorithm would result in a reduction of over 50% in the cost to identify participants for secondary prevention trials.