Machine Learning models for detection and assessment of progression in Alzheimer's disease based on blood and cerebrospinal fluid biomarkers

Saturnino Luz, Fasih Haider, Paul De Sousa

Abstract: Machine-learning techniques were applied to human blood plasma and cerebrospinal fluid (CSF) biomarker data related to cognitive decline in Alzheimer’s Disease (AD) patients available via Alzheimer Disease Neuroimaging Initiative (ADNI) study. We observed the accuracy of AD diagnosis is greatest when protein biomarkers from cerebrospinal fluid are combined with plasma proteins using Support Vector Machines (SVM); this is not improved by adding age and sex. The area under the receiver operator characteristic (ROC) curve for our model of AD diagnosis based on a full (unbiased) set of plasma proteins was 0.94 in cross-validation and 0.82 on an external validation (test) set. Taking plasma in combination with CSF, the model reaches 0.98 area under the ROC curve on the test set. Accuracy of prediction of risk of mild cognitive impairment progressing to AD is the same for blood plasma biomarkers as for CSF and is not improved by combining them or adding age and sex as covariates.Clinical relevance— The identification of accurate and cost-effective biomarkers to screen for risk of developing AD and monitoring its progression is crucial for improved understanding of its causes and stratification of patients for treatments under development. This paper demonstrates the feasibility of AD detection and prognosis based on blood plasma biomarkers.