Why Inclusion Matters for Alzheimer’s Disease Biomarker Discovery in Plasma

Abstract

Background: African American/Black adults have a disproportionate incidence of Alzheimer’s disease (AD) and are underrepresented in biomarker discovery efforts. Objective: This study aimed to identify potential diagnostic biomarkers for AD using a combination of proteomics and machine learning approaches in a cohort that included African American/Black adults. Methods: We conducted a discovery-based plasma proteomics study on plasma samples (N = 113) obtained from clinically diagnosed AD and cognitively normal adults that were self-reported African American/Black or non-Hispanic White. Sets of differentially-expressed proteins were then classified using a support vector machine (SVM) to identify biomarker candidates. Results: In total, 740 proteins were identified of which, 25 differentially-expressed proteins in AD came from comparisons within a single racial and ethnic background group. Six proteins were differentially-expressed in AD regardless of racial and ethnic background. Supervised classification by SVM yielded an area under the curve (AUC) of 0.91 and accuracy of 86%for differentiating AD in samples from non-Hispanic White adults when trained with differentially-expressed proteins unique to that group. However, the same model yielded an AUC of 0.49 and accuracy of 47%for differentiating AD in samples from African American/Black adults. Other covariates such as age, APOE4 status, sex, and years of education were found to improve the model mostly in the samples from non-Hispanic White adults for classifying AD. Conclusion: These results demonstrate the importance of study designs in AD biomarker discovery, which must include diverse racial and ethnic groups such as African American/Black adults to develop effective biomarkers.

What Influences the Willingness of Blacks and African Americans to Enroll in Preclinical Alzheimer’s Disease Biomarker Research? A Qualitative Vignette Analysis

“…The limited inclusiveness of biomarker study samples raises concerns about the validity and reliability of biomarker data in underrepresented groups [ 19 ]. Data shows that biomarker changes in AD can vary between Black/African American and White populations, and similar biomarker profiles can be associated with divergent cognitive function [ 20, 21 ].…”

Transcript levels in plasma contribute substantial predictive value as potential Alzheimer's disease biomarkers in African Americans

“…A few studies have evaluated in an AA cohort the use of plasma proteins or metabolites as a fluid biomarker for AD, but none of these have evaluated plasma cf-mRNAs. 9 , 39 , 40 , 41 , 42 , 43 Future studies should systematically evaluate the biomarker potential of all transcripts detectable in plasma in diverse populations and incorporate these plasma cf-RNAs into a biomarker panel along with plasma levels of proteins and metabolites that have been shown to effectively discriminate AD from CU and other types of dementias, such as Aß42/Aß40 ratio and p-tau, in order to achieve greater discriminatory potential and add theragnostic value.…”

Improved Discrimination of Disease States Using Proteomics Data with the Updated Aristotle Classifier

“…The combination of machine learning and mass spectrometry is burgeoning and offering new opportunities for disease diagnosis. In one example, the combination of clinical features and proteomics data of plasma samples from Alzheimer’s patients effectively predicted Alzheimer’s disease using a Support Vector Machine (SVM) classifier; the performance strongly depended on the patient’s race, reiterating the importance of including patients of different racial backgrounds in omics data sets . Machine learning and omics data have also been used to identify leukemia in children with 90% accuracy by combining the supervised classification tool, XGBoost, with LC–MS data quantifying amino acids .…”

“…More recent supervised classification strategies that leverage the power and speed of modern computing, including Support Vector Machine (SVM) and decision tree-based classifiers, such as XGBoost, show even greater promise for omics researchers over these older methods. In several examples of studies using mass spectrometry data, SVM was the method of choice for performing supervised classification; , this approach outperformed methods such as linear discriminant analysis and partial least-squares discriminant analysis on multiple proteomics data sets. , Decision-tree-based classifiers, including Random Forest, boosted decision trees, and XGBoost, have shown similar promise for accurate classification of omics data. ,, The development of new and better classifiers provides new opportunities to do a better job of supervised classification, which translates into an enhanced ability to discriminate disease and ultimately improve health outcomes.…”

“…Replacing missing data with zeros is not a good choice, as the reason the data are missing is often not because the peptide of interest has no abundance, but rather because the entire group of samples with which it was mixed did not trigger an MS/MS experiment for that peptide. When using SVM for proteomics data, one effective choice in dealing with missing data is to calculate the average of all of the training data for that particular feature and to use that value in place of the missing one . In principle, this approach is also necessarily flawed as there is no reason why the peak with missing data would be equivalent to the average of the training data.…”