Machine Learning Models of Polygenic Risk for Enhanced Prediction of Alzheimer Disease Endophenotypes

Background and Objectives

Alzheimer disease (AD) has a polygenic architecture, for which genome-wide association studies (GWAS) have helped elucidate sequence variants (SVs) influencing susceptibility. Polygenic risk score (PRS) approaches show promise for generating summary measures of inherited risk for clinical AD based on the effects of APOE and other GWAS hits. However, existing PRS approaches, based on traditional regression models, explain only modest variation in AD dementia risk and AD-related endophenotypes. We hypothesized that machine learning (ML) models of polygenic risk (ML-PRS) could outperform standard regression-based PRS methods and therefore have the potential for greater clinical utility.

Methods

We analyzed combined data from the Mayo Clinic Study of Aging (n = 1,791) and the Alzheimer's Disease Neuroimaging Initiative (n = 864). An AD PRS was computed for each participant using the top common SVs obtained from a large AD dementia GWAS. In parallel, ML models were trained using those SV genotypes, with amyloid PET burden as the primary outcome. Secondary outcomes included amyloid PET positivity and clinical diagnosis (cognitively unimpaired vs impaired). We compared performance between ML-PRS and standard PRS across 100 training sessions with different data splits. In each session, data were split into 80% training and 20% testing, and then five-fold cross-validation was used within the training set to ensure the best model was produced for testing. We also applied permutation importance techniques to assess which genetic factors contributed most to outcome prediction.

Results

ML-PRS models outperformed the AD PRS (r2 = 0.28 vs r2 = 0.24 in test set) in explaining variation in amyloid PET burden. Among ML approaches, methods accounting for nonlinear genetic influences were superior to linear methods. ML-PRS models were also more accurate when predicting amyloid PET positivity (area under the curve [AUC] = 0.80 vs AUC = 0.63) and the presence of cognitive impairment (AUC = 0.75 vs AUC = 0.54) compared with the standard PRS.

Discussion

We found that ML-PRS approaches improved upon standard PRS for prediction of AD endophenotypes, partly related to improved accounting for nonlinear effects of genetic susceptibility alleles. Further adaptations of the ML-PRS framework could help to close the gap of remaining unexplained heritability for AD and therefore facilitate more accurate presymptomatic and early-stage risk stratification for clinical decision-making.

Cerebrospinal fluid dynamics disorders: Relationship to Alzheimer biomarkers and cognition

OBJECTIVE

To determine the frequency of high-convexity tight sulci (HCTS) in a population-based sample and whether the presence of HCTS and related features influenced participants' cognitive status and classification within the new Alzheimer-biomarker framework.

METHODS

We analyzed 684 participants ≥50 years of age who were enrolled in the prospective population-based Mayo Clinic Study of Aging and underwent structural MRI, amyloid PET imaging, and tau PET imaging. A fully automated machine-learning algorithm that had been developed previously in house was used to detect neuroimaging features of HCTS. On the basis of PET and MRI measures, participants were classified as having normal (A^-) or abnormal (A⁺) amyloid, normal (T^-) or abnormal (T⁺) tau, and normal (N^-) or abnormal (N⁺) neurodegeneration. The neuropsychological battery assessed domain-specific and global cognitive scores. Gait speed also was assessed. Analyses were adjusted for age and sex.

RESULTS

Of 684 participants, 45 (6.6%) were classified with HCTS according to the automated algorithm. Patients with HCTS were older than patients without HCTS (mean [SD] 78.0 [8.3] vs 71.9 [10.8] years; p < 0.001). More were cognitively impaired after age and sex adjustment (27% vs 9%; p = 0.005). Amyloid PET status was similar with and without HCTS, but tau PET standard uptake value ratio (SUVR) was lower for those with HCTS after age and sex adjustment (p < 0.001). Despite a lower tau SUVR, patients with HCTS had lower Alzheimer disease (AD) signature cortical thickness. With the amyloid-tau-neurodegeneration framework, HCTS was overrepresented in the T^-(N)⁺ group, regardless of amyloid status.

CONCLUSION

The HCTS pattern represents a definable subgroup of non-AD pathophysiology (i.e., T^-[N]⁺) that is associated with cognitive impairment. HCTS may confound clinical and biomarker interpretation in AD clinical trials.

Automated detection of imaging features of disproportionately enlarged subarachnoid space hydrocephalus using machine learning methods

OBJECTIVE

Create an automated classifier for imaging characteristics of disproportionately enlarged subarachnoid space hydrocephalus (DESH), a neuroimaging phenotype of idiopathic normal pressure hydrocephalus (iNPH).

METHODS

1597 patients from the Mayo Clinic Study of Aging (MCSA) were reviewed for imaging characteristics of DESH. One core feature of DESH, the presence of tightened sulci in the high-convexities (THC), was used as a surrogate for the presence of DESH as the expert clinician-defined criterion on which the classifier was trained. Anatomical MRI scans were automatically segmented for cerebrospinal fluid (CSF) and overlaid with an atlas of 123 named sulcal regions. The volume of CSF in each sulcal region was summed and normalized to total intracranial volume. Area under the receiver operating characteristic curve (AUROC) values were computed for each region individually, and these values determined feature selection for the machine learning model. Due to class imbalance in the data (72 selected scans out of 1597 total scans) adaptive synthetic sampling (a technique which generates synthetic examples based on the original data points) was used to balance the data. A support vector machine model was then trained on the regions selected.

RESULTS

Using the automated classification model, we were able to classify scans for tightened sulci in the high convexities, as defined by the expert clinician, with an AUROC of about 0.99 (false negative ≈ 2%, false positive ≈ 5%). Ventricular volumes were among the classifier's most discriminative features but are not specific for DESH. The inclusion of regions outside the ventricles allowed specificity from atrophic neurodegenerative diseases that are also accompanied by ventricular enlargement.

CONCLUSION

Automated detection of tight high convexity, a key imaging feature of DESH, is possible by using support vector machine models with selected sulcal CSF volumes as features.