Identifying probable dementia in undiagnosed Black and White Americans using machine learning in Veterans Health Administration electronic health records.

The application of machine learning (ML) tools in electronic health records (EHRs) can help reduce the underdiagnosis of dementia, but models that are not designed to reflect minority population may perpetuate that underdiagnosis. To address the underdiagnosis of dementia in both Black Americans (BAs) and white Americans (WAs), we sought to develop and validate ML models that assign race-specific risk scores. These scores were used to identify undiagnosed dementia in BA and WA Veterans in EHRs. More specifically, risk scores were generated separately for BAs (n=10K) and WAs (n=10K) in training samples of cases and controls by performing ML, equivalence mapping, topic modeling, and a support vector-machine (SVM) in structured and unstructured EHR data. Scores were validated via blinded manual chart reviews (n=1.2K) of controls from a separate sample (n=20K). AUCs and negative and positive predictive values (NPVs and PPVs) were calculated to evaluate the models. There was a strong positive relationship between SVM-generated risk scores and undiagnosed dementia. BAs were more likely than WAs to have undiagnosed dementia per chart review, both overall (15.3% vs 9.5%) and among Veterans with >90th percentile cutoff scores (25.6% vs 15.3%). With chart reviews as the reference standard and varied cutoff scores, the BA model performed slightly better than the WA model (AUC=0.86 with NPV=0.98 and PPV=0.26 at >90th percentile cutoff vs AUC=0.77 with NPV=0.98 and PPV=0.15 at >90th). The AUCs, NPVs, and PPVs suggest that race-specific ML models can assist in the identification of undiagnosed dementia, particularly in BAs. Future studies should investigate implementing EHR-based risk scores in clinics that serve both BA and WA Veterans.

Evaluating and Improving Cancer Screening Process Quality in a Multilevel Context: The PROSPR II Consortium Design and Research Agenda.

BACKGROUND: Cancer screening is a complex process involving multiple steps and levels of influence (e.g., patient, provider, facility, health care system, community, or neighborhood). We describe the design, methods, and research agenda of the Population-based Research to Optimize the Screening Process (PROSPR II) consortium. PROSPR II Research Centers (PRC), and the Coordinating Center aim to identify opportunities to improve screening processes and reduce disparities through investigation of factors affecting cervical, colorectal, and lung cancer screening in U.S. community health care settings. METHODS: We collected multilevel, longitudinal cervical, colorectal, and lung cancer screening process data from clinical and administrative sources on >9 million racially and ethnically diverse individuals across 10 heterogeneous health care systems with cohorts beginning January 1, 2010. To facilitate comparisons across organ types and highlight data breadth, we calculated frequencies of multilevel characteristics and volumes of screening and diagnostic tests/procedures and abnormalities. RESULTS: Variations in patient, provider, and facility characteristics reflected the PROSPR II health care systems and differing target populations. PRCs identified incident diagnoses of invasive cancers, in situ cancers, and precancers (invasive: 372 cervical, 24,131 colorectal, 11,205 lung; in situ: 911 colorectal, 32 lung; precancers: 13,838 cervical, 554,499 colorectal). CONCLUSIONS: PROSPR II's research agenda aims to advance: (i) conceptualization and measurement of the cancer screening process, its multilevel factors, and quality; (ii) knowledge of cancer disparities; and (iii) evaluation of the COVID-19 pandemic's initial impacts on cancer screening. We invite researchers to collaborate with PROSPR II investigators. IMPACT: PROSPR II is a valuable data resource for cancer screening researchers.

Redefining transcriptional regulation of the APOE gene and its association with Alzheimer's disease.

The apolipoprotein E gene (APOE) is the strongest genetic risk factor for late-onset Alzheimer's disease (AD), yet the expression of APOE is not clearly understood. For example, it is unclear whether AD patients have elevated or decreased APOE expression or why the correlation levels of APOE RNA and the ApoE protein differ across studies. Likewise, APOE has a single CpG island (CGI) that overlaps with its 3'-exon, and this CGI's effect is unknown. We previously reported that the APOE CGI is highly methylated in human postmortem brain (PMB) and that this methylation is altered in AD frontal lobe. In this study, we comprehensively characterized APOE RNA transcripts and correlated levels of RNA expression with DNA methylation levels across the APOE CGI. We discovered the presence of APOE circular RNA (circRNA) and found that circRNA and full-length mRNA each constitute approximately one third of the total APOE RNA, with truncated mRNAs likely constituting some of the missing fraction. All APOE RNA species demonstrated significantly higher expression in AD frontal lobe than in control frontal lobe. Furthermore, we observed a negative correlation between the levels of total APOE RNA and DNA methylation at the APOE CGI in the frontal lobe. When stratified by disease status, this correlation was strengthened in controls but not in AD. Our findings suggest a possible modified mechanism of gene action for APOE in AD that involves not only the protein isoforms but also an epigenetically regulated transcriptional program driven by DNA methylation in the APOE CGI.

Emerging cerebrospinal fluid biomarkers in autosomal dominant Alzheimer's disease.

INTRODUCTION: Four less well-studied but promising "emerging" cerebrospinal fluid (CSF) biomarkers are elevated in late-onset Alzheimer disease (AD): neurogranin, synaptosomal-associated protein-25 (SNAP-25), visinin-like protein 1 (VILIP-1), and chitinase-3-like protein 1 (YKL-40). METHODS: CSF neurogranin, SNAP-25, VILIP-1, and YKL-40 were measured in families carrying autosomal-dominant AD mutations. RESULTS: The four emerging CSF biomarkers were significantly elevated in the mutation carriers (n = 235) versus noncarriers (n = 145). CSF SNAP-25, VILIP-1, and YKL-40 were altered very early in the AD time course, approximately 15-19 years before estimated symptom onset. All CSF biomarkers predicted important AD-related outcomes including performance on a cognitive composite, brain amyloid burden as measured by amyloid positron emission tomography, and the estimated years from symptom onset. DISCUSSION: Early abnormalities in CSF tTau, pTau, SNAP-25, VILIP-1, and YKL-40 suggest that synaptic damage, neuronal injury, and neuroinflammation begin shortly after the commencement of brain amyloid accumulation.

DNA methylation of TOMM40-APOE-APOC2 in Alzheimer's disease.

The apolipoprotein E (APOE) ε4 allele is the major genetic risk factor for Alzheimer's disease (AD). Multiple regulatory elements, spanning the extended TOMM40-APOE-APOC2 region, regulate gene expression at this locus. Regulatory element DNA methylation changes occur under different environmental conditions, such as disease. Our group and others have described an APOE CpG island as hypomethylated in AD, compared to cognitively normal controls. However, little is known about methylation of the larger TOMM40-APOE-APOC2 region. The hypothesis of this investigation was that regulatory element methylation levels of the larger TOMM40-APOE-APOC2 region are associated with AD. The aim was to determine whether DNA methylation of the TOMM40-APOE-APOC2 region differs in AD compared to cognitively normal controls in post-mortem brain and peripheral blood. DNA was extracted from human brain (n = 12) and peripheral blood (n = 67). A methylation array was used for this analysis. Percent methylation within the TOMM40-APOE-APOC2 region was evaluated for differences according to tissue type, disease state, AD-related biomarkers, and gene expression. Results from this exploratory analysis suggest that regulatory element methylation levels within the larger TOMM40-APOE-APOC2 gene region correlate with AD-related biomarkers and TOMM40 or APOE gene expression in AD.

Regulatory region genetic variation is associated with FYN expression in Alzheimer's disease.

Neurofibrillary tangles (NFTs), composed of hyperphosphorylated tau, are a key pathologic feature of Alzheimer's disease (AD). Tau phosphorylation is under the control of multiple kinases and phosphatases, including Fyn. Previously, our group found an association between 2 regulatory single nucleotide polymorphisms in the FYN gene with increased tau levels in the cerebrospinal fluid. In this study, we hypothesized that Fyn expression in the brain is influenced by AD status and genetic content. We found that Fyn protein, but not messenger RNA, levels were increased in AD patients compared to cognitively normal controls and are associated with regulatory region single nucleotide polymorphisms. In addition, the expression of the FYN 3'UTR can decrease expression in multiple cell lines, suggesting this regulatory region plays an important role in FYN expression. Taken together, these data suggest that FYN expression is regulated according to AD status and regulatory region haplotype, and genetic variants may be instrumental in the development of neurofibrillary tangles in AD and other tauopathies.