Genetic risk modeling for dementia offers significant benefits, but studies based on real-world data, particularly for underrepresented populations, are limited. We employ an Elastic Net model for dementia risk prediction using single-nucleotide polymorphisms prioritized by functional genomic data from multiple neurodegenerative disease genome-wide association studies. We compare this model with APOE and polygenic risk score models across genetic ancestry groups (Hispanic Latino American sample: 610 patients with 126 cases; African American sample: 440 patients with 84 cases; East Asian American sample: 673 patients with 75 cases), using electronic health records from UCLA Health for discovery and the All of Us cohort for validation. Our model significantly outperforms other models across multiple ancestries, improving the area-under-precision-recall curve by 31-84% (Wilcoxon signed-rank test p-value <0.05) and the area-under-the-receiver-operating characteristic by 11-17% (DeLong test p-value <0.05) compared to the APOE and the polygenic risk score models. We identify shared and ancestry-specific risk genes and biological pathways, reinforcing and adding to existing knowledge. Our study highlights the benefits of integrating functional mapping, multiple neurodegenerative diseases, and machine learning for genetic risk models in diverse populations. Our findings hold potential for refining precision medicine strategies in dementia diagnosis.

Alzheimer's disease (AD) is the most common form of dementia and a growing public health burden in the United States. Significant progress has been made in identifying genetic risk for AD, but limited studies have investigated how AD genetic risk may be associated with other disease conditions in an unbiased fashion. In this study, we conducted a phenome-wide association study (PheWAS) by genetic ancestry groups within a large academic health system using the polygenic risk score (PRS) for AD. PRS was calculated using LDpred2 with genome-wide association study (GWAS) summary statistics. Phenotypes were extracted from electronic health record (EHR) diagnosis codes and mapped to more clinically meaningful phecodes. Logistic regression with Firth's bias correction was used for PRS phenotype analyses. Mendelian randomization was used to examine causality in significant PheWAS associations. Our results showed a strong association between AD PRS and AD phenotype in European ancestry (OR = 1.26, 95% CI: 1.13, 1.40). Among a total of 1,515 PheWAS tests within the European sample, we observed strong associations of AD PRS with AD and related phenotypes, which include mild cognitive impairment (MCI), memory loss, and dementias. We observed a phenome-wide significant association between AD PRS and gouty arthropathy (OR = 0.90, adjusted p = 0.05). Further causal inference tests with Mendelian randomization showed that gout was not causally associated with AD. We concluded that genetic predisposition of AD was negatively associated with gout, but gout was not a causal risk factor for AD. Our study evaluated AD PRS in a real-world EHR setting and provided evidence that AD PRS may help to identify individuals who are genetically at risk of AD and other related phenotypes. We identified non-neurodegenerative diseases associated with AD PRS, which is essential to understand the genetic architecture of AD and potential side effects of drugs targeting genetic risk factors of AD. Together, these findings expand our understanding of AD genetic and clinical risk factors, which provide a framework for continued research in aging with the growing number of real-world EHR linked with genetic data.

Lung cancer screening (LCS) is effective in reducing mortality, particularly when patients adhere to follow-up recommendations standardized by the Lung CT Screening Reporting & Data System (Lung-RADS). Nevertheless, patient adherence to recommended intervals varies, potentially diminishing benefit from screening. We conducted a systematic review and meta-analysis of patient adherence to Lung-RADS-recommended screening intervals. We systematically searched MEDLINE, EMBASE, Web of Science, the Cochrane Central Register of Controlled Trials, and major radiology and oncology conference archives between April 28, 2014, and December 17, 2020. Eligible studies mentioned patient adherence to the recommendations of Lung-RADS. The review protocol was registered with PROSPERO (CRD42020189326). We identified 24 eligible studies for qualitative summary, of which 21 were suitable for meta-analysis. The pooled adherence rate was 57% (95% confidence interval: 46%-69%) for defined adherence (e.g., an annual incidence screen was performed within 15 mo) among 6689 patients and 65% (95% confidence interval: 55%-75%) for anytime adherence among 5085 patients. Large heterogeneity in adherence rates between studies was observed (I² = 99% for defined adherence, I² = 98% for anytime adherence). Heterogeneous adherence rates were associated with Lung-RADS scores, with significantly higher adherence rates among Lung-RADS 3 to 4 than Lung-RADS 1 to 2 (p < 0.05). Patient adherence to Lung-RADS-recommended screening intervals is suboptimal across clinical LCS programs in the United States, especially among patients with results of Lung-RADS categories 1 to 2. To improve adherence rates, future research may focus on implementing tailored interventions after identifying barriers to LCS. We also propose a minimum standardized set of data elements for future pooled analyses of LCS adherence on the basis of our findings.

We present a deep-learning-based platform, MIND-S, for protein post-translational modification (PTM) predictions. MIND-S employs a multi-head attention and graph neural network and assembles a 15-fold ensemble model in a multi-label strategy to enable simultaneous prediction of multiple PTMs with high performance and computation efficiency. MIND-S also features an interpretation module, which provides the relevance of each amino acid for making the predictions and is validated with known motifs. The interpretation module also captures PTM patterns without any supervision. Furthermore, MIND-S enables examination of mutation effects on PTMs. We document a workflow, its applications to 26 types of PTMs of two datasets consisting of ∼50,000 proteins, and an example of MIND-S identifying a PTM-interrupting SNP with validation from biological data. We also include use case analyses of targeted proteins. Taken together, we have demonstrated that MIND-S is accurate, interpretable, and efficient to elucidate PTM-relevant biological processes in health and diseases.