arXiv subjects

Jiheum Park

Publications and source records attributed to Jiheum Park.

3 recordsLinked to original sources

arXiv2026

Population-Specific Genetic and Non-Genetic Influences on Sleep Traits and Health Outcomes

Sleep traits are shaped by genetic and environmental factors and may influence many health conditions. The All of Us Research Program, which includes EHR, physical measurements, genomic data, and wearable data across ancestry groups, provides an opportunity to study genetic and non-genetic contributors to sleep-related health outcomes. We examined associations between genetic predispositions to chronotype, sleep duration, and short sleep and health outcomes across ancestries, as well as the role of measured sleep duration. We used All of Us genome-wide association study results, including ancestry-specific and meta-analyses for 3,414 phenotypes, to identify phenotypes associated with 455 sleep-related SNPs. Cross-sectional and longitudinal analyses (n = 212,529) evaluated associations between polygenic risk scores (PRS) and anthropometric and metabolic measures from EHR. A subgroup analysis (n = 7,655) assessed sleep duration using Fitbit data. Across six ancestry groups, SNP analysis identified 61 phenotypes linked to 29 sleep-trait-associated SNPs. The chronotype SNP rs1421085 in FTO showed the strongest associations with obesity, diabetes, and cardiovascular conditions, mainly in European, American, and African groups. PRS analysis showed that higher predisposition to shorter sleep duration was associated with increased risk of obesity and diabetes, with ancestry-specific variation. Measured sleep duration attenuated these associations, with relative contributions of 85.6%-99.9% in cross-sectional analyses and 7.1%-44.0% in longitudinal analyses compared with PRS. This study identified health conditions associated with genetic predispositions to sleep traits and suggests that actual sleep duration may play a prominent role in sleep-related health outcomes. Differences among meta-, pooled-, and ancestry-specific analyses highlight the importance of population-specific research.

q-bio.GN↗

arXiv2026

Toward Scalable Early Cancer Detection: Evaluating EHR-Based Predictive Models Against Traditional Screening Criteria

Current cancer screening guidelines cover only a few cancer types and rely on narrowly defined criteria such as age or a single risk factor like smoking history, to identify high-risk individuals. Predictive models using electronic health records (EHRs), which capture large-scale longitudinal patient-level health information, may provide a more effective tool for identifying high-risk groups by detecting subtle prediagnostic signals of cancer. Recent advances in large language and foundation models have further expanded this potential, yet evidence remains limited on how useful EHR-based models are compared with traditional risk factors currently used in screening guidelines. We systematically evaluated the clinical utility of EHR-based predictive models against traditional risk factors, including gene mutations and family history of cancer, for identifying high-risk individuals across eight major cancers (breast, lung, colorectal, prostate, ovarian, liver, pancreatic, and stomach), using data from the All of Us Research Program, which integrates EHR, genomic, and survey data from over 865,000 participants. Even with a baseline modeling approach, EHR-based models achieved a 3- to 6-fold higher enrichment of true cancer cases among individuals identified as high risk compared with traditional risk factors alone, whether used as a standalone or complementary tool. The EHR foundation model, a state-of-the-art approach trained on comprehensive patient trajectories, further improved predictive performance across 26 cancer types, demonstrating the clinical potential of EHR-based predictive modeling to support more precise and scalable early detection strategies.

cs.LG↗

arXiv2025

CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records

Electronic Health Records (EHRs) provide a rich, longitudinal view of patient health and hold significant potential for advancing clinical decision support, risk prediction, and data-driven healthcare research. However, most artificial intelligence (AI) models for EHRs are designed for narrow, single-purpose tasks, limiting their generalizability and utility in real-world settings. Here, we present CEHR-XGPT, a general-purpose foundation model for EHR data that unifies three essential capabilities - feature representation, zero-shot prediction, and synthetic data generation - within a single architecture. To support temporal reasoning over clinical sequences, CEHR-XGPT incorporates a novel time-token-based learning framework that explicitly encodes patients' dynamic timelines into the model structure. CEHR-XGPT demonstrates strong performance across all three tasks and generalizes effectively to external datasets through vocabulary expansion and fine-tuning. Its versatility enables rapid model development, cohort discovery, and patient outcome forecasting without the need for task-specific retraining.

cs.LG↗