Citations

Background. Rare diseases collectively affect an estimated 300 million people worldwide, yet patients wait an average of 4-8 years for a correct diagnosis after visiting multiple physicians, accumulating unexplained findings, and suffering preventable disease progression before a unifying diagnosis is reached. Electronic health records (EHRs) capture this pre-diagnostic trajectory in rich detail, but conventional methods typically collapse years of longitudinal phenotypic signals into a single static snapshot; our approach instead models this temporal structure directly. Methods. We conducted a retrospective cohort study using longitudinal EHR data from approximately 3 million patients at Mayo Clinic Platform_Accelerate. Cases were patients with confirmed diagnoses of 10 rare diseases; controls (~5,200 per disease) had no record of any rare disease. HPO phenotype terms were extracted from clinical notes and laboratory results using a medspaCy NLP pipeline; ICD codes were grouped at three-character level. We developed and trained two temporal models, GRU-Attn and Conformer, that encode patient histories as quarterly time-binned sequences spanning up to 30 years, and compared these against three static baselines (CatBoost, XGBoost, logistic regression). Models were evaluated systematically at prediction horizons h = 1-10 years before diagnosis. Results. In the full held-out cohort benchmark, temporal models outperformed static baselines across the large majority of diseases and prediction horizons, with the advantage widening substantially as the horizon lengthened. At 1-2 years prior to diagnosis, mean AUROC was 0.928 (GRU-Attn) versus 0.871 (CatBoost); at 6-10 years prior to diagnosis, 0.726 versus 0.693, with static models degrading to near-chance for some diseases. Combining HPO and ICD features yielded the strongest performance, with a mean gain of +0.063 AUROC over the best single source at 1-2 years prior to diagnosis. Separately, in a manually curated cohort of 143 confirmed-undiagnosed cases with extended EHR histories, GRU-Attn identified 138 cases before first disease mention and all 143 cases before formal diagnosis at the prespecified 99th-percentile specificity threshold, with median lead times of 1.1-8.3 years and 1.9-21.7 years, respectively. Conclusions. By learning from the temporal trajectory of phenotypic signals rather than their static aggregate, temporal EHR models improved retrospective early detection performance across several rare diseases, most powerfully for conditions where pre-diagnostic findings accrue gradually and heterogeneously over years. These results show that longitudinal EHR trajectories carry rare-disease signal beyond static phenotypic burden and support prospective evaluation of temporal EHR modeling for rare-disease risk stratification.

Background Subjective cognitive decline (SCD) is a preclinical condition associated with an increased risk of dementia and Alzheimer’s disease, with no consensus regarding effective therapeutic interventions to date. As the global burden of aging-related neurodegenerative diseases continues to rise, early intervention has become increasingly critical. Cognitive training has been proposed as a promising behavioral intervention; however, few studies have integrated multimodal assessments to elucidate its underlying neurobiological and psychological mechanisms, particularly within the educational system that shapes cognitive reserve and learning strategies across the lifespan. This pilot study aims to estimate effect sizes for future definitive trials, assess the feasibility and acceptability of the intervention and multimodal evaluations, and generate hypotheses regarding the relationship between recitation practice and clinical biomarkers. Methods A total of 60 individuals with subjective cognitive decline will be enrolled in a randomized, assessor-blinded, controlled pilot study. Participants will be randomly assigned to either an intervention group or a non-active control group prior to baseline assessment. The intervention group will undergo a six-month structured recitation training program. Both groups will undergo short-term follow-up after the intervention, and long-term follow-up annually post-intervention. Multimodal assessments will include neuropsychological testing, functional magnetic resonance imaging (fMRI), electroencephalography (EEG), blood biomarker profiling, gut microbiota analysis, and fecal metabolomics. Discussion This study protocol outlines a randomized, assessor-blinded, controlled pilot study designed to advance understanding of the feasibility of Chinese Classics recitation training on both physiological and psychological outcomes in individuals with subjective cognitive decline. The findings are expected to provide mechanistic insights into non-pharmacological interventions and to address the current underrepresentation of Asian populations in neuroscience research. Clinical trial registration We registered this randomized controlled trial on ClinicalTrials.gov on March 11, 2026, under the identifier NCT07463391.

Abstract Heterogeneous treatment effects (HTE) are key to precision medicine, but most real-world studies lack the scale and diversity needed to detect them. While multi-site analyses offer a potential solution, data-sharing constraints often prevent access to patient-level information across institutions. We introduce POLARIS, a federated framework for time-to-event target trial emulation. POLARIS converts each site’s weighted Cox risk function into a compact tensor shared once with the coordinating center, enabling lossless reproduction of pooled estimates without sharing patient-level data. We applied POLARIS across five U.S. health systems to study risk of gastrointestinal outcomes after GLP-1 receptor agonist (GLP-1RAs) initiation versus sodium-glucose cotransporter 2 inhibitors (SGLT2is) and dipeptidyl peptidase 4 inhibitors (DPP4is). Results showed that GLP-1RAs were consistently associated with higher risks of nausea and vomiting, particularly among men, individuals with higher baseline HbA1c (≥ 8.5%), and lipid therapy. POLARIS provides a scalable solution for distributed target trial emulation and fine-grained assessment of HTE across diverse health systems.

Early allograft failure (EAF) after living donor liver transplantation (LDLT) remains a clinical challenge. Existing prediction models developed for deceased donor transplantation poorly apply to LDLT due to distinct surgical and physiological factors. This study identifies clinical determinants of EAF and develops an LDLT-specific prediction model. We conducted a multicenter retrospective cohort study from 17 high-volume LDLT centers (January 2016–December 2020) with external validation at a tertiary center in Saudi Arabia (January 2015–December 2022). The primary outcome was EAF (graft loss or patient death ≤90 d). Multivariable mixed-effects logistic regression identified preoperative/intraoperative risk factors. The EAGLE-LDLT model was constructed using postoperative laboratory values. Performance was compared against established models (EAD, MEAF, A2ALL) using ROC analysis and decision curve analysis. The development cohort included 2944 adult LDLT recipients (67.7% male; median age 55 y; median MELD 14) with a 5.5% EAF rate. External validation included 1020 recipients (median MELD 21, 6.7% EAF). Independent risk factors for EAF were MELD (OR 1.06, 95% CI 1.04–1.08), donor BMI (OR 1.05, 95% CI 1.00–1.10), portal vein thrombosis (OR 1.73, 95% CI 1.13–2.63), and hepaticojejunostomy (OR 1.58, 95% CI 1.06–2.36). The EAGLE-LDLT model incorporating peak ALT (>468 U/L), peak INR (>1.9), and bilirubin (>3.5 mg/dL) and INR (>1.3) at POD7, demonstrated superior discrimination (AUC=0.81) compared with MEAF (AUC=0.77, p =0.004), EAD (AUC=0.67, p <0.001), and A2ALL (AUC=0.65, p <0.001). EAGLE-LDLT achieved balanced sensitivity (75.0%) and specificity (73.7%), effectively stratifying patients into high-risk (15% of patients; 40.4% EAF incidence) and low-risk groups. Preoperative and intraoperative clinical factors predict EAF in LDLT. The EAGLE-LDLT model accurately identifies LDLT recipients at the highest risk for EAF postoperatively.

Importance Monoclonal gammopathy of undetermined significance (MGUS) is associated with an increased risk of cardiovascular disease. Glucagon-like peptide-1 (GLP-1) receptor agonists (RAs) have demonstrated cardiorenal benefits in patients with type 2 diabetes, but their effectiveness in patients with MGUS remains unexplored. Objective To assess the effectiveness of GLP-1 RAs for primary prevention of major adverse cardiovascular and cerebrovascular events (MACCE) in patients with MGUS and diabetes. Design, Setting, and Participants This retrospective cohort study used a propensity score–matched analysis of data from the TriNetX Global Database, encompassing patients diagnosed with diabetes and MGUS between January 1, 2018, and January 13, 2023. Patients with prior heart failure (HF), ischemic heart disease, coronary revascularization, or stroke or transient ischemic attack before MGUS diagnosis were excluded. The cohort was divided into 2 groups: GLP-1 RA users and nonusers at baseline. After 1:1 propensity score matching, GLP-1 RA users and nonusers were compared up to 5 years from the MGUS diagnosis date. Data analyses were completed January 19, 2025. Exposure GLP-1 RA use within 1 year before MGUS diagnosis. Main Outcomes and Measures The primary end point was MACCE, defined as a composite of all-cause mortality, new-onset HF, acute coronary syndrome, and stroke or transient ischemic attack. Secondary end points included individual MACCE components, decompensated HF, and acute kidney injury or end-stage kidney disease. Results A total of 4871 patients with MGUS (mean [SD] age, 68.9 [10.1] years; 2366 [48.5%] male) were included (473 GLP-1 RA users and 4398 non-users). A total of 460 users were matched to 460 nonusers, with balanced characteristics (mean [SD] age, 65.0 [10.6] vs 65.1 [11.0] years; 229 [49.7%] male vs 234 [50.8%] male), including 14 patients (3.0%) vs 13 patients (2.8%) identifying as Asian, 8 (21.3%) vs 92 (20.0%) as Black or African American, 25 patients (5.4%) vs 20 patients (4.3%) as Hispanic or Latino, and 243 patients (52.8%) vs 250 patients (54.3%) as White. GLP-1 RA use was associated with a significantly lower risk of MACCE (hazard ratio [HR], 0.75; 95% CI, 0.60-0.93). Significant reductions were also observed in all-cause mortality (HR, 0.57; 95% CI, 0.37-0.87), new-onset HF (HR, 0.69; 95% CI, 0.54-0.90), decompensated HF (HR, 0.60; 95% CI, 0.43-0.84), and acute kidney injury or end-stage kidney disease (HR, 0.73; 95% CI, 0.57-0.92). Conclusions and Relevance The findings of this cohort study of GLP-1 RA use vs no use in patients with MGUS and diabetes suggest the potential of GLP-1 RA for primary prevention of MACCE. These findings warrant further investigation in prospective randomized trials.