Summary Background The poor prognosis of cholangiocarcinoma (CCA) is largely driven by rapid, asymptomatic disease progression, which usually results in a late diagnosis in the absence of established screening strategies. An early, cost-effective, and universally applicable risk assessment strategy would therefore be valuable. Methods We developed machine learning (ML) models on prospective, multimodal data from 487,495 UK Biobank (UKB) participants, of whom 649 developed CCA during follow-up. Data from England (80%) were utilised for ML development via five-fold cross-validation, and then all models were tested on withheld data from Scotland, Wales, and Newcastle (20%). Iterative ablation studies reduced inputs from >150 features across demographic data, lifestyle, health records, blood parameters, genomics, and metabolomics to models built on five and ten routinely available clinical parameters. These were externally validated in the Penn Medicine Biobank (PMBB; n = 2638; 28 CCA), All of Us Research Program (AOU; n = 330,433; 362 CCA), Japan Medical Data Centre Claims Database (JMDC; n = 8,425,522; 723 CCA) and TriNetX (n = 728,886; 1592 CCA). Findings We show that ML models integrating biliary-disease associated health records and Gamma glutamyltransferase can stratify risk of future CCA. Evaluation on the UKB test set as well as three independent cohorts revealed robust performance and generalisability across ethnicities. We achieved AUROCs of 0.71 [95% CI: 0.703–0.711], 0.77 [95% CI: 0.764–0.778 ], 0.796 [95% CI: 0.795–0.798] and 0.8 [95% CI: 0.794–0.805] for UKB, PMBB, AOU, and JMDC respectively, with respective AUPRCs of 0.014 [95% CI: 0.009–0.018], 0.042 [95% CI: 0.037–0.048], 0.038 [95% CI: 0.033–0.042] and 0.001 [95% CI: 0.001–0.001]. In AOU, application of the Youden J-optimised threshold yielded a number needed to screen of 79. Separate models for intra- and extrahepatic CCA did not improve performance. In line with the pathophysiology, performance declined for longer intervals between assessment and event. A group-level analysis in the TriNetX cohort revealed hazard ratios of up to 82.5 [95% CI: 26.4–257.96]. We provide extensive interpretability results and release all source codes used to develop the presented models. Interpretation We provide a comprehensive framework for early CCA risk stratification in the general population, identifying key predictors, and demonstrating the potential of data-driven models in personalised screening for hepatobiliary cancer. Funding German Cancer Aid (grant #70115730), Junior Principal Investigator Fellowship programme of RWTH Aachen Excellence strategy.
Felix van Haag, J. Clusmann, Paul-Henry Koop et al.· EBioMedicine· 0 citations
OBJECTIVE
Limited research has assessed prospective associations of systemic inflammatory (GlycA) and immune (complement factor 3 [C3] and 4 [C4]) biomarkers with future cognition in midlife women, who potentially experience worsening inflammation around the menopause transition. We aim to assess the associations of midlife serum GlycA, C3, and C4 with future cognitive performance in women.
METHODS
Serum GlycA, C3, and C4 were repeatedly measured over 6.1 ± 3.9 years in 503 midlife women (1,234 observations) from the Study of Women's Health Across the Nation high-density lipoprotein ancillary study. Longitudinal measures of working memory, processing speed, and episodic memory, immediate and delayed recall, were administered 1.46 ± 0.95 years later. We applied joint models to examine the associations of baseline biomarkers and their changes since baseline with subsequent cognition.
RESULTS
Higher levels of serum GlycA and complement factor 4 at baseline (50.17 ± 2.65 y) were significantly associated with worse working memory and better immediate recall, respectively, over the next decade. Higher baseline complement factor 4 and increases in C3 and C4 since baseline tended to associate with better future immediate and/or delayed recall.
CONCLUSIONS
Higher baseline GlycA, rather than its changes since baseline, was associated with lower future working memory, whereas higher baseline complement factor 4 and increases in C3 and C4 since baseline appeared cognitively protective. Targeting inflammation amelioration and immunity improvement over the menopause transition may provide an open avenue to preserve future cognitive health.
Meiyuzhen Qi, Carol A. Derby, Daniel J. Rader et al.· Menopause· 0 citations
Rare variants in MSH6 and BRCA2 are significantly associated with increased HCC risk, revealing a previously unconfirmed role for DNA repair genes in HCC susceptibility across ancestrally diverse populations and may inform genetic risk stratification and surveillance strategies.
A. Garófalo, Perapa Chotiprasidhi, Josephine P. Johnson et al.· JHEP Reports· 0 citations
This study shows that integrating plasma proteomics with multi-organ imaging provides a comprehensive pan-organ imaging-proteomics map and reveals molecular pathways linking circulating proteins to human organ biology.
Zi-Rui Fan, J. Chirinos, Xiao-Chen Yang et al.· Nature Communications· 0 citations
This study provides the most comprehensive assessment of IBS genetics to date, demonstrating reproducible polygenic inheritance and linking IBS risk to convergent neurogastrointestinal and novel cardiometabolic mechanisms, highlight specific biological pathways and actionable mechanisms and outline translational opportunities emerging from integrated computational analyses.
Biagio Di Lorenzo, L. Camargo Tavares, Cristian Díaz-Muñoz et al.· Gut· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
