Elevated lipoprotein(a) [Lp(a)] is associated with a higher risk of atherosclerotic cardiovascular disease (ASCVD). Although Lp(a) is a genetically determined risk factor, the plasma proteomic feature Show more
Elevated lipoprotein(a) [Lp(a)] is associated with a higher risk of atherosclerotic cardiovascular disease (ASCVD). Although Lp(a) is a genetically determined risk factor, the plasma proteomic features associated with Lp(a) and whether they provide information about ASCVD risk beyond Lp(a) concentration are not well characterized. We sought to identify plasma proteomic features associated with Lp(a) concentration and to evaluate whether an Lp(a)-associated proteomic signature is associated with ASCVD phenotypes in young, healthy adults. In the Coronary Artery Risk Development in Young Adults (CARDIA) study, we measured Year 7 Lp(a) and 184 cardiovascular proteins using the Olink proximity extension assay in 3,920 participants without prior coronary heart disease. Lp(a)-associated proteomic signatures were derived using LASSO regression in a split-sample design and tested for association with coronary artery calcification (CAC), incident CHD, and hs-CRP over 27 years of follow-up. External replication was performed in the UK Biobank (n=37,996). Lp(a) was associated with CAC (OR 1.23 [1.13-1.34]; p<0.0001) and incident CHD (HR 1.23 [1.07-1.41]; p=0.004). Lp(a) correlated with proteomic features reflecting immune activation, coagulation, and vascular dysfunction. A quantitative Lp(a) proteomic score was independently associated with incident CAC (standardized beta = 0.40, p<0.0001) and hs-CRP (standardized beta = 0.11, p = 0.00015) after adjustment for Lp(a) concentration. In the UK Biobank, a recalibrated Lp(a)-associated proteomic score was associated with CRP, incident CHD, and all-cause mortality. In young adults, Lp(a) is associated with distinct proteomic features that independently predict ASCVD phenotypes beyond Lp(a) concentration, generating hypotheses regarding biological pathways linked to Lp(a)-related cardiovascular risk. Show less
Early-onset psychosis presents diagnostic challenges due to overlapping clinical presentations and complex comorbidities, typically requiring specialized tertiary care with extensive neuroimaging, neu Show more
Early-onset psychosis presents diagnostic challenges due to overlapping clinical presentations and complex comorbidities, typically requiring specialized tertiary care with extensive neuroimaging, neuropsychometric testing, and multidisciplinary evaluation. This case-control study investigated whether machine learning could integrate multiple diagnostic modalities to create an objective diagnostic framework for early-onset psychosis. We recruited 45 patients with early-onset psychosis and 34 healthy controls from a tertiary referral centre. Participants underwent comprehensive assessment including serum protein biomarker analysis (brain-derived neurotrophic factor, proBDNF, p75 neurotrophin receptor, S100B), neuropsychometric testing (Iowa Gambling Task, Simple Response Time, Zabor Verbal Task), and demographic evaluation. Four machine learning algorithms (logistic regression, support vector machine, random forest, XGBoost) were trained on five feature combinations using nested cross-validation with hyperparameter optimization. XGBoost demonstrated superior performance, achieving optimal classification with the complete multimodal dataset (accuracy: 0.91 ± 0.08, precision: 0.92 ± 0.08, area under curve: 0.97 ± 0.04). Feature importance analysis revealed cognitive measures, particularly Zabor Verbal Task errors and response time parameters, as most discriminative, with brain-derived neurotrophic factor pathway components showing highest biomarker importance. Machine learning effectively integrated neuropsychometric and protein biomarker data for high-accuracy early-onset psychosis classification, with multimodal approaches outperforming single-domain assessments. Show less