Background: To develop and validate a quantitative computed tomography (QCT) based radiomics model for discriminating osteoporosis and osteopenia. Methods: A total of 635 patients underwent QCT were retrospectively included from November 2016 to November 2019. The patients with osteopenia or osteoporosis (N = 590) were divided into a training cohort (N = 414) and a test cohort (N = 176). Radiomics features were extracted from the QCT images of the third lumbar vertebra. Minimum redundancy and maximum relevance and least absolute shrinkage and selection operator were used for data dimensional reduction, features selection and radiomics model building. Multivariable logistic regression was applied to construct the combined clinical-radiomic model that incorporated radiomics signatures and clinical characteristics. The performance of the combined clinical-radiomic model was evaluated by the area under the curve of receiver operator characteristic curve (ROC–AUC), accuracy, specificity, sensitivity, positive predictive value, and negative predictive value. Results: The patients with osteopenia or osteoporosis were randomly divided into training and test cohort with a ratio of 7:3. Six more predictive radiomics signatures, age, alkaline phosphatase and homocysteine were selected to construct the combined clinical-radiomic model for diagnosis of osteoporosis and osteopenia. The AUC of the combined clinical-radiomic model was 0.96 (95% confidence interval (CI), 0.95 to 0.98) in the training cohort and 0.96 (95% CI 0.92 to 1.00) in the test cohort, which were superior to the clinical model alone (training-AUC = 0.81, test-AUC = 0.79). The calibration curve demonstrated that the radiomics nomogram had good agreement between prediction and observation and decision curve analysis confirmed clinically useful. Conclusions: The combined clinical-radiomic model that incorporates the radiomics score and clinical risk factors, can serve as a reliable and powerful tool for discriminating osteoporosis and osteopenia.

Aging research has primarily focused on adult aging clocks, leaving a critical gap in understanding a biological clock across the full life cycle, particularly during infancy and childhood. Here we introduce LifeClock, a biological clock model that predicts biological age across all life stages using routine electronic health records and laboratory test data. To enhance individualized predictions, we integrated virtual patient representations from 24,633,025 heterogeneous longitudinal clinical visits across 9,680,764 individuals and projected them into a latent space. Our approach leverages EHRFormer, a time-series transformer-based model, to analyze developmental and aging dynamics with high precision and develop accurate biological age clocks spanning infancy to old age. Our findings reveal distinct biological clock patterns across different life stages. The pediatric clock is strongly associated with children’s development and accurately predicts current and future risks of major pediatric diseases, including malnutrition, growth and developmental abnormalities. The adult clock is strongly associated with aging and accurately predicts current and future risks of major age-related diseases, such as diabetes, renal failure, stroke and cardiovascular diseases. This work therefore distinguishes pediatric development from adult aging, establishing a novel framework to advance precision health by leveraging routine clinical data across the entire lifespan.

Objective: Rheumatoid arthritis (RA) is a chronic inflammatory joint disease, which is associated with progressive disability, systemic complications, and early death. But its etiology and pathogenesis are not fully understood. We aimed to investigate the alterations in plasma metabolite profiles, gut bacteria, and fungi and their role of them in the pathogenesis of RA.Methods: Metabolomics profiling of plasma from 363 participants including RA (n = 244), systemic lupus erythematosus (SLE, n = 50), and healthy control (HC, n = 69) were performed using the ultra-high performance liquid chromatography-quadrupole time-of-flight mass spectrometry. The differentially expressed metabolites were selected among groups and used to explore important metabolic pathways. Gut microbial diversity analysis was performed by 16S rRNA sequencing and ITS sequencing (RA = 195, HC = 269), and the specific microbial floras were identified afterward. The diagnosis models were established based on significant differential metabolites and microbial floras, respectively.Results: There were 63 differential metabolites discovered between RA and HC groups, mainly significantly enriched in the arginine and proline metabolism, glycine, serine, and threonine metabolism, and glycerophospholipid metabolism between RA and HC groups. The core differential metabolites included L-arginine, creatine, D-proline, ornithine, choline, betaine, L-threonine, LysoPC (18:0), phosphorylcholine, and glycerophosphocholine. The L-arginine and phosphorylcholine were increased in the RA group. The AUC of the predictive model was 0.992, based on the combination of the 10 differential metabolites. Compared with the SLE group, 23 metabolites increased and 61 metabolites decreased in the RA group. However, no significant metabolic pathways were enriched between RA and SLE groups. On the genus level, a total of 117 differential bacteria genera and 531 differential fungal genera were identified between RA and HC groups. The results indicated that three bacteria genera (Eubacterium_hallii_group, Escherichia-Shigella, Streptococcus) and two fungal genera (Candida and Debaryomyces) significantly increased in RA patients. The AUC was 0.80 based on a combination of six differential bacterial genera and the AUC was 0.812 based on a combination of seven differential fungal genera. Functional predictive analysis displayed that differential bacterial and differential fungus both were associated with KEGG pathways involving superpathway of L-serine and glycine biosynthesis I, arginine, ornithine, and proline interconversion.Conclusion: The plasma metabolism profile and gut microbe profile changed markedly in RA. The glycine, serine, and threonine metabolism and arginine and proline metabolism played an important role in RA.

Objectives: Rheumatoid arthritis (RA) is a chronic autoimmune disease with complex causes and recurrent attacks that can easily develop into chronic arthritis and eventually lead to joint deformity. Our study aims to elucidate potential mechanism among control, new-onset RA (NORA) and chronic RA (CRA) with multi-omics analysis. Methods: A total of 113 RA patients and 75 controls were included in our study. Plasma and stool samples were obtained for 16S rRNA sequencing, internally transcribed spacer (ITS) sequencing and metabolomics analysis. And PBMCs were obtained for RNA sequencing. We used three models, logistic regression, least absolute shrinkage and selection operator (LASSO), and random forest, respectively, to distinguish NORA from CRA, and finally we validated model performance using an external cohort of 26 subjects. Results: Our results demonstrated intestinal flora disturbance in RA development, with significantly increased abundance of Escherichia-Shigella and Proteobacteria in NORA. We also found that the diversity was significantly reduced in CRA compared to NORA through fungi analysis. Moreover, we identified 29 differential metabolites between NORA and CRA. Pathway enrichment analysis revealed significant dysregulation of glycerophospholipid metabolism and phenylalanine metabolism pathways in RA patients. Next, we identified 40 differentially expressed genes between NORA and CRA, which acetylcholinesterase (ACHE) was the core gene and significantly enriched in glycerophospholipid metabolism pathway. Correlation analysis showed a strong negatively correlation between glycerophosphocholine and inflammatory characteristics. Additionally, we applied three approaches to develop disease classifier models that were based on plasma metabolites and gut microbiota, which effectively distinguished between new-onset and chronic RA patients in both discovery cohort and external validation cohort. Conclusions: These findings revealed that glycerophospholipid metabolism plays a crucial role in the development and progression of RA, providing new ideas for early clinical diagnosis and optimizing treatment strategies.

Epithelial ovarian cancer (EOC) is the deadliest women's cancer and has a poor prognosis. Early detection is the key for improving survival (a 5-year survival rate in stage I/II is over 70% compared to that of 25% in stage III/IV) and can be achieved through methylation markers from circulating cell-free DNA (cfDNA) using a liquid biopsy. In this study, we first identify top 500 EOC markers differentiating EOC from healthy female controls from 3.3 million methylome-wide CpG sites and validated them in 1,800 independent cfDNA samples. We then utilize a pretrained AI transformer system called MethylBERT to develop an EOC diagnostic model which achieves 80% sensitivity and 95% specificity in early-stage EOC diagnosis. We next develop a simple digital droplet PCR (ddPCR) assay which archives good performance, facilitating early EOC detection.