Search

We construct non-linear machine learning (ML) prediction models for systolic and diastolic blood pressure (SBP, DBP) using demographic and clinical variables and polygenic risk scores (PRSs). We developed a two-model ensemble, consisting of a baseline model, where prediction is based on demographic and clinical variables only, and a genetic model, where we also include PRSs. We evaluate the use of a linear versus a non-linear model at both the baseline and the genetic model levels and assess the improvement in performance when incorporating multiple PRSs. We report the ensemble models performance as percentage variance explained (PVE) on a held-out test dataset. A non-linear baseline model improved the PVEs from 28.1 to 30.1% (SBP) and 14.3% to 17.4% (DBP) compared with a linear baseline model. Including seven PRSs in the genetic model computed based on the largest available GWAS of SBP/DBP improved the genetic model PVE from 4.8 to 5.1% (SBP) and 4.7 to 5% (DBP) compared to using a single PRS. Adding additional 14 PRSs computed based on two independent GWASs further increased the genetic model PVE to 6.3% (SBP) and 5.7% (DBP). PVE differed across self-reported race/ethnicity groups, with primarily all non-White groups benefitting from the inclusion of additional PRSs. In summary, non-linear ML models improves BP prediction in models incorporating diverse populations.

Abstract Biomass pyrolysis greatly impacts climates, ecosystem dynamics, air quality, human health, global carbon and nitrogen cycle. The emissions of nitrogen-containing compounds from biomass pyrolysis highly depend on the protein nitrogen existing in biomass. However, the quantitative kinetic information, including the rate constant and apparent activation energy of individual amino acid induced by pyrolysis are still yet to be well-constrained. Towards this, we performed a series of controlled pyrolysis experiments where 18 equimolar free amino acids standard mixtures were pyrolyzed under ambient oxygen at temperatures between 160 and 240 °C. Additionally, straw samples were pyrolyzed to understand the mechanism of combined amino acids in protein liberation to free amino acids during pyrolytic processes. Our observations indicated that an increase in heating duration and temperature promote the degradation of free amino acids. Further, the heating stability of the 18 examined amino acids varied, which could be related to the length and functional groups present in their side chains. Our result shows that the degradation processes of all examined 18 amino acids followed irreversible first-order reaction kinetics in air within the given temperature range, with their activation energy ranging from 88.5 to 137.44 kJ mol−1. The distinct distribution patterns of both combined and free amino acids in aerosol samples from straw pyrolytic processes were obtained. The kinetic information of amino acids garnered herein helps to elucidate the transformation mechanisms of nitrogenous compounds during biomass burning.

Abstract Endometriosis is a chronic inflammatory disease and an estrogen-dependent disease, so dietary factors that can modulate estrogen activity may be clinically important. Dietary fiber, widely distributed in vegetables and fruits, is closely associated with a plant-based diet. Therefore, this study aims to analyze and explore the relationship between dietary fiber intake and the risk of endometriosis providing insights for future clinical significance and treatment approaches. This cross-sectional study obtained data from the National Health and Nutrition Examination Survey (NHANES) 1999–2006 for women aged 20–54 years. A total of 2840 subjects were finally included for analysis, 2599 (91.51%) in the non-endometriosis group and 241 (8.49%) in the endometriosis group. The study used dietary fibre intake as exposure variable and endometriosis risk as outcome variable. Through the use of multiple regression modelling, subgroup analyses, smoothed curve fitting, and threshold effect tests, we uncovered a significant link between exposure and outcome. In Model 2 (Multiple regression equation model after adjusting all confounding variables), after adjusting for confounders, dietary fiber intake was negatively associated with the likelihood of developing endometriosis(OR = 0.588, 95% CI = 0.360–0.959, p = 0.041). In subgroup analyses stratified by age, race, BMI, educational level, hypertension, diabetes,and hyperlipidemia, significant interactions were visualised from smoothed fitted curves. In the cross-sectional study, a connection was observed between a higher intake of dietary fiber and a decreased risk of endometriosis.

Abstract Background: Microvascular invasion (MVI) is an independent risk factor of poor prognosis in hepatocellular carcinoma (HCC) and can be used to guide the diagnosis and treatment of HCC. The immune system serves as an integral role in the incidence and progression of HCC. However, the molecular biology correlation between MVI and tumor immunity and the value of combining the two parameters to predict patient prognosis and HCC response to treatment remain to be evaluated. Results: In this study, we used univariate Cox regression analysis and least absolute shrinkage and selection operator (LASSO) Cox analysis to establish the MVI and immune-related gene index (MIRGPI) including eight genes. We demonstrated that the MIRGPI was an independent risk factor in predicting the prognosis of HCC. Subsequently, our research established a nomogram model combining pathologic characteristics and verified its good clinical application value. In addition, our study found that the TP53 gene had a higher mutation frequency and a lower degree of immune infiltration in the high-risk group. The low-risk group had higher sensitivity to immunotherapy, sorafenib, and TACE treatment, and the high-risk group had higher sensitivity to common chemotherapeutic agents. Finally, SEMA3C was found to facilitate the proliferation, migration and invasive ability of HCC by in vitro and in vivo experiments, and its mechanism may be associated with the activation of the NF-Κb/EMT signaling pathway. Conclusions: In summary, the MIRGPI signature we developed is a reliable marker for the prediction of prognosis and treatment response, and is important for the prognostic assessment and individualized treatment of HCC.

Abstract Due to the influence of construction quality, engineering geology and hydrological environment, defects such as dehollowing and insufficient compaction can occur in tunnels. Aiming at the problems of complex detection model, poor real-time performance and low accuracy of the current tunnel lining defect detection methods, the study proposes a lightweight defect detection algorithm of tunnel lining based on knowledge distillation. Firstly, a high-precision teacher model based on yolov5s was constructed by constructing a C3CSFM module that combines residual structure and attention mechanism, a MDFPN network structure with multi-scale feature fusion and a reweighted RWNMS re-screening mechanism. Secondly, in the distillation process, the feature and output dimension results are fused to improve the detection accuracy, and the mask feature relationship is learned in the space and channel dimension to improve the real-time detection. Tests on the tunnel lining radar defect image dataset showed that the number of parameters of the improved model was reduced from 16.03 MB to 3.20 MB, a reduction of 80%, and the average accuracy was improved from 83.4 to 86.5%, an increase of 3.1%. On the basis of maintaining the structure and detection performance of the model, the lightweight degree of the model is greatly improved, and the high-precision and real-time detection of tunnel lining defects is realized.

Abstract Due to the polycrystalline cubic boron nitride tool has the characteristics of high hardness, brittleness, etc., it is easy to break the tool or produce defects in the laser cutting process, which affects the cutting performance of the tool. Traditional defect detection methods can no longer meet the needs of modern manufacturing. Aiming at the problems of low accuracy and poor real-time detection of surface defects on laser-cutting polycrystalline cubic boron nitride tools, this study proposes the surface defect detection model of laser cutting polycrystalline cubic boron nitride tool based on asymptotic fusion strategy, which fills the gap in the field. In the backbone network, the C3SE module is constructed by modeling the correlation between feature channels to improve the model’s focus on key features in order to enhance the feature extraction and processing capability of the backbone network; In the neck network, adaptive spatial fusion operation and direct interaction of non-adjacent layers are utilized for multi-scale information fusion, and the asymptotic feature pyramid network for object detection (AFPN) is used instead of the FPN structure to improve the detection performance; In the head network, a soft suppression mechanism is introduced to reduce the overlapping frame score using a decay function, thus improving the detection accuracy. The experimental results based on the self-constructed laser-cutting polycrystalline cubic boron nitride tool surface defects dataset show that the average accuracy of the AFFS-YOLO model is improved by 5.6% compared with that of the YOLOv5 model, reaching 86.1%, and the detection effect is better than that of the original network and other classical target detection networks.

Abstract We aim to evaluate the prevalence of steatotic liver disease (SLD) in United States (US) adolescents and explore whether metabolic dysfunction-associated steatotic liver disease (MASLD) can identify individuals with clinically significant fibrosis (CSF) in this study. The prevalence of SLD and its categories, including MASLD, metabolic dysfunction and alcohol associated liver disease (MetALD), alcohol related liver disease (ALD) and other SLD were determined. Weighted multivariable logistic regression analysis was conducted to evaluate the association between MASLD and CSF in adolescents with SLD. Among the total 1,446 US adolescents, SLD was present in 291 (20.1%) of individuals, including 260 (17.9%) for MASLD, 9 (0.6%) for MetALD and 5 (0.3%) for ALD. Only 58 (4%) had CSF. Patients with SLD showed a higher prevalence of CSF (9.6% vs. 2.6%, p

Abstract Pilocytic astrocytoma (PA) is classified as a Grade I benign neuroglial tumor. The extent of surgical resection is a critical factor influencing the prognosis for patients with PA. In prior researches of PA, the extent of surgical resection is generally categorized into GTR, STR and biopsy. In some researches on brain tumor surgeries, the extent of resection also includes GTL. There is no existing research specifically comparing the efficacy of GTR versus GTL in PA treatment. In this study, the data we used are from the SEER database. We categorized the extent of resection into GTL, GTR, STL, STR, biopsy, and no surgery based on SEER classification of surgical procedures, to investigate the impact of extent of resection on PA patient survival. A multivariate logistic regression model was utilized to acquire odds ratios (OR) for different extent of resection. Survival outcomes across different extent of resection (GTL, GTR, STL, STR, biopsy, no surgery) were assessed using Kaplan–Meier survival curve analysis, with curve comparisons conducted via log-rank tests. The impact of various risk factors on survival was assessed using the Cox proportional hazards model. The hazard ratio (HR) was employed to quantify the influence of one or more factors on overall survival throughout the follow-up period. Multivariate Cox analysis revealed that age, tumor location, extent of resection, as well as the application of radiotherapy and chemotherapy, all significantly impacted prognosis. Compared to GTL, GTR did not significantly increase the risk of mortality (HR 1.17; 95% CI 0.73–1.86, p = 0.5). Furthermore, there was no statistically significant difference between the Kaplan–Meier survival curves of the two groups (p = 0.18). We employed propensity score matching (PSM) to balance the differences in baseline characteristics of patients receiving chemotherapy or radiotherapy. A total of 4429 patients were included in this study. Age, diagnosis period, race, tumor size, and tumor location as influential on the extent of resection. Age, tumor location, extent of resection, and application of radiotherapy and chemotherapy influenced the survival of PA patients. The Kaplan–Meier survival curves revealed that the long-term survival rate for GTR is slightly higher than that for GTL. The PSM analysis revealed that the application of radiotherapy and chemotherapy was associated with the reduction of overall survival in PA patients. In conclusion, there was no significant difference in survival between GTR and GTL, so GTR with less damage was preferred. The application of radiotherapy and chemotherapy can reduce overall survival of patients with PA.