Accuracy Predictive Values Research Articles

Development and validation of a prediction model of hospital mortality for patients with cardiac arrest survived 24 hours after cardiopulmonary resuscitation

ObjectiveResearch on predictive models for hospital mortality in patients who have survived 24 h following cardiopulmonary resuscitation (CPR) is limited. We aim to explore the factors associated with hospital mortality in these patients and develop a predictive model to aid clinical decision-making and enhance the survival rates of patients post-resuscitation.MethodsWe sourced the data from a retrospective study within the Dryad dataset, dividing patients who suffered cardiac arrest following CPR into a training set and a validation set at a 7:3 ratio. We identified variables linked to hospital mortality in the training set using Least Absolute Shrinkage and Selection Operator (LASSO) regression, as well as univariate and multivariate logistic analyses. Utilizing these variables, we developed a prognostic nomogram for predicting mortality post-CPR. Calibration curves, the area under receiver operating curves (ROC), decision curve analysis (DCA), and clinical impact curve were used to assess the discriminability, accuracy, and clinical utility of the nomogram.ResultsThe study population comprised 374 patients, with 262 allocated to the training group and 112 to the validation group. Of these, 213 patients were dead in the hospital. Multivariate logistic analysis revealed age (OR 1.05, 95% CI: 1.03–1.08), witnessed arrest (OR 0.28, 95% CI: 0.11–0.73), time to return of spontaneous circulation (ROSC) (OR 1.05, 95% CI: 1.02–1.08), non-shockable rhythm (OR 3.41, 95% CI: 1.61–7.18), alkaline phosphatase (OR 1.01, 95% CI: 1–1.01), and sequential organ failure assessment (SOFA) (OR 1.27, 95% CI: 1.15–1.4) were independent risk factors for hospital mortality for patients who survived 24 h after CPR. ROC of the nomogram showed the AUC in the training and validation group was 0.827 and 0.817, respectively. Calibration curves, DCA, and clinical impact curve demonstrated the nomogram with good accuracy and clinical utility.ConclusionOur prediction model had accurate predictive value for hospital mortality in patients who survived 24 h after CPR, which will be beneficial for assisting in identifying high-risk patients and intervention. Further confirmation of the model's accuracy required external validation data.

Preprocessing vannamei skeleton image for feature classification

Abstract The use of visual imaging technology on underwater objects is still being developed, one of which is vaname shrimp (Litopenaeus vannamei). It is one type of shrimp that is popularly consumed by the world community. Super intensive shrimp pond farming can produce high amounts of production, but sometimes farmers also find very low production or in this case, harvest failure. It is influenced by many factors, one of which is the supervision of post-molting shrimp that require stable calcium levels in water to form new shells. This is done to keep soft shrimp without skin (post-molting) from dying due to cannibalism. Handling this requires monitoring using underwater imaging. The purpose of this research is to interpret the image of vaname shrimp molting underwater. The method used is image processing which consists of: Resize image, grayscale, thresholding, erosion and skeleton techniques. Skeleton features are well used for prediction of molting and not molting vanamei shrimp, where the prediction accuracy value using Support Vector Machine (SVM) classification Linear model shows an accuracy value of 71.43%.

Association between C-reactive protein-albumin-lymphocyte index and overall survival in patients with esophageal cancer.

Esophageal cancer is an aggressive malignant tumor with poor prognosis, making early detection and treatment crucial. C-reactive protein-albumin-lymphocyte (CALLY) index is a comprehensive indicator which is involved in the process of metabolism, inflammation and immune reaction, and has been addressed to correlate with clinical outcomes in cancer patients. However, However, the evidence in esophageal cancer remains unclear. This study aims to investigate the association between CALLY index and overall survival of patients with esophageal cancer. This study includes the clinical characteristics of 518 patients with esophageal cancer from the Investigation on Nutrition Status and Clinical Outcome of Common Cancers (INSCOC) project, and evaluates the correlation between CALLY index and overall survival by COX regression analysis. Time-patient survival trends are verified using Kaplan-Meier method, and cubic spline function. Based on the results of multivariate Cox analysis, a nomogram showing 1, 2, 3, and 5-year survival rates is constructed. Calibration curve and decision curve analysis are used to evaluate the prediction accuracy and practical value of nomogram survival prediction. TNM staging of patients with esophageal cancer is determined according to the pathological examination results of the tumor and surrounding tissues, including the size and depth of the tumor (T), the involvement of lymph nodes (N), and the distant metastasis (M). Multivariate Cox regression analysis demonstrates that CALLY index (HR:0.967, 0.937-0.997, P<0.05), smoking (HR: 1.592, 1.064-2.380, P<0.05), TNM staging (HR: 1.595, 1.120-2.270, P<0.05) are independent prognostic factors for survival of patients with esophageal cancer. Patients with high CALLY index has the lower risk of death than those with low CALLY index (HR: 0.54, 0.36-0.80, P<0.05). The nomogram model including CALLY index shows better prediction ability than traditional TNM staging system. CALLY index is independently positive associated with overall survival in patients with esophageal cancer and nomogram model displays superiority over TMN staging in predicting overall survival.

Urinary Metabolite Profiles of Participants with Overweight and Obesity Prescribed a Weight Loss High Fruit and Vegetable Diet: A Single Arm Intervention Study.

Thus far, no studies have examined the relationship between fruit and vegetable (F and V) intake, urinary metabolite quantities, and weight change. Therefore, the aim of the current study was to explore changes in urinary metabolomic profiles during and after a 10-week weight loss intervention where participants were prescribed a high F and V diet (7 servings daily). Adults with overweight and obesity (n = 34) received medical nutrition therapy counselling to increase their F and V intakes to national targets (7 servings a day). Data collection included weight, dietary intake, and urine samples at baseline at week 2 and week 10. Urinary metabolite profiles were quantified using 1H NMR spectroscopy. Machine learning statistical approaches were employed to identify novel urine-based metabolite biomarkers associated with high F and V diet patterns at weeks 2 and 10. Metabolic changes appearing in urine in response to diet were quantified using Metabolite Set Enrichment Analysis (MSEA). Energy intake was significantly lower (p = 0.02) at week 10 compared with baseline. Total F and V intake was significantly higher at week 2 and week 10 (p < 0.05). In total, 123 urinary metabolites were quantified. At week 10, 21 metabolites showed significant changes relative to baseline. Of these, 11 metabolites also significantly changed at week 2. These overlapping metabolites were acetic acid, dimethylamine, choline, fumaric acid, glutamic acid, L-tyrosine, histidine, succinic acid, uracil, histamine, and 2-hydroxyglutarate. Ridge Classifier and Linear Discriminant Analysis provided best prediction accuracy values of 0.96 when metabolite level of baseline was compared to week 10. Urinary metabolites quantified represent potential candidate biomarkers of high F and V intake, associated with a reduction in energy intake. Further studies are needed to validate these findings in larger population studies.

ALGORITMA NAIVE BAYES UNTUK MEMPREDIKSI KELAYAKAN PENERIMA BANTUAN PANGAN NON TUNAI (BPNT) DESA JAGANG LAMPUNG UTARA

Jagang Village is a government agency in Blambangan Pagar District, North Lampung Regency. Jagang Village runs a government program, namely the Non-Cash Food Assistance (BPNT) program in running the program, some residents who are considered capable actually get assistance. In this study, the method used in predicting the eligibility of recipients and non-recipients of Non-Cash Food Assistance (BPNT) is the Naïve Bayes method with manual calculations using Excel formulas that are composed in such a way as to facilitate data input and testing using RapidMiner 7.1 and produces the same accuracy as manual calculations. The results of the implementation of Data Mining using the Naïve Bayes Method to predict the Eligibility of recipients and non-recipients of Non-Cash Food Assistance (BPNT) obtained a prediction accuracy value of 91% and was tested with RapidMiner software with an Accuracy result of 90.91%.

Genome-Wide Association Study and Genomic Prediction of Soft Wheat End-Use Quality Traits Under Post-Anthesis Heat-Stressed Conditions.

Wheat end-use quality is an important component of a wheat breeding program. Heat stress during grain filling impacts wheat quality traits, making it crucial to understand the genetic basis of wheat quality traits under post-anthesis heat stress. This study aimed to identify the genomic regions associated with wheat quality traits using genome-wide association studies (GWASs) and evaluate the prediction accuracy of different genomic selection (GS) models. A panel of 236 soft red facultative wheat genotypes was evaluated for end-use quality traits across four heat-stressed environments over three years. Significant phenotypic variation was observed across environments for traits such as grain yield (GY), grain protein (GP), grain hardness (GH), and flour yield (AFY). Heritability estimates ranged from 0.52 (GY) to 0.91 (GH). The GWASs revealed 136 significant marker-trait associations (MTAs) across all 21 chromosomes, with several MTAs located within candidate genes involved in stress responses and quality traits. Genomic selection models showed prediction accuracy values up to 0.60, with within-environment prediction outperforming across-environment prediction. These results suggest that integrating GWAS and GS approaches can enhance the selection of wheat quality traits under heat stress, contributing to the development of heat-tolerant varieties.

NHPP Software Reliability Model with Rayleigh Fault Detection Rate and Optimal Release Time for Operating Environment Uncertainty

Software is used in diverse settings and depends on development and testing environments. Software development should improve the reliability, quality, cost, and stability of software, making the software testing period crucial. We proposed a software reliability model (SRM) that considers the uncertainty of software environments and the fault detection rate function as a Rayleigh distribution, with an explicit mean value function solution in the model. The goodness-of-fit of the proposed model relative to several existing nonhomogeneous Poisson process (NHPP) SRMs is presented based on three software application failure datasets. Further, a cost model is also presented that addresses the error-removal risk level and required time. The optimal testing release policy for minimizing the expected total cost (ETC) is also determined for NHPP SRMs. The impact of the software environment is studied by varying it, and the optimal release times and minimum ETCs are compared. The goodness-of-fit comparison confirmed that the proposed model has more accurate prediction values than other models. Further, whereas the existing models applied to the cost model do not change after a certain operation period, the proposed model yields changes in release time even for long operating periods.

Predicting temporal evacuation travel time in staircases between adjacent floors of super high-rise buildings by artificial neural networks

Predicting temporal evacuation travel time in staircases between adjacent floors is crucial for dynamic evacuation guidance to improve vertical evacuation efficiency during emergencies in super high-rise buildings. However, the prediction methods used in previous studies mainly focus on the total evacuation time in buildings and cannot predict the temporal evacuation travel time in every single part of the total evacuation route. This study proposes a novel method to predict temporal evacuation travel time in staircases between adjacent floors of super high-rise buildings by using artificial neural networks. Firstly, evacuation simulation data of a 71-storey office building are analyzed for feature engineering and dataset building. Secondly, three types of artificial neural networks, including convolutional neural networks, RNN-based model (the traditional recurrent neural networks, long-short term memory networks, and bidirectional long-short term memory networks), and Attention-based model (Attention model and Transformer model) are extended to predict the temporal evacuation travel time in staircases between adjacent floors based on the simulation data. Finally, the prediction results by different artificial neural networks are compared. The results show that the artificial neural networks can provide accurate prediction values for the temporal evacuation travel time in staircases between adjacent floors of super high-rise buildings.

Enhancing artificial permafrost table predictions using integrated climate and ground temperature data: A case study from the Qinghai-Xizang highway

The complexities of permafrost changes, driven by climate warming and engineering activities, coupled with challenges in data acquisition, make it crucial and challenging to accurately predict the artificial permafrost table, particularly for subgrades in high-temperature unstable permafrost regions. To address this, this study developed a hybrid machine learning model (RF-LSTM-XGBoost) for permafrost table prediction. By analyzing climate change and ground temperature data from various positions and depths along the subgrade in the Tuotuo River section of the Qinghai-Xizang Highway, the Spearman correlation coefficient method was initially used to determine the important influencing factors. Random Forest (RF), Long Short-Term Memory Neural Network (LSTM), and Extreme Gradient Boosting (XGBoost) models were used to predict the artificial permafrost table, and grid search and cross-validation methods were employed to optimize the hyperparameters of each model. A linear weighted combination method based on the minimum cumulative absolute error was utilized to merge the models, and its performance was compared with the individual RF, LSTM, and XGBoost models. Subsequently, the feature importance of the variables in the machine learning model was analyzed. The results indicated a strong correlation between artificial permafrost table changes and factors such as daily average atmospheric temperature, subgrade surface ground temperature, and subgrade surface ground heat flux during the freezing-thawing cycle. The combined model highlighted daily atmospheric temperature as the most influential predictor, followed by ground heat flux, with the surface ground temperature being less impactful. The combined model demonstrated improved predictive accuracy, with MSE, MAPE, RMSE, MAE, and R2 values of 0.003, 0.052, 0.0085, 0.029, and 0.989, respectively, surpassing those of individual models. This model offers a rapid, accurate, and reliable approach for permafrost table prediction, advancing subgrade stability research in challenging permafrost environments.

A robust approach for bond strength prediction of mortar using machine learning with SHAP interpretability

Application of machine learning (ML) in predicting mortars bond strength contributes to low experimental cost and high accuracy. This study explores the performance of four ML models—Back Propagation Neural Network (BPNN), Support Vector Regression (SVR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost)—using 304 experimental data points for training and 76 results for testing. Among these, the XGBoost model demonstrated the highest predictive accuracy, with R², MAE, and RMSE values of 0.95, 0.06, and 0.13 in the training set, and 0.94, 0.08, and 0.16 in the testing set, respectively. Compared with traditional models, ML approaches, particularly XGBoost, were more effective in providing reliable predictions of bond strength. SHapley Additive exPlanation (SHAP) show that substrate type, ethylene-vinyl acetate (EVA) content and water to binder ratio W/C have the most remarkable effect on bond strength, while the type of cement and admixture shows the least effect. These findings highlight the potential of ML models in optimizing mortar formulations and improving prediction reliability.

The clinical value of serum long non-coding RNA human leukocyte antigen complex group 11/microRNA-532-3p in the diagnosis and prognosis of patients with acute myocardial infarction undergoing percutaneous coronary intervention

BackgroundAcute myocardial infarction (AMI) is a cardiovascular disease with the highest morbidity and mortality rate in the world. Several studies have suggested that abnormal regulation of non-coding RNAs (ncRNAs) may play a vital role in the occurrence and progress of AMI.ObjectiveThe purpose of this study was to investigate the clinical values of human leukocyte antigen complex group 11 (HCG11) or miR-532-3p in the diagnosis and prognosis of patients with AMI after percutaneous coronary intervention (PCI).MethodsThe clinical data of 100 AMI patients who underwent PCI were analyzed retrospectively. According to whether major adverse cardiovascular events (MACE) occurred after PCI, they were divided into MACE group (n = 38) and non-MACE group (n = 62). Basic clinical data and serum HCG11 and miR-532-3p levels were analyzed. Multivariate Cox regression analysis was performed to evaluate the risk factors for MACE, and the receiver operator characteristic (ROC) curve was constructed to assess the clinical predictive value of HCG11 and miR-532-3p for MACE.ResultsCompared with the control group, the serum HCG11 level and miR-532-3p in AMI patients were significantly increased or decreased, and the serum levels of HCG11 and miR-532-3p in the MACE group were significantly increased and decreased, compared with those in non-MACE group. Multivariate Cox regression showed that HCG11 and miR-532-3p were risk factors for MACE occurrence. ROC curve investigated that HCG11 combined with miR-532-3p has accurate predictive value for MACE.ConclusionThis study showed that serum HCG11 and miR-532-3p have certain predictive value for MACE after PCI in patients with AMI.

Halving Time of BCR-ABL Transcripts as a Precise Predictor for Deep Molecular Response in Patients with Chronic Myeloid Leukemia Treated with TKI

To investigate the early predictive value of halving time (HT) of BCR-ABLIS for deep molecular response (DMR) in patients with chronic myeloid leukemia (CML) treated with tyrosine kinase inhibitor (TKI). The continuous data of newly diagnosed CML patients with complete case data and first-line imatinib treatment admitted to the Affiliated Hospital of Inner Mongolia Medical University from January 2014 to June 2022 were retrospectively analyzed. Combined with the clinical characteristics of the patients and the efficacy analysis at each time point, a logistic regression model was used to explore the independent influencing factors of DMR, and combined HT of BCR-ABLIS with BCR-ABLIS level at 3 months to predict DMR of the patients. Univariate and multivariate analyses showed that HT and 3-month BCR-ABLIS levels were independent influencing factors for MR4, MR4.5, and stable MR4.5 ( P < 0.05). ROC curve analysis determined that the best cut-off value of HT was 28 days. Compared with patients with HT>28 d, patients with HT≤28 d were more likely to obtain DMR at 2, 3, and 5 years, respectively (74.2% vs 27.3%, 71.2% vs 22.7%, and 63.6% vs 25.0%, all P < 0.001). The patients were divided into 4 groups according to BCR-ABLIS levels at 3 months and HT. Kaplan-Meier analysis showed that the patients in the BCR-ABLIS≤10% and HT≤28 d group had a higher probability of obtaining cumulative MR4 and MR4.5 than those in the BCR-ABLIS≤10% and HT>28 d group (P < ＜0.05); Patients in the BCR-ABLIS>10% and HT≤28 d group had a higher probability of obtaining cumulative MR4 and MR4.5 than those in the BCR-ABLIS＞10% and HT>28 d group ( P < 0.05). In addition to BCR-ABLIS level, HT of BCR-ABLIS can be used as another important predictor of treatment efficacy in CML patients. The combination of BCR-ABLIS level and HT has a more accurate predictive value for long-term molecular response of CML patients after TKI treatment.

Prestack reservoir prediction method in ray parameter domain based on wide azimuth ocean bottom node seismic data

AbstractWide azimuth seismic data play an important role in deep reservoir prediction. According to the Paleogene clastic rock reservoir prediction, the high‐density and wide azimuth 3D seismic data acquisition of ocean bottom nodes was first carried out in a Chinese offshore oilfield in 2019. After high precision amplitude‐preserving processing, we obtained the high‐quality wide azimuth gathers. However, the research on anisotropy and reservoir prediction using wide azimuth seismic data mainly focuses on carbonate and bedrock intervals, which is not suitable for clastic rock reservoir prediction. Therefore, this paper innovatively proposes a clastic rock reservoir prediction method, which studies prestack reservoir prediction in the ray parameter domain based on wide azimuth ocean bottom node seismic data. Based on the azimuth gathers, we can obtain elastic parameters through prestack amplitude versus offset inversion, which is used to characterize the reservoir, so it is significant to obtain high precision elastic parameters in order to get highly reliable reservoir prediction results. In this paper, we develop an amplitude versus offset inversion method based on the Bayesian theory in ray parameter domain, the output of which is density, P‐wave impedance and Vp/Vs. These elastic parameters have high precision, and density data are valuable input for reservoir characterization because they are sensitive to the lithology of clastic rock reservoir at different orientations. In ray parameter domain inversion, the ray path of seismic wave propagation is considered polyline, which is more consistent with the actual situation; thus, extracted amplitudes of P gathers used in inversion are more accurate. In addition, the reflection coefficient formula in ray parameter domain has higher precision when the incident angle is large. The inversion based on the Bayesian theory can improve the stability of the inversion. Test on the actual data shows that the result of ray parameter domain inversion with a Bayesian scheme is more accurate, stable and reliable. Based on the above high precision density inversion results, an innovative wide azimuth data reservoir prediction technology based on elliptical short‐axis fitting was proposed. The actual prediction of the deep reservoir in the Bohai oilfield shows that sand thickness fitting prediction results in the short axis can best match the actual drilling sandstone thickness. The coincidence rate is 86% and the short‐axis fitting results are more in agreement with geological laws. Theoretical research and practical applications have shown that this method is feasible and effective, with high prediction accuracy, computational efficiency and strong application value.

Machine learning insights into the evolution of flood Resilience: A synthesized framework study

Enhancing urban resilience represented a viable strategy to mitigate flooding induced by intense human activities and climate change. However, existing studies often concentrated on system attributes or isolated resilience characteristics, failing to offer a holistic evaluation of urban flood resilience performance. Thus, it was imperative to develop a comprehensive flood resilience framework that incorporated the resilience evolution process including resistance, economic and function recovery. Consequently, this study endeavored to devise a synthesized framework for evaluating urban flood resilience, subsequently employing a Convolutional Neural Network (CNN) model for simulation. The findings indicated that: (1) Guangzhou’s maximum resistance capacity diminished from 0.52 to 0.50 as rainfall return periods altered, while Dongguan exhibited the lowest resistance, decreasing from 0.42 to 0.40. Regarding functional recovery capacity, Guangzhou ranked highest (0.35) and Foshan lowest (0.19); (2) according to Triangular Fuzzy Number-based AHP (TFN-AHP) analysis, the area classified as highest in resilience decreased from 15.6% to 12.1% of the total, whereas the low resilience area increased from 7.6% to 8.7%; (3) Zhuhai and Zhaoqing were primarily clustered along the resistance axis, in contrast, Dongguan was distinguished by its advancement along the axis of functional recovery.(4) CNN simulations yielded precise outcomes, with the Area Under the Receiver Operating Characteristic Curve (AUC) and predictive accuracy (ACC) values exceeding 0.8,respectively. The insights provided by this research were crucial for entities tasked with flood risk management.

An integrated framework for driving risk evaluation that combines lane-changing detection and an attention-based prediction model

Objective In recent years, the increase in traffic accidents has emerged as a significant social issue that poses a serious threat to public safety. The objective of this study is to predict risky driving scenarios to improve road safety. Methods On the basis of data collected from naturalistic driving real-vehicle experiments, a comprehensive framework for identifying and analyzing risky driving scenarios, which combines an integrated lane-changing detection model and an attention-based long short-term memory (LSTM) prediction model, is proposed. The performance of the 4 machine learning methods on the CULane data set is compared in terms of model running time and running speed as evaluation metrics, and the ultrafast network with the best performance is selected as the method for lane line detection. We compared the performance of LSTM and attention-based LSTM on the basis of the prediction accuracy, recall, precision, and F1 value and selected the better model (attention-based LSTM) for risky scenario prediction. Furthermore, Shapley additive explanation analysis (SHAP) is used to understand and interpret the prediction results of the model. Results In terms of algorithm efficiency, the running time of the ultrafast lane detection network only requires 4.1 ms, and the average detection speed reaches 131 fps. For prediction performance, the accuracy rate of attention-based LSTM reaches 96%, the precision rate is 98%, the recall rate is 96%, and the F1 value is 97%. Conclusions The improved attention-based LSTM model is significantly better than the LSTM model in terms of convergence speed and prediction accuracy and can accurately identify risky scenarios that occur during driving. The importance of factors varies by risky scenario. The characteristics of the yaw rate, speed stability, vehicle speed, acceleration, and lane change significantly influence the driving risk, among which lane change has the greatest impact. This study can provide real-time risky scenario prediction, warnings, and scientific decision guidance for drivers.

Tumor-Resident Microbiota-Based Risk Model Predicts Neoadjuvant Therapy Response of Locally Advanced Esophageal Squamous Cell Carcinoma Patients.

Few predictive biomarkers exist for identifying patients who may benefit from neoadjuvant therapy (NAT). The intratumoral microbial composition is comprehensively profiled to predict the efficacy and prognosis of patients with esophageal squamous cell carcinoma (ESCC) who underwent NAT and curative esophagectomy. Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis is conducted to screen for the most closely related microbiota and develop a microbiota-based risk prediction (MRP) model on the genera of TM7x, Sphingobacterium, and Prevotella. The predictive accuracy and prognostic value of the MRP model across multiple centers are validated. The MRP model demonstrates good predictive accuracy for therapeutic responses in the training, validation, and independent validation sets. The MRP model also predicts disease-free survival (p= 0.00074 in the internal validation set and p= 0.0017 in the independent validation set) and overall survival (p= 0.00023 in the internal validation set and p= 0.11 in the independent validation set) of patients. The MRP-plus model basing on MRP, tumor stage, and tumor size can also predict the patients who can benefit from NAT. In conclusion, the developed MRP and MRP-plus models may function as promising biomarkers and prognostic indicators accessible at the time of diagnosis.

Gender Differences in the Predictive Value of Obesity Indices for Insulin Resistance in Adult Mexican Individuals.

Obesity-linked insulin resistance (IR) is an important risk factor for metabolic diseases, and anthropometric indices are commonly used for risk assessment. The study aimed to assess possible differences between women and men in the predictive value and association of nine obesity indices with IR, as assessed by HOMA-IR, in a nondiabetic adult population. The cross-sectional study included individuals recruited from a hospital in Mexico City. Indices evaluated were waist circumference (WC), hip circumference (HC), body mass index (BMI), waist-to-hip ratio, waist-to-height ratio, visceral adiposity index, body adiposity index (BAI), relative fat mass (RFM), and conicity index (CI). Fasting plasma glucose and insulin were measured to calculate HOMA-IR. Correlation analysis was performed between obesity indices and HOMA-IR. Receiver operating characteristics curve analyses were performed to determine predictive accuracy and cut-off values of obesity indices for IR. A binary logistic regression (BLR) analysis with OR calculation was performed to determine the strength of association with HOMA-IR. We included 378 individuals (59% females, mean age 46.38 ±12.25 years). The highest Pearson coefficient value was observed for BMI among women, while among men, the highest values were found for BMI and BAI. WC among women, and BAI and RFM among men showed the highest sensitivity, while the highest specificity was observed for WHR among women and WC among men with respect to insulin prediction. In the adjusted BLR model, BMI, WC, and WHR among women and WC and RFM and BAI among men were independently associated with IR, showing the highest odds ratio (OR). In Mexican adults, WC, WHR, RFM and BAI could be complementary tools for BMI in screening for IR.

Assessing the accuracy of directional forecasts

ABSTRACT Directional predictions are used in a variety of settings, including economics, finance, meteorology and medicine. Since the objectives in each setting can be quite different, appropriate tests for assessing the predictions are necessary. After summarizing existing tests, we propose new tests to assess the accuracy for cases where getting extreme events wrong is particularly costly and where there is serial dependence in small samples. We show in simulations that the latter test has a more favourable power-size trade-off relative to existing tests. The new tests are then applied to the directional EUR/USD forecasts in the ifo-Institute’s World Economic Survey and to the point forecasts in the Philadelphia Fed’s Survey of Professional Forecasters. For the former, the new tests show that while there is profitability and predictive accuracy in some cases, a simple time-series model is not beaten. For the latter, extreme values are not the main driver of the predictive value up to two quarters ahead. This shows that the additional tests allow a more precise determination of predictive accuracy and economic value and where it is coming from.

PhosBERT: A self-supervised learning model for identifying phosphorylation sites in SARS-CoV-2-infected human cells

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a single-stranded RNA virus, which mainly causes respiratory and enteric diseases and is responsible for the outbreak of coronavirus disease 19 (COVID-19). Numerous studies have demonstrated that SARS-CoV-2 infection will lead to a significant dysregulation of protein post-translational modification profile in human cells. The accurate recognition of phosphorylation sites in host cells will contribute to a deep understanding of the pathogenic mechanisms of SARS-CoV-2 and also help to screen drugs and compounds with antiviral potential. Therefore, there is a need to develop cost-effective and high-precision computational strategies for specifically identifying SARS-CoV-2-infected phosphorylation sites. In this work, we first implemented a custom neural network model (named PhosBERT) on the basis of a pre-trained protein language model of ProtBert, which was a self-supervised learning approach developed on the Bidirectional Encoder Representation from Transformers (BERT) architecture. PhosBERT was then trained and validated on serine (S) and threonine (T) phosphorylation dataset and tyrosine (Y) phosphorylation dataset with 5-fold cross-validation, respectively. Independent validation results showed that PhosBERT could identify S/T phosphorylation sites with high accuracy and AUC (area under the receiver operating characteristic) value of 81.9% and 0.896. The prediction accuracy and AUC value of Y phosphorylation sites reached up to 87.1% and 0.902. It indicated that the proposed model was of good prediction ability and stability and would provide a new approach for studying SARS-CoV-2 phosphorylation sites.

Autoantibodies as putative biomarkers and triggers of cell dysfunctions in systemic sclerosis.

Antinuclear autoantibodies represent a serological hallmark of systemic sclerosis (SSc), with anticentromere, antitopoisomerase-I, and anti-RNA polymerase III antibodies routinely assessed for diagnosis, clinical subset classification, and prognosis. In addition, an increasing number of autoantibodies have been demonstrated to play a pathogenic role by mediating different SSc manifestations. This review aims to give an overview on autoantibodies as putative biomarkers in SSc and discuss their possible pathogenic role as triggers of cell dysfunctions. Over the years, different autoantibodies have been proposed as biomarkers aiding in diagnosis, disease subtype classification, disease progression prediction, organ involvement, as well as in understanding treatment response. Increasing literature also indicates functional autoantibodies as direct contributors to SSc pathogenesis by exerting agonistic or antagonistic activities on their specific cognate targets. In SSc, search and validation of novel autoantibodies with higher diagnostic specificity and more accurate predictive values are increasingly needed for early diagnosis and specific follow-up, and to define the best therapeutic option according to different disease subsets. Moreover, since autoantibodies are also emerging as functional pathogenic players, a better unraveling of their possible pathomechanisms becomes essential to identify new targets and develop promising therapeutic agents able to neutralize their effects.