Lasso Regression Model Research Articles

Health Insurance Annual Premium Forecast Analysis

This study focuses on predicting an important socioeconomic indicator: health insurance costs and provides an in-depth exploration of the impact of multiple factors on insurance costs. The data used in the study comes from a representative health insurance company, and its data individuals include indicators of multiple dimensions, such as the age, gender, body fat percentage, family size of the insured, as well as whether they have smoking habits and the specific region where they are located. and other information. In order to accurately reveal the impact of these factors on insurance premiums, we adopted a machine learning model, the Lasso regression model, for modeling and prediction, supplemented by the calculation of correlation coefficients to quantify the strength of the relationship between these factors and insurance premiums. After in-depth exploration and analysis, the research results show that among all factors considered, age, body fat percentage and whether you smoke have a significant impact. It is particularly noteworthy that the factor of smoking has the most significant impact on insurance costs. In addition, the study also revealed that women and insured persons living in the southeast region tend to choose higher premiums. These research results not only have a certain enlightenment effect on theoretical research, but also have significant reference value for the practice of the insurance industry. It can help insurance companies more accurately identify and evaluate potential risks, and set more scientific and reasonable insurance rates accordingly.

Predicting Summer Precipitation Anomalies in the Yunnan–Guizhou Plateau Using Spring Sea-Surface Temperature Anomalies

By constructing a correlation network between global sea surface temperature anomalies (SSTAs) and summer precipitation anomalies in the Yunnan–Guizhou Plateau, key SST regions influencing summer precipitation anomalies in the Yunnan–Guizhou Plateau were selected. It was found that spring SSTAs in the Bay of Bengal, southwestern Atlantic, and eastern Pacific are crucial for influencing summer precipitation anomalies in the Yunnan–Guizhou Plateau. Setting SSTAs from these three regions as predictor variables 3 months in advance, we constructed multiple linear regression (MLR), ridge regression (RR), and lasso regression (LR) models to predict summer precipitation anomalies over the Yunnan–Guizhou region. The training phase involved data spanning from 1961 to 2005, which aimed to predict precipitation anomalies in the Yunnan–Guizhou Plateau for the period extending from 2006 to 2022. Based on MLR, RR, and LR models, the correlations between predicted values and observed summer precipitation anomalies in Yunnan–Guizhou were 0.48, 0.46, and 0.46, respectively. These values were all higher than the correlation coefficients of the NCC_CSM model’s predicted and observed values. Additionally, its performance in predicting summer precipitation anomalies over the Yunnan–Guizhou region, based on key SST regions, was assessed using performance metrics such as anomaly correlation coefficient (ACC), anomaly sign consistency rate (PC), and trend anomaly comprehensive score (PS score). The average ACC of MLR, RR, and LR models was higher than that of the NCC_CSM model’s predictions. For MLR, RR, LR, and NCC_CSM models, the PCs exceeding 50% of the year were 14, 14, 11, and 10, respectively. Furthermore, the average PS score for predicting summer precipitation anomalies over the Yunnan–Guizhou region using MLR, RR, and LR was approximately 73 points; 8 higher than the average PS score of the NCC_CSM model. Therefore, predicting summer precipitation anomalies over the Yunnan–Guizhou region based on key SST regions is of great significance for improving the prediction skills of precipitation anomalies in this region.

Prediction of malignant esophageal fistula in esophageal cancer using a radiomics-clinical nomogram

BackgroundMalignant esophageal fistula (MEF), which occurs in 5% to 15% of esophageal cancer (EC) patients, has a poor prognosis. Accurate identification of esophageal cancer patients at high risk of MEF is challenging. The goal of this study was to build and validate a model to predict the occurrence of esophageal fistula in EC patients.MethodsThis study retrospectively enrolled 122 esophageal cancer patients treated by chemotherapy or chemoradiotherapy (53 with fistula, 69 without), and all patients were randomly assigned to a training (n = 86) and a validation (n = 36) cohort. Radiomic features were extracted from pre-treatment CTs, clinically predictors were identified by logistic regression analysis. Lasso regression model was used for feature selection, and radiomics signature building. Multivariable logistic regression analysis was used to develop the clinical nomogram, radiomics-clinical nomogram and radiomics prediction model. The models were validated and compared by discrimination, calibration, reclassification, and clinical benefit.ResultsThe radiomic signature consisting of ten selected features, was significantly associated with esophageal fistula (P = 0.001). Radiomics-clinical nomogram was created by two predictors including radiomics signature and stenosis, which was identified by logistic regression analysis. The model showed good discrimination with an AUC = 0.782 (95% CI 0.684–0.8796) in the training set and 0.867 (95% CI 0.7461–0.987) in the validation set, with an AIC = 101.1, and good calibration. When compared to the clinical prediction model, the radiomics-clinical nomogram improved NRI by 0.236 (95% CI 0.153, 0.614) and IDI by 0.125 (95% CI 0.040, 0.210), P = 0.004.ConclusionWe developed and validated the first radiomics-clinical nomogram for malignant esophageal fistula, which could assist clinicians in identifying patients at high risk of MEF.

Pathway-based stratification of gliomas uncovers four subtypes with different TME characteristics and prognosis.

Increasing evidences have found that the interactions between hypoxia, immune response and metabolism status in tumour microenvironment (TME) have clinical importance of predicting clinical outcomes and therapeutic efficacy. This study aimed to develop a reliable molecular stratification based on these key components of TME. The TCGA data set (training cohort) and two independent cohorts from CGGA database (validation cohort) were enrolled in this study. First, the enrichment score of 277 TME-related signalling pathways was calculated by gene set variation analysis (GSVA). Then, consensus clustering identified four stable and reproducible subtypes (AFM, CSS, HIS and GLU) based on TME-related signalling pathways, which were characterized by differences in hypoxia and immune responses, metabolism status, somatic alterations and clinical outcomes. Among the four subtypes, HIS subtype had features of immunosuppression, oxygen deprivation and active energy metabolism, resulting in a worst prognosis. Thus, for better clinical application of this acquired stratification, we constructed a risk signature by using the LASSO regression model to identify patients in HIS subtype accurately. We found that the risk signature could accurately screen out the patients in HIS subtype and had important reference value for individualized treatment of glioma patients. In brief, the definition of the TME-related subtypes was a valuable tool for risk stratification in gliomas. It might serve as a reliable prognostic classifier and provide rational design of individualized treatment, and follow-up scheduling for patients with gliomas.

Circulating Biomarkers for Tumour Monitoring, Prognosis Predictions and Detection of Temozolomide Resistance Mutations in Glioma

INTRODUCTION: The potential benefits of circulating biomarkers have been well demonstrated in other cancers. Despite this, no circulating biomarker exists for glioma due to poor sensitivity and hetereogeneity of results. METHODS: Serum miRNA and plasma ctDNA was isolated in a cohort of 212 gliomas using next-generation sequencing (NGS) and digital droplet PCR (ddPCR). Differentially expressed miRNAs were discovered using a machine learning algorithm and compared to tumor volume on MRI. A Lasso-regression model identified miRNAs that were associated with both progression-free and overall survival. Tumor mutations and ctDNA was compared in 49 plasma samples from 10 patients with tumor tissue available from at least two operations using NGS. Identified mutations were validated using ddPCR in the whole cohort. RESULTS: A 9-gene miRNA signature was found that could distinguish between glioma and healthy controls with 99.8% accuracy, including two that demonstrated dynamic changes that correlated with tumor volume on MRI. We found a separate 4-gene miRNA signature that was predictive of survival outcomes and could be incorporated into a clinical nomogram. Common glioma mutations were identified within 93% of plasma samples, including 25% that were not found in the tumor tissue. Mutations in the mismatch repair genes (MMR) were frequently detected in the plasma following temozolomide treatment and observed prior to their appearance in tissue at progression. CONCLUSIONS: We have identified serum miRNA biomarker signatures that can monitor tumour burden and improve prognostic predictions. We also show that contrary to previous reports, ctDNA can be reliably detected in the plasma of gliomas. We found that ctDNA offers complementary information to tissue biopsy alone and provides early evidence of temozolomide resistance through mutations in MMR genes.

Identification of important genes for human periodontal ligament cells in response to mechanical force based on WGCNA.

To identify the differentially important genes of human periodontal ligament cells (PDLC) in response to different types of force, the dataset with regard to human PDLC in response to force was retrieved from the GEO. Differentially expressed genes (DEG) analysis between mechanical force (MF) and the control group was conducted. The gene set enrichment analysis (GSEA) was applied to identify the functional enrichment in different MF groups. Weighted gene co-expression network analysis (WGCNA) of transcriptomic data was performed to identify the highly correlated genes in human PDLC in response to MF. The Lasso regression model was applied to screen the key genes. Results showed A total of 2861 DEGs were identified between the MF group and control group, including 1470 up-regulated DEGs and 1391 down-regulated DEGs. Different biological processes were enriched between the static group and the intermittent group. The Myc targets, TGF-β signaling pathway and PI3K/AKT/MTOR signaling pathway were enriched in intermittent-MF and static-MF groups. The turquoise module (including 386 hub genes) in WGCNA was highly correlated with intermittent traits and the black module (including 33 hub genes) was positively correlated with static traits. The lasso analysis result showed that the CLIC4, NPLOC4 and PRDX6 had the greatest impact on the human PDLC with mechanic stimuli with good predictive efficiency. In conclusion, we developed important genes for human PDLC in response to MF, which might be potential markers for orthodontic tooth movement.

An androgen receptor-based signature to predict prognosis and identification of ORC1 as a therapeutical target for prostate adenocarcinoma.

Aberrant activation of androgen receptor (AR) signaling plays a crucial role in the progression of prostate adenocarcinoma (PRAD) and contributes significantly to the development of enzalutamide resistance. In this study, we aimed to identify a novel AR-driven signature that can predict prognosis and endows potentially reveal novel therapeutic targets for PRAD. The Seurat package was used to preprocess the single-cell RNA sequencing (scRNA-seq). Differentially expressed genes were visualized using limma and pheamap packages. LASSO and multi-variate Cox regression models were established using glmnet package. The package "Consensus Cluster Plus" was utilized to perform the consensus clustering analysis. The biological roles of origin recognition complex subunit 1 (ORC1) in PRAD were determined by gain- and loss-of-function studies in vitro and in vivo. We characterized the scRNA-seq data from GSE99795 and identified 10 AR-associated genes (ARGs). The ARGs model was trained and validated in internal and external cohorts. The ARGs were identified as an independent hazard factor in PRAD and correlated with clinical risk characteristics. In addition, the ARGs were found to be correlated with somatic tumor mutation burden (TMB) levels. Two groups that have distinct prognostic and molecular features were identified through consensus clustering analysis. ORC1 was identified as a critical target among these ARGs, and it ORC1 promoted proliferation and stem-like properties of PRAD cells. Chromatin immunoprecipitation (ChIP)-qPCR assay confirmed that AR could directly bind the promoter of ORC1. Activated AR/ORC1 axis contributed to enzalutamide resistance, and targeting ORC1 rendered PRAD cells more susceptible to enzalutamide. This study defines an AR-driven signature that AR activates ORC1 expressions to promote PRAD progression and enzalutamide resistance, which may provide novel targets for PRAD treatment.

Study on Abnormal Pattern Detection Method for In-Service Bridge Based on Lasso Regression

The real-time operational safety of in-service bridges has received wide attention in recent years. By fully utilizing the health monitoring data of bridges, a structural abnormal pattern detection method based on data mining can be established to effectively ensure the safety of in-service bridges. This paper takes a large-span arch bridge as the research object, analyzes the time-based variation of the main monitoring data of the structure, establishes Lasso regression models for load characteristic indicators and vertical bending fundamental frequency of the structure under different time scales, and uses the residuals of the Lasso model to indicate the structural state and identify abnormal patterns. Firstly, the monitoring data of bridge structural temperature, girder end displacement, and girder acceleration were analyzed, and the interrelationships were studied to extract characteristic parameters of structural load characteristics and structural frequency. Then, the time-varying patterns of structural response were analyzed, and Lasso regression models and their regression variables were discussed based on monitoring data under two different time scales: daily cycle and annual cycle. The abnormal pattern detection method for bridge structures was developed. Finally, the effectiveness of this method was verified by taking the bridge deck pavement replacement as the abnormal pattern. The research results indicate that the proposed bridge structure abnormal pattern detection method based on Lasso regression can effectively monitor changes in the state of the bridge, and the residual dispersion of the model established on the annual cycle scale is relatively smaller than that on the daily cycle scale, resulting in better abnormal detection performance.

Comparison and analysis of the accuracy of Lasso regression, Ridge regression and Elastic Net regression models in predicting students' teaching quality achievement

In this paper, the "Student Performance Data Set" data set of Kaggle competition is used to conduct correlation analysis on multiple attributes such as students' personal information, school information and students' school performance, and a correlation heat map is drawn. The results show that there is a strong positive correlation among the attributes. We then divided the data set into training, validation, and test sets in a 6:2:2 ratio, and used the Lasso regression model, the Elastic Net model, and the Ridge regression model to make predictions. After training 50 epochs, we evaluated and compared the models. The results show that Lasso regression model has the lowest prediction error and the best error effect. Elastic Net was the next best predictor, while Ridge regression model had the largest prediction error and was the worst. To sum up, Lasso regression model has the best Performance in grade prediction based on the "Student Performance Data Set" dataset. This conclusion is of great significance for schools and educational institutions, as it can help them better understand students' learning and improve the quality and effectiveness of teaching. At the same time, this conclusion is also valuable for data scientists and machine learning researchers, because it can guide them to choose the most appropriate model and algorithm on similar data sets, improving the accuracy and effectiveness of predictions. In general, this paper analyzes and discusses the problem of Student achievement prediction, puts forward the Lasso regression model based on the "Student Performance Data Set" data set, which has the best performance prediction effect, and analyzes the principles of the three models. This conclusion has practical applications for schools and educational institutions, as well as providing a reference for data scientists and machine learning researchers.

A prognostic signature of fatty acid metabolism-related genes for predicting survival of gastric cancer patients.

To analyze the expression profile of fatty acid metabolism (FAM)-related genes, identify a prognostic signature, and evaluate its clinical value for gastric cancer (GC) patients. The mRNA expression profiles of 493 FAM-related genes were obtained from TCGA database. Differentially expressed genes (DEGs) between cancer and non-cancer samples were identified, and their relationships with overall survival (OS) of GC patients were evaluated. A prognostic signature of FAM-related genes was identified by the LASSO regression model, and its predictive performance was tested by an independent external cohort. Ninety-three DEGs were identified, of which 44 were downregulated and 49 were upregulated. After optimizing risk characteristics, a prognostic signature of four FAM-related genes (ACBD5, AVPR1A, ELOVL4, and FAAH) were developed. All patients were divided into high-risk (>1.020) and low-risk groups (≤1.020) on the basis of the median risk score. Survival analysis indicated that high-risk patients had a shorter OS than low-risk patients (5-year OS rate, 26.3% vs. 45.0%, p < 0.001). The AUC values for the prediction of 3-year and 5-year OS were 0.664 and 0.624, respectively. In the GSE62254 data set, the 5-year OS rate of high-risk and low-risk patients were 44.7% versus 61.5%, respectively (p = 0.003). The AUC values were 0.632 and 0.627 at 3-year and 5-year prediction. The prognostic signature of FAM-related genes was an independent predictor of OS (hanzard ratio [HR] for TCGA cohort: 1.851, 95% confidence interval [CI]: 1.394-2.458, p < 0.001; HR for GSE62254: 1.549, 95% CI: 1.098-2.185, p = 0.013). The risk signature of four FAM-related genes was a valuable prognostic tool, and it might be helpful for clinical management and therapeutic decision of gastric cancer patients.

Abstract P185: Plasma Lipidome Signature of Visceral Fat Reveals Heterogenous Cardiometabolic Risk Profiles

Background: Excessive visceral fat is associated with metabolic alterations and is a causal risk factor for CVD. The plasma lipidome is altered in obesity and lipidome signatures of BMI and obesity have been identified. However, few studies have examined the plasma lipidome in relation to visceral fat. Methods: Plasma lipids were measured using the C8-positive LC-MS method in 671 participants from the HERITAGE Family Study (56% Female, 35% Black, 35 yrs). Visceral fat was measured using CT scans. Linear mixed models were used to test the associations of 193 known plasma lipids with visceral fat adjusting for age, sex, race, and BMI. A FDR&lt;5% was used to determine significance. Results: In individual models, 156 lipid species were significantly associated with visceral fat, with 109 species associated after additional adjustment for BMI ( Fig 1 ). The top positively associated lipids were triglycerides, while cholesterol esters showed the strongest inverse associations with visceral fat. A LASSO regression model retained 73 lipids and explained 78.5% of the variance in visceral fat. Delta visceral fat was calculated as the difference between predicted (from LASSO) and measured visceral fat. Examining quartiles of delta visceral fat showed that discordance between predicted and actual visceral fat was associated with differing cardiometabolic profiles independent of age, sex, race, visceral fat, and BMI. Individuals with higher delta visceral fat (Q4, overpredicted) had significantly (p&lt;1.0x10 -04 ) higher levels of TG, apoB, total cholesterol, LDL-C, and fasting insulin and lower levels of large HDL particles and LPL activity compared to those with lower delta visceral fat (Q1, underpredicted). Conclusions: The plasma lipidome is widely associated with visceral fat levels. A lipidome-based visceral fat score may provide additional information over measured visceral fat for assessment of cardiometabolic health. Further studies are needed to test and validate the clinical utility of such lipidome-based scores.

Trend-attribute forecasting of hourly PM2.5 trends in fifteen cities of Central England applying optimized machine learning feature selection

Recorded particulate matter (PM2.5) hourly trends are compared for fifteen urban recording sites distributed across central England for the period 2018 to 2022. They include 10 urban-background and five urban-traffic (roadside) sites with some located within the same urban area. The sites all show consistent background and peak distributions with mean annual values and standard deviations higher for 2018 and 2019 than for 2020 to 2022. The objective of this study is to demonstrate that trend attributes extracted from hourly recorded univariate PM2.5 trends at these sites can be used to provide reliable short-term hourly predictions and provide valuable insight into the regional variations in the recorded trends. Fifteen trend attributes extracted from the prior 12 h (t-1 to t-12) of recorded PM2.5 data were compiled and used as input to four supervised machine learning models (SML) to forecast PM2.5 concentrations up to 13 h ahead (t0 to t+12). All recording sites delivered forecasts with similar ranges of error levels for specific hours ahead which are consistent with their PM2.5 recorded ranges. Forecasting results for four representative sites are presented in detail using models trained and cross-validated with 2020 and 2021 hourly data to forecast 2021 and 2022 hourly data, respectively. A novel optimized feature selection procedure using a suite of five optimizers is used to improve the efficiency of the forecasting models. The LASSO and support vector regression models generate the best and most generalizable hourly PM2.5 forecasts from trained and validated SML models with mean average error (MAE) of between ∼1 and ∼3 μg/m3 for t0 to t+3 h ahead. A novel overfitting indicator, exploiting the cross-validation mean values, demonstrates that these two models are not affected by overfitting. Forecasts for t+6 to t+12 h forward generate higher MAE values between ∼3 and ∼4 μg/m3 due to their tendency to underestimate some of the extreme PM2.5 peaks. These findings indicate that further model refinements are required to generate more reliable short-term predictions for the t+6 to t+24 h ahead.

Predicting dental anxiety in young adults: classical statistical modelling approach versus machine learning approach

ObjectivesTo predict and identify the key demographic and clinical exposure factors associated with dental anxiety among young adults, and to compare if the traditional statistical modelling approach provides similar results to the machine learning (ML) approach in predicting factors for dental anxiety.MethodsA cross-sectional study of Western Illinois University students. Three survey instruments (sociodemographic questionnaire, modified dental anxiety scale (MDAS), and dental concerns assessment tool (DCA)) were distributed via email to the students using survey monkey. The dependent variable was the mean MDAS scores, while the independent variables were the sociodemographic and dental concern assessment variables. Multivariable analysis was done by comparing the classical statistical model and the machine learning model. The classical statistical modelling technique was conducted using the multiple linear regression analysis and the final model was selected based on Akaike information Criteria (AIC) using the backward stepwise technique while the machine learining modelling was performed by comparing two ML models: LASSO regression and extreme gradient boosting machine (XGBOOST) under 5-fold cross-validation using the resampling technique. All statistical analyses were performed using R version 4.1.3.ResultsThe mean MDAS was 13.73 ± 5.51. After careful consideration of all possible fitted models and their interaction terms the classical statistical approach yielded a parsimonious model with 13 predictor variables with Akaike Information Criteria (AIC) of 2376.4. For the ML approach, the Lasso regression model was the best-performing model with a mean RMSE of 0.617, R2 of 0.615, and MAE of 0.483. Comparing the variable selection of ML versus the classical statistical model, both model types identified 12 similar variables (out of 13) as the most important predictors of dental anxiety in this study population.ConclusionThere is a high burden of dental anxiety within this study population. This study contributes to reducing the knowledge gap about the impact of clinical exposure variables on dental anxiety and the role of machine learningin the prediction of dental anxiety. The predictor variables identified can be used to inform public health interventions that are geared towards eliminating the individual clinical exposure triggers of dental anxiety are recommended.

Prediction of metabolic syndrome following a first pregnancy

The prevalence of metabolic syndrome is rapidly increasing in the United States. We hypothesized that prediction models using data obtained during pregnancy can accurately predict the future development of metabolic syndrome. This study aimed to develop machine learning models to predict the development of metabolic syndrome using factors ascertained in nulliparous pregnant individuals. This was a secondary analysis of a prospective cohort study (Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be Heart Health Study [nuMoM2b-HHS]). Data were collected from October 2010 to October 2020, and analyzed from July 2023 to October 2023. Participants had in-person visits 2 to 7 years after their first delivery. The primary outcome was metabolic syndrome, defined by the National Cholesterol Education Program Adult Treatment Panel III criteria, which was measured within 2 to 7 years after delivery. A total of 127 variables that were obtained during pregnancy were evaluated. The data set was randomly split into a training set (70%) and a test set (30%). We developed a random forest model and a lasso regression model using variables obtained during pregnancy. We compared the area under the receiver operating characteristic curve for both models. Using the model with the better area under the receiver operating characteristic curve, we developed models that included fewer variables based on SHAP (SHapley Additive exPlanations) values and compared them with the original model. The final model chosen would have fewer variables and noninferior areas under the receiver operating characteristic curve. A total of 4225 individuals met the inclusion criteria; the mean (standard deviation) age was 27.0 (5.6) years. Of these, 754 (17.8%) developed metabolic syndrome. The area under the receiver operating characteristic curve of the random forest model was 0.878 (95% confidence interval, 0.846-0.909), which was higher than the 0.850 of the lasso model (95% confidence interval, 0.811-0.888; P<.001). Therefore, random forest models using fewer variables were developed. The random forest model with the top 3 variables (high-density lipoprotein, insulin, and high-sensitivity C-reactive protein) was chosen as the final model because it had the area under the receiver operating characteristic curve of 0.867 (95% confidence interval, 0.839-0.895), which was not inferior to the original model (P=.08). The area under the receiver operating characteristic curve of the final model in the test set was 0.847 (95% confidence interval, 0.821-0.873). An online application of the final model was developed (https://kawakita.shinyapps.io/metabolic/). We developed a model that can accurately predict the development of metabolic syndrome in 2 to 7 years after delivery.

Development and Validation of a Nomogram Predicting Postoperative Recurrent Lumbar Disc Herniation Based on Activity Factors.

To develop an individualized predictive model for postoperative recurrent lumbar disc herniation (PRLDH) in patients undergoing percutaneous endoscopic transforaminal discectomy (PETD) by considering postoperative activity factors. Retrospectively collected data from 612 LDH patients who underwent PETD in our institution from January 2017 to June 2023. They were divided into a training group (429 cases) and a validation group (183 cases). Lasso regression (Model 1) and random forest (Model 2) were applied for variable selection in the training group. The two models were compared in terms of discrimination (the area under curve, AUC), calibration (calibration curve), and clinical utility (decision curve analysis, DCA). Akaike information criterion (AIC) was used for model comparison, and internal validation employed 1000 times Bootstrap + 10-fold cross-validation. Finally, a Nomogram was constructed to display the results and uploaded to the web version. Among 612 treated LDH patients, 66 (10.78%) developed PRLDH. Model 1, superior in AUC, calibration, DCA, and AIC over Model 2, was chosen as the predictive model. Logistic regression in the training group identified BMI, smoking, activity level score, time to first ambulation, diabetes, Modic change, and Pfirrmann grade as independent predictors of PRLDH. Model 1 exhibited a training group AUC of 0.813 (95% CI 0.753-0.872) and a validation group AUC of 0.868 (95% CI 0.773-0.962). At a Youden index of 0.50, sensitivity was 0.73, specificity was 0.77. Internal validation (1000 times Bootstrap + 10-fold cross-validation) for the training group showed accuracy of 0.889, kappa consistency of 0.112, and AUC of 0.757. The Hosmer-Lemeshow goodness-of-fit tests indicated good discriminative ability for Model 1 in both the training (χ2=2.895, P=0.941) and validation groups (χ2=8.197, P=0.414). The DCA and Nomogram are accessible at https://sofarnomogram.shinyapps.io/PRLDHNom/. The Nomogram predictive model, developed based on postoperative activity factors in this study, demonstrates excellent predictive capability, facilitating risk assessment for the occurrence of PRLDH after PETD.

A Prognostic Index Derived From LASSO-Selected Preoperative Inflammation and Nutritional Markers for Non–Muscle-Invasive Bladder Cancer

BackgroundThere is an urgent need to identify a robust predictor for BCG response in patients with non–muscle-invasive bladder cancer (NMIBC). We aimed to employ the Lasso regression model for the selection and construction of an index (BCGI) utilizing inflammation and nutrition indicators to predict the response to BCG therapy. MethodsAfter acquiring the ethics approval, we searched the electric medical records in our institution and performed data screening. Then, we developed the BCGI using a Lasso regression model and subsequently evaluated its performance in both the train and internal test datasets through Kaplan-Meier survival curves and Cox regression analysis. Then, we also evaluated the prognostic value of BCGI alongside the EAU2021 model. ResultsThe training dataset and internal test dataset contained 295 and 196 patients, respectively. Referring to the Lasso results, BCGI consisted of hemoglobin, albumin, and platelet count, which could significantly predict the recurrence of NMIBC patients who accepted BCG in train (P = .012) and test (P = .004) datasets. The BCGI also exhibited statistically prognostic value in no smoking history, World Health Organization high grade, and T1 subgroups, both in train and test datasets. In multivariable analysis, BCGI exhibited independent prognostic value in train (P = .012) and test (P = .012) datasets. Finally, we constructed a nomogram that consisted of smoking history, T stage, World Health Organization grade, tumor size, and BCGI. Then, BCGI demonstrated significant independent prognostic value in NMIBC patients treated with BCG, a result not observed with the EAU2021 score or classification. ConclusionBased on the results, we reasonably suggest that BCGI may be a useful predictor for NMIBC patients who accepted BCG. Furthermore, we have demonstrated the efficacy of constructing a prognostic index using clinical factors and a Lasso regression model, a versatile approach applicable to various medical conditions.

Assessment of intracranial aneurysm rupture risk using a point cloud-based deep learning model.

Background and Purpose: Precisely assessing the likelihood of an intracranial aneurysm rupturing is critical for guiding clinical decision-making. The objective of this study is to construct and validate a deep learning framework utilizing point clouds to forecast the likelihood of aneurysm rupturing. Methods: The dataset included in this study consisted of a total of 623 aneurysms, with 211 of them classified as ruptured and 412 as unruptured, which were obtained from two separate projects within the AneuX morphology database. The HUG project, which included 124 ruptured aneurysms and 340 unruptured aneurysms, was used to train and internally validate the model. For external validation, another project named @neurIST was used, which included 87 ruptured and 72 unruptured aneurysms. A standardized method was employed to isolate aneurysms and a segment of their parent vessels from the original 3D vessel models. These models were then converted into a point cloud format using open3d package to facilitate training of the deep learning network. The PointNet++ architecture was utilized to process the models and generate risk scores through a softmax layer. Finally, two models, the dome and cut1 model, were established and then subjected to a comprehensive comparison of statistical indices with the LASSO regression model built by the dataset authors. Results: The cut1 model outperformed the dome model in the 5-fold cross-validation, with the mean AUC values of 0.85 and 0.81, respectively. Furthermore, the cut1 model beat the morphology-based LASSO regression model with an AUC of 0.82. However, as the original dataset authors stated, we observed potential generalizability concerns when applying trained models to datasets with different selection biases. Nevertheless, our method outperformed the LASSO regression model in terms of generalizability, with an AUC of 0.71 versus 0.67. Conclusion: The point cloud, as a 3D visualization technique for intracranial aneurysms, can effectively capture the spatial contour and morphological aspects of aneurysms. More structural features between the aneurysm and its parent vessels can be exposed by keeping a portion of the parent vessels, enhancing the model's performance. The point cloud-based deep learning model exhibited good performance in predicting rupture risk while also facing challenges in generalizability.

Identification of SLC40A1, LCN2, CREB5, and SLC7A11 as ferroptosis-related biomarkers in alopecia areata through machine learning

Alopecia areata (AA) is a common non-scarring hair loss condition driven by the collapse of immune privilege and oxidative stress. The role of ferroptosis, a type of cell death linked to oxidative stress, in AA is yet to be explored, even though it's implicated in various diseases. Using transcriptome data from AA patients and controls from datasets GSE68801 and GSE80342, we aimed to identify AA diagnostic marker genes linked to ferroptosis. We employed Single-sample gene set enrichment analysis (ssGSEA) for immune cell infiltration evaluation. Correlations between ferroptosis-related differentially expressed genes (FRDEGs) and immune cells/functions were identified using Spearman analysis. Feature selection was done through Support vector machine-recursive feature elimination (SVM-RFE) and LASSO regression models. Validation was performed using the GSE80342 dataset, followed by hierarchical internal validation. We also constructed a nomogram to assess the predictive ability of FRDEGs in AA. Furthermore, the expression and distribution of these molecules were confirmed through immunofluorescence. Four genes, namely SLC40A1, LCN2, CREB5, and SLC7A11, were identified as markers for AA. A prediction model based on these genes showed high accuracy (AUC = 0.9052). Immunofluorescence revealed reduced expression of these molecules in AA patients compared to normal controls (NC), with SLC40A1 and CREB5 showing significant differences. Notably, they were primarily localized to the outer root sheath and in proximity to the sebaceous glands. Our study identified several ferroptosis-related genes associated with AA. These findings, emerging from the integration of immune cell infiltration analysis and machine learning, contribute to the evolving understanding of diagnostic and therapeutic strategies in AA. Importantly, this research lays a solid foundation for subsequent studies exploring the intricate relationship between AA and ferroptosis.

Validating core therapeutic targets for osteoporosis treatment based on integrating network pharmacology and informatics

ObjectiveOur goal was to find metabolism-related lncRNAs that were associated with osteoporosis (OP) and construct a model for predicting OP progression using these lncRNAs. MethodsThe GEO database was employed to obtain gene expression profiles. The WGCNA technique and differential expression analysis were used to identify hypoxia-related lncRNAs. A Lasso regression model was applied to select 25 hypoxia-related genes, from which a classification model was created. Its robust classification performance was confirmed with an area under the ROC curve close to 1, as verified on the validation set. Concurrently, we constructed a ceRNA network based on these genes to unveil potential regulatory processes. Biologically active compounds of STZYD were identified using the Traditional Chinese Medicine System Pharmacology Database and Analysis Platform (TCMSP) database. BATMAN was used to identify its targets, and we obtained OP-related genes from Malacards and DisGeNET, followed by identifying intersection genes with metabolism-related genes. A pharmacological network was then constructed based on the intersecting genes. The pharmacological network was further integrated with the ceRNA network, resulting in the creation of a comprehensive network that encompasses herb-active components, pathways, lncRNAs, miRNAs, and targets. Expression levels of hypoxia-related lncRNAs in mononuclear cells isolated from peripheral blood of OP and normal patients were subsequently validated using quantitative real-time PCR (qRT-PCR). Protein levels of RUNX2 were determined through a western blot assay. ResultsCBFB, GLO1, NFKB2 and PIK3CA were identified as central therapeutic targets, and ADD3-AS1, DTX2P1-UPK3BP1-PMS2P11, TTTY1B, ZNNT1 and LINC00623 were identified as core lncRNAs. ConclusionsOur work uncovers a possible therapeutic mechanism for STZYD, providing a potential therapeutic target for OP. In addition, a prediction model of metabolism-related lncRNAs of OP progression was constructed to provide a reference for the diagnosis of OP patients.

Machine learning prediction of factors affecting Major League Baseball (MLB) game attendance: algorithm comparisons and macroeconomic factor of unemployment

PurposeThis study aims to identify an automated machine learning algorithm with high accuracy that sport practitioners can use to identify the specific factors for predicting Major League Baseball (MLB) attendance. Furthermore, by predicting spectators for each league (American League and National League) and division in MLB, the authors will identify the specific factors that increase accuracy, discuss them and provide implications for marketing strategies for academics and practitioners in sport.Design/methodology/approachThis study used six years of daily MLB game data (2014–2019). All data were collected as predictors, such as game performance, weather and unemployment rate. Also, the attendance rate was obtained as an observation variable. The Random Forest, Lasso regression models and XGBoost were used to build the prediction model, and the analysis was conducted using Python 3.7.FindingsThe RMSE value was 0.14, and the R2 was 0.62 as a consequence of fine-tuning the tuning parameters of the XGBoost model, which had the best performance in forecasting the attendance rate. The most influential variables in the model are “Rank” of 0.247 and “Day of the week”, “Home team” and “Day/Night game” were shown as influential variables in order. The result was shown that the “Unemployment rate”, as a macroeconomic factor, has a value of 0.06 and weather factors were a total value of 0.147.Originality/valueThis research highlights unemployment rate as a determinant affecting MLB game attendance rates. Beyond contextual elements such as climate, the findings of this study underscore the significance of economic factors, particularly unemployment rates, necessitating further investigation into these factors to gain a more comprehensive understanding of game attendance.