Least Absolute Shrinkage And Selection Operator Logistic Regression Research Articles

Predicting risk of the subsequent early pregnancy loss in women with recurrent pregnancy loss based on preconception data

BackgroundFor women who have experienced recurrent pregnancy loss (RPL), it is crucial not only to treat them but also to evaluate the risk of recurrence. The study aimed to develop a risk predictive model to predict the subsequent early pregnancy loss (EPL) in women with RPL based on preconception data.MethodsA prospective, dynamic population cohort study was carried out at the Second Hospital of Lanzhou University. From September 2019 to December 2022, a total of 1050 non-pregnant women with RPL were participated. By December 2023, 605 women had subsequent pregnancy outcomes and were randomly divided into training and validation group by 3:1 ratio. In the training group, univariable screening was performed on RPL patients with subsequent EPL outcome. The least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression were utilized to select variables, respectively. Subsequent EPL prediction model was constructed using generalize linear model (GLM), gradient boosting machine (GBM), random forest (RF), and deep learning (DP). The variables selected by LASSO regression and multivariate logistic regression were then established and compared using the best prediction model. The AUC, calibration curve, and decision curve (DCA) were performed to assess the prediction performances of the best model. The best model was validated using the validation group. Finally, a nomogram was established based on the best predictive features.ResultsIn the training group, the GBM model achieved the best performance with the highest AUC (0.805). The AUC between the variables screened by the LASSO regression (16-variables) and logistic regression (9-variables) models showed no significant difference (AUC: 0.805 vs. 0.777, P = 0.1498). Meanwhile, the 9-variable model displayed a well discrimination performance in the validation group, with an AUC value of 0.781 (95%CI 0.702, 0.843). The DCA showed the model performed well and was feasible for making beneficial clinical decisions. Calibration curves revealed the goodness of fit between the predicted values by the model and the actual values, the Hosmer–Lemeshow test was 7.427, and P = 0.505.ConclusionsPredicting subsequent EPL in RPL patients using the GBM model has important clinical implications. Future prospective studies are needed to verify the clinical applicability.Trial registrationThis study was registered in the Chinese Clinical Trial Registry with the registration number of ChiCTR2000039414 (27/10/2020).

Prediction and analysis of albumin-bilirubin score combined with liver function index and carcinoembryonic antigen on liver metastasis of colorectal cancer.

Colorectal cancer (CRC) is a common malignant tumor, and liver metastasis is one of the main recurrence and metastasis modes that seriously affect patients' survival rate and quality of life. Indicators such as albumin bilirubin (ALBI) score, liver function index, and carcinoembryonic antigen (CEA) have shown some potential in the prediction of liver metastasis but have not been fully explored. To evaluate its predictive value for liver metastasis of CRC by conducting the combined analysis of ALBI, liver function index, and CEA, and to provide a more accurate liver metastasis risk assessment tool for clinical treatment guidance. This study retrospectively analyzed the clinical data of patients with CRC who received surgical treatment in our hospital from January 2018 to July 2023 and were followed up for 24 months. According to the follow-up results, the enrolled patients were divided into a liver metastasis group and a nonliver metastasis group and randomly divided into a modeling group and a verification group at a ratio of 2:1. The risk factors for liver metastasis in patients with CRC were analyzed, a prediction model was constructed by least absolute shrinkage and selection operator (LASSO) logistic regression, internal validation was performed by the bootstrap method, the reliability of the prediction model was evaluated by subject-work characteristic curves, calibration curves, and clinical decision curves, and a column graph was drawn to show the prediction results. Of 130 patients were enrolled in the modeling group and 65 patients were enrolled in the verification group out of the 195 patients with CRC who fulfilled the inclusion and exclusion criteria. Through LASSO regression variable screening and logistic regression analysis. The ALBI score, alanine aminotransferase (ALT), and CEA were found to be independent predictors of liver metastases in CRC patients [odds ratio (OR) = 8.062, 95% confidence interval (CI): 2.545-25.540], (OR = 1.037, 95%CI: 1.004-1.071) and (OR = 1.025, 95%CI: 1.008-1.043). The area under the receiver operating characteristic curve (AUC) for the combined prediction of CRLM in the modeling group was 0.921, with a sensitivity of 78.0% and a specificity of 95.0%. The H-index was 0.921, and the H-L fit curve had χ2 = 0.851, a P value of 0.654, and a slope of the calibration curve approaching 1. This indicates that the model is extremely accurate, and the clinical decision curve demonstrates that it can be applied effectively in the real world. We conducted internal verification of one thousand resamplings of the modeling group data using the bootstrap method. The AUC was 0.913, while the accuracy was 0.869 and the kappa consistency was 0.709. The combination prediction of liver metastasis in patients with CRC in the verification group had an AUC of 0.918, sensitivity of 85.0%, specificity of 95.6%, C-index of 0.918, and an H-L fitting curve with χ 2 = 0.586, P = 0.746. The ALBI score, ALT level, and CEA level have a certain value in predicting liver metastasis in patients with CRC. These three criteria exhibit a high level of efficacy in forecasting liver metastases in patients diagnosed with CRC. The risk prediction model developed in this work shows great potential for practical application.

Predicting CD27 expression and clinical prognosis in serous ovarian cancer using CT-based radiomics

BackgroundThis study aimed to develop and evaluate radiomics models to predict CD27 expression and clinical prognosis before surgery in patients with serous ovarian cancer (SOC).MethodsWe used transcriptome sequencing data and contrast-enhanced computed tomography images of patients with SOC from The Cancer Genome Atlas (n = 339) and The Cancer Imaging Archive (n = 57) and evaluated the clinical significance and prognostic value of CD27 expression. Radiomics features were selected to create a recursive feature elimination-logistic regression (RFE-LR) model and a least absolute shrinkage and selection operator logistic regression (LASSO-LR) model for CD27 expression prediction.ResultsCD27 expression was upregulated in tumor samples, and a high expression level was determined to be an independent protective factor for survival. A set of three and six radiomics features were extracted to develop RFE-LR and LASSO-LR radiomics models, respectively. Both models demonstrated good calibration and clinical benefits, as determined by the receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis. The LASSO-LR model performed better than the RFE-LR model, owing to the area under the curve (AUC) values of the ROC curves (0.829 vs. 0.736). Furthermore, the AUC value of the radiomics score that predicted the overall survival of patients with SOC diagnosed after 60 months was 0.788 using the LASSO-LR model.ConclusionThe radiomics models we developed are promising noninvasive tools for predicting CD27 expression status and SOC prognosis. The LASSO-LR model is highly recommended for evaluating the preoperative risk stratification for SOCs in clinical applications.

Applying LASSO logistic regression for the prediction of biliary complications after ex vivo liver resection and autotransplantation in patients with end-stage hepatic alveolar echinococcosis

BackgroundThe purpose of this study was to explore the relevant risk factors associated with biliary complications (BCs) in patients with end-stage hepatic alveolar echinococcosis (HAE) following ex vivo liver resection and autotransplantation (ELRA) and to establish and visualize a nomogram model.MethodsThis study retrospectively analysed patients with end-stage HAE who received ELRA treatment at the First Affiliated Hospital of Xinjiang Medical University between August 1, 2010 and May 10, 2023. The least absolute shrinkage and selection operator (LASSO) regression model was applied to optimize the feature variables for predicting the incidence of BCs following ELRA. Multivariate logistic regression analysis was used to develop a prognostic model by incorporating the selected feature variables from the LASSO regression model. The predictive ability, discrimination, consistency with the actual risk, and clinical utility of the candidate prediction model were evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Internal validation was performed by the bootstrapping method.ResultsThe candidate prediction nomogram included predictors such as age, hepatic bile duct dilation, portal hypertension, and regular resection based on hepatic segments. The model demonstrated good discrimination ability and a satisfactory calibration curve, with an area under the ROC curve (AUC) of 0.818 (95% CI 0.7417–0.8958). According to DCA, this prediction model can predict the risk of BCs occurrence within a probability threshold range of 9% to 85% to achieve clinical net benefit.ConclusionsA prognostic nomogram with good discriminative ability and high accuracy was developed and validated to predict BCs after ELRA in patients with end-stage HAE.

A Nomogram Prediction Model for Persistent Pulmonary Hypertension of the Newborn in Neonates Hospitalized for the First Time After Birth.

Persistent pulmonary hypertension of the newborn (PPHN) is one of the critical neonatal diseases associated with high morbidity and mortality. This study attempted to conduct a nomogram prediction model for performing early identification of PPHN and providing effective information for clinical practice. A total of 456 newborns who first admitted to the hospital after birth were included in the analysis, including 138 newborns with PPHN and 318 newborns without PPHN (as controls). The optimal predictive variables selection was performed based on LASSO (least absolute shrinkage and selection operator) regression and multivariate logistic regression. Using the selected variables, a nomogram prediction model was developed. To validate the model, the model was assessed using the receiver operating characteristic curve, calibration plot, and clinical impact curve. Six predictors, namely, gestational age, neonatal respiratory distress syndrome, the levels of hemoglobin and creatine kinase-MB, gestational thyroid dysfunction, and Pao2, were identified by LASSO and multivariate logistic regression analysis from the original 30 variables studied. The constructed model, using these predictors, exhibited favorable predictive ability for PPHN, with an area under the receiver operating characteristic of 0.897 (sensitivity = 0.876, specificity = 0.785) in the training set and 0.871 (sensitivity = 0.902, specificity = 0.695) in the validation set, and was well calibrated, as indicated by the PHosmer-Lemeshow test values of 0.233 and 0.876 for the training and validation sets, respectively. The model included gestational age, neonatal respiratory distress syndrome, the levels of hemoglobin and creatine kinase-MB, gestational thyroid dysfunction, and Pao2 had good prediction performance for predicting PPHN among newborns first admitted to the hospital after birth.

Construction and Validation of a MRI‑Based Radiomic Nomogram to Predict Overall Survival in Patients with Local Advanced Cervical Cancer: A Multicenter Study

BackgroundCervical cancer is the fourth most common cancer among women. Radiomics has emerged as a new approach providing valuable information for cancer management. The aim of this study was to construct a radiomics nomogram to accurately predict survival outcomes in patients with locally advanced cervical cancer. MethodsThis retrospective study enrolled a total of 582 locally advanced cervical cancer patients from three center (training cohort: n=228; internal validation cohort: n=98; external validation cohort: n=256). Radiomic features were extracted from pretreatment MRI images. Least absolute shrinkage and selection operator logistic regression (LASSO) was applied to select radiomic features and calculated the radiomic scores. Univariate and multivariate Cox proportional hazards regression analyses were used to identify the independent prognostic clinic-radiological factors for cervical cancer, which were incorporated into the nomogram. ResultsA total of 6 radiomic features were found to be associated with overall survival of locally advanced cervical cancer patients. The AUC of radiomic scores in the training cohort was 0.634-0.708 for the training cohort, 0.725-0.762 for internal validation cohort and 0.788-0.881 for the external validation cohort. Age, parametrial invasion, and radiomic score were the independent prognostic indicators for cervical cancer patients (Age: HR=1.041, 95% CI=1.012-1.071, p=0.006; Parametrial invasion: HR=4.755, 95% CI=1.493-15.144, p=0.008; HR=2.324, 95% CI=1.050-5.143, p=0.037). The nomogram model incorporating these factors showed favorable discrimination in predicting the overall survival rates of cervical cancer patients, with the AUC values of 0.809, 0.808, and 0.862 for 1-, 2-, and 3-year predictions. The decision curve analysis (DCA) indicated that the nomogram model achieved the highest clinical net benefit across the entire range of reasonable threshold probabilities. ConclusionThe nomogram, incorporating clinicopathological factors and radiomic features derived from MRI images, showed satisfactory discrimination in predicting the overall survival rates of locally advanced cervical cancer patients.

Pretreatment mortality risk prediction model in patients with polymyositis/dermatomyositis-associated interstitial lung disease

ObjectivesRisk prediction for patients with polymyositis/dermatomyositis-associated interstitial lung disease (PM/DM-ILD) is challenging due to heterogeneity in the disease course. We aimed to develop a mortality risk prediction model for PM/DM-ILD.MethodsThis...

Dyslipidemia and its associated factors among community adults located in Shangcheng district, Zhejiang province

Dyslipidemia and its associated factors among community adults located in Shangcheng district, Zhejiang province

A nomogram for predicting left atrial thrombus or spontaneous echo contrast in non-valvular atrial fibrillation patients using hemodynamic parameters from transthoracic echocardiography.

Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with a high risk of stroke. This study was designed to investigate the relationship between hemodynamic parameters and left atrial thrombus/spontaneous echo contrast (LAT/SEC) in non-valvular atrial fibrillation (NVAF) patients and establish a predictive nomogram that integrates hemodynamic parameters with clinical predictors to predict the risk of LAT/SEC. From January 2019 to September 2022, a total of 354 consecutive patients with NVAF were enrolled in this cross-sectional study at the First Affiliated Hospital of Guangxi Medical University. To identify the optimal predictive features, we employed least absolute shrinkage and selection operator (LASSO) regression. A multivariate logistic regression model was subsequently constructed, and the results were visualized with a nomogram. We evaluated the model's performance using discrimination, calibration, and the concordance index (C-index). We observed a 38.7% incidence of SEC/TH in NVAF patients. Independent influencing factors of LAT/SEC were identified through LASSO and multivariate logistic regression. Finally, four indicators were included, namely, previous stroke/transient ischaemic attack (OR = 4.25, 95% CI = 1.57-12.23, P = 0.006), left atrial volume index (LAVI) (OR = 1.04, 95% CI = 1.01-1.06, P = 0.001), S/D ratio (OR = 0.27, 95% CI = 0.11-0.59, P = 0.002), and left atrial acceleration factor (OR = 4.95, 95% CI = 2.05-12.79, P = 0.001). The nomogram, which incorporated these four influencing factors, demonstrated excellent predictive ability. The training set had a C-index of 0.878, while the validation set had a C-index of 0.872. Additionally, the calibration curve demonstrated great consistency between the predicted probabilities and the observed outcomes, and the decision curve analysis confirmed the important clinical advantage of the model for patients with NVAF. Our findings indicate that an enlarged left atrium and abnormal hemodynamic parameters in the left atrial and pulmonary veins are linked to a greater risk of LAT/SEC. Previous stroke/transient ischaemic attack, LAVI, the S/D ratio, and left atrial acceleration factor were independently associated with LAT/SEC in NVAF patients. With the incorporation of these four variables, the developed nomogram effectively predicts the risk of LAT/SEC and outperforms the CHA2DS2-VASc score.

A combined analysis of TyG index, SII index, and SIRI index: positive association with CHD risk and coronary atherosclerosis severity in patients with NAFLD.

Insulin resistance(IR) and inflammation have been regarded as common potential mechanisms in coronary heart disease (CHD) and non-alcoholic fatty liver disease (NAFLD). Triglyceride-glucose (TyG) index is a novel biomarker of insulin resistance, System immune-inflammation index(SII) and Systemic inflammation response index(SIRI) are novel biomarkers of inflammation, these biomarkers have not been studied in CHD with NAFLD patients. This study investigated the correlation between the TyG index, SII index, and SIRI index and CHD risk among NAFLD patients. This cross-sectional study included 407 patients with NAFLD in the Department of Cardiology, The Second Hospital of Shanxi Medical University. Of these, 250 patients with CHD were enrolled in the NAFLD+CHD group and 157 patients without CHD were enrolled as NAFLD control. To balance covariates between groups, 144 patients were selected from each group in a 1:1 ratio based on propensity score matching (PSM). Potential influences were screened using Lasso regression analysis. Univariate and multivariate logistic regression analyses and the Least Absolute Shrinkage and Selection Operator (LASSO) regression were used to assess independent risk and protective factors for CHD. Construction of nomogram using independent risk factors screened by machine learning. The receiver operating characteristic(ROC) curve was used to assess the ability of these independent risk factors to predict coronary heart disease. The relationship between the Gensini score and independent risk factors was reflected using the Sankey diagram. The LASSO logistic regression analysis and Logistic regression analyses suggest that TyG index (OR, 2.193; 95% CI, 1.242-3.873; P = 0.007), SII index (OR, 1.002; 95% CI, 1.001-29 1.003; P <0.001), and SIRI index (OR,1.483;95%CI,1.058-2.079,P=0.022) are independent risk factors for CHD. At the same time, Neutrophils, TG, and LDL-C were also found to be independent risk factors in patients, HDL-C was a protective factor for CHD in patients with NAFLD. Further analysis using three machine learning algorithms found these independent risk factors to have good predictive value for disease diagnosis, SII index shows the highest predictive value. ROC curve analysis demonstrated that combining the SII index, SIRI index, and TyG index can improve the diagnostic ability of non-alcoholic liver cirrhosis patients with CHD.ROC curve analysis showed that the combined analysis of these independent risk factors improved the predictive value of CHD(AUC: 0.751; 95% CI: 0.704-0.798; P <0.001). TyG index, SII index, and SIRI index are all independent risk factors for CHD in patients with NAFLD and are strongly associated with prediction and the severity of CHD.

UTILIZATION OF LASSO AND POISSON REGRESSION DEALING WITH COUNT VARIABLES IN NURSING HOME RESEARCH

Abstract Regression has been used for decades; thus, more empirical studies are necessary to choose appropriate regression methods, as traditional regression has many drawbacks and is limited in analysis and synthesis with large numbers of covariates. This study aims to investigate factors related to pressure ulcers in nursing homes using three regressions: least absolute shrinkage and selection operator (LASSO) Poisson, LASSO linear, and LASSO logistic regression. We represent how each model’s estimating, inferencing, and performance measures work. The datasets accrued from 51 nursing homes that operated between 2021 and 2022. A total of 35 independent variables included organizational and nurse staffing variables. The variable of interest was the number of residents in each nursing home who had an occurrence of pressure ulcers within the last 3 months. The significant factors were different; turnover of Certified Nurse Aides and government incentives of more RNs were significant in the LASSO Poison regression, no factors were significant in the LASSO Linear regression, while and the percentage of residents who are completely dependent for activities of daily living in LASSO was significant factor in the Logistic regression. Using the coefficients in the Poisson regression, we interpreted that more nursing staff turnover increased the percentage of residents with pressure ulcers by 3.02 times, which would not be possible with linear regression. The Lasso model uses a technique of shrinking coefficient estimates to zero to improve the fit of a model that includes all explanatory variables and improves model interpretability by identifying most important features.

Machine learning-based model for predicting major adverse cardiovascular and cerebrovascular events in patients aged 65 years and older undergoing noncardiac surgery

BackgroundFew evidence-based prediction models have been developed for predicting major adverse cardiovascular and cerebrovascular events (MACCE) in patients aged 65 years or older undergoing noncardiac surgery. In this study, we aimed to analyze the risk factors for perioperative MACCE in patients aged 65 years or older undergoing noncardiac surgery and construct a prediction model.MethodsIn this nested case–control study, a total of 342 Chinese patients who were aged ≥ 65 years and underwent medium- or high-risk noncardiac surgery in our hospital were included. There were 84 cases with MACCE (the MACCE group) and 258 without MACCE (the control group). Univariable logistic regression analysis was performed to identify the risk factors for MACCE. Least absolute shrinkage and selection operator (LASSO) regression was used to screen the variables. Nomogram was constructed using the selected variables. Machine learning methods, including Decision Tree, XGBoost, Support Vector Machine, K-nearest Neighbor, and Neural network, was used to establish, validate, and compare the performance of different prediction models.ResultsA prediction model based on nine variables, including age ≥ 85 years, history of ischemic chest pain, symptoms of decompensated heart failure, high-risk surgery, intraoperative minimum systolic blood pressure, postoperative systolic blood pressure, Cr levels over 2.0 mg/dL, left ventricular ejection fraction, and perioperative blood transfusion, was constructed. This LASSO logistic regression model showed good discriminatory ability to predict MACCE (area under the curve = 0.89; 95% confidence interval, 0.818 – 0.963) and fit to the test set (Hosmer–Lemeshow, χ2 = 7.4053, P = 0.4936). The decision curve analysis showed a positive net benefit of the new model. Compared with logistic regression model, the XGBoost model showed better prediction ability (area under the curve = 0.903). A preoperative prediction model based on five variables, including age ≥ 85 years, symptoms of decompensated heart failure, ischemic chest pain, high-risk type of surgery and Cr levels over 2.0 mg/dL was also constructed. This model showed good discriminatory ability to predict MACCE before surgery (area under the curve = 0.720 [95% CI, 0.591–0.848]. Both models compared with the modified RCRI score had improvement in reclassification.ConclusionBy analyzing Chinese patients aged ≥ 65 years undergoing medium- or high-risk noncardiac surgery, the risk factors for perioperative MACCE were identified. Then, simple prediction models were constructed and validated, which showed good prediction performance and may be used as a decision-making assistant tool for clinicians. These findings provide a basis for preventing and improving the perioperative management of MACCE.

Applications of Machine Learning to Diagnosis of Parkinson's Disease.

Accurate diagnosis of Parkinson's disease (PD) is challenging due to its diverse manifestations. Machine learning (ML) algorithms can improve diagnostic precision, but their generalizability across medical centers in China is underexplored. To assess the accuracy of an ML algorithm for PD diagnosis, trained and tested on data from different medical centers in China. A total of 1656 participants were included, with 1028 from Beijing (training set) and 628 from Fuzhou (external validation set). Models were trained using the least absolute shrinkage and selection operator-logistic regression (LASSO-LR), decision tree (DT), random forest (RF), eXtreme gradient boosting (XGboost), support vector machine (SVM), and k-nearest neighbor (KNN) techniques. Hyperparameters were optimized using five-fold cross-validation and grid search techniques. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, accuracy, sensitivity (recall), specificity, precision, and F1 score. Variable importance was assessed for all models. SVM demonstrated the best differentiation between healthy controls (HCs) and PD patients (AUC: 0.928, 95% CI: 0.908-0.947; accuracy: 0.844, 95% CI: 0.814-0.871; sensitivity: 0.826, 95% CI: 0.786-0.866; specificity: 0.861, 95% CI: 0.820-0.898; precision: 0.849, 95% CI: 0.807-0.891; F1 score: 0.837, 95% CI: 0.803-0.868) in the validation set. Constipation, olfactory decline, and daytime somnolence significantly influenced predictability. We identified multiple pivotal variables and SVM as a precise and clinician-friendly ML algorithm for prediction of PD in Chinese patients.

Gene Expression and Metadata Based Identification of Key Genes for Hepatocellular Carcinoma Using Machine Learning and Statistical Models.

Biomarkers associated with hepatocellular carcinoma (HCC) are of great importance to better understand biological response mechanisms to internal or external intervention. The study aimed to identify key candidate genes for HCC using machine learning (ML) and statistics-based bioinformatics models. Differentially expressed genes (DEGs) were identified using limma and then selected their common genes among DEGs identified from four datasets. After that, protein-protein interaction networks were constructed using STRING and then Cytoscape was used to determine hub genes, significant modules, and their associated genes. Simultaneously, three ML-based techniques such as support vector machine (SVM), least absolute shrinkage and selection operator-logistic regression (LASSO-LR), and partial least squares-discriminant analysis (PLS-DA) were implemented to determine the discriminative genes of HCC from common DEGs. Moreover, metadata of hub genes were formed by listing all hub genes from existing studies to incorporate other findings in our analysis. Finally, seven key candidate genes (ASPM, CCNB1, CDK1, DLGAP5, KIF20 A, MT1X, and TOP2A) were identified by intersecting common genes among hub genes, significant modules genes, discriminative genes from SVM, LASSO-LR, and PLS-DA, and meta hub genes from existing studies. Another three independent test datasets were also used to validate these seven key candidate genes using AUC, computed from ROC.

Establishment of a prediction model for prehospital return of spontaneous circulation in out-of-hospital patients with cardiac arrest.

Out-of-hospital cardiac arrest (OHCA) is a leading cause of death worldwide. To explore factors influencing prehospital return of spontaneous circulation (P-ROSC) in patients with OHCA and develop a nomogram prediction model. Clinical data of patients with OHCA in Shenzhen, China, from January 2012 to December 2019 were retrospectively analyzed. Least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression were applied to select the optimal factors predicting P-ROSC in patients with OHCA. A nomogram prediction model was established based on these influencing factors. Discrimination and calibration were assessed using receiver operating characteristic (ROC) and calibration curves. Decision curve analysis (DCA) was used to evaluate the model's clinical utility. Among the included 2685 patients with OHCA, the P-ROSC incidence was 5.8%. LASSO and multivariate logistic regression analyses showed that age, bystander cardiopulmonary resuscitation (CPR), initial rhythm, CPR duration, ventilation mode, and pathogenesis were independent factors influencing P-ROSC in these patients. The area under the ROC was 0.963. The calibration plot demonstrated that the predicted P-ROSC model was concordant with the actual P-ROSC. The good clinical usability of the prediction model was confirmed using DCA. The nomogram prediction model could effectively predict the probability of P-ROSC in patients with OHCA.

Predicting the prognosis of lung cancer patients treated with intensity-modulated radiotherapy based on radiomic features.

This study aimed to develop a method for predicting short-term outcomes of lung cancer patients treated with intensity-modulated radiotherapy (IMRT) using radiomic features detected through computed tomography images. A prediction model was developed based on a dataset of radiomic features obtained from 132 patients with lung cancer receiving IMRT. Dimension reduction was performed for the features using the maximum-relevance and minimum-redundancy (mRMR) algorithm, and the least absolute shrinkage and selection operator (LASSO) regression model was utilized to optimize feature selection for the IMRT-sensitivity prediction model. The model was constructed using binary logistic regression analysis and was evaluated using the concordance index (C-index), calibration plots, receiver operating characteristic curve, and decision curve analysis. Fifty features were selected from 1348 radiomic features using the mRMR method. Of these, three radiomic features were selected by LASSO logistic regression to construct the radiomics nomogram. The C-index of the model was 0.776 (95% confidence interval: 0.689-0.862) and 0.791 (95% confidence interval: 0.607-0.974) in the training and validation cohorts, respectively. Decision curve analysis showed that the radiomics nomogram was clinically useful. Radiomic features have the potential to be applied to predict the short-term efficacy of IMRT in patients with inoperable lung cancer.

Development and validation of radiomics models for the prediction of diagnosis of classic trigeminal neuralgia.

The study aims to develop a magnetic resonance imaging (MRI)-based radiomics model for the diagnosis of classic trigeminal neuralgia (cTN). This study involved 350 patients with cTN and 100 control participants. MRI data were collected retrospectively for all the enrolled subjects. The symptomatic side trigeminal nerve regions of patients and both sides of the trigeminal nerve regions of control participants were manually labeled on MRI images. Radiomics features of the areas labeled were extracted. Principle component analysis (PCA) and least absolute shrinkage and selection operator (LASSO) regression were utilized as the preliminary feature reduction methods to decrease the high dimensionality of radiomics features. Machine learning methods were established, including LASSO logistic regression, support vector machine (SVM), and Adaboost methods, evaluating each model's diagnostic abilities using 10-fold cross-validation. All the models showed excellent diagnostic ability in predicting trigeminal neuralgia. A prospective study was conducted, 20 cTN patients and 20 control subjects were enrolled to validate the clinical utility of all models. Results showed that the radiomics models based on MRI can predict trigeminal neuralgia with high accuracy, which could be used as a diagnostic tool for this disorder.

Identifying potential biomarkers of idiopathic pulmonary fibrosis through machine learning analysis

Idiopathic pulmonary fibrosis (IPF) is the most common and serious type of idiopathic interstitial pneumonia, characterized by chronic, progressive, and low survival rates, while unknown disease etiology. Until recently, patients with idiopathic pulmonary fibrosis have a poor prognosis, high mortality, and limited treatment options, due to the lack of effective early diagnostic and prognostic tools. Therefore, we aimed to identify biomarkers for idiopathic pulmonary fibrosis based on multiple machine-learning approaches and to evaluate the role of immune infiltration in the disease. The gene expression profile and its corresponding clinical data of idiopathic pulmonary fibrosis patients were downloaded from Gene Expression Omnibus (GEO) database. Next, the differentially expressed genes (DEGs) with the threshold of FDR < 0.05 and |log2 foldchange (FC)| > 0.585 were analyzed via R package “DESeq2” and GO enrichment and KEGG pathways were run in R software. Then, least absolute shrinkage and selection operator (LASSO) logistic regression, support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF) algorithms were combined to screen the key potential biomarkers of idiopathic pulmonary fibrosis. The diagnostic performance of these biomarkers was evaluated through receiver operating characteristic (ROC) curves. Moreover, the CIBERSORT algorithm was employed to assess the infiltration of immune cells and the relationship between the infiltrating immune cells and the biomarkers. Finally, we sought to understand the potential pathogenic role of the biomarker (SLAIN1) in idiopathic pulmonary fibrosis using a mouse model and cellular model. A total of 3658 differentially expressed genes of idiopathic pulmonary fibrosis were identified, including 2359 upregulated genes and 1299 downregulated genes. FHL2, HPCAL1, RNF182, and SLAIN1 were identified as biomarkers of idiopathic pulmonary fibrosis using LASSO logistic regression, RF, and SVM-RFE algorithms. The ROC curves confirmed the predictive accuracy of these biomarkers both in the training set and test set. Immune cell infiltration analysis suggested that patients with idiopathic pulmonary fibrosis had a higher level of B cells memory, Plasma cells, T cells CD8, T cells follicular helper, T cells regulatory (Tregs), Macrophages M0, and Mast cells resting compared with the control group. Correlation analysis demonstrated that FHL2 was significantly associated with the infiltrating immune cells. qPCR and western blotting analysis suggested that SLAIN1 might be a signature for the diagnosis of idiopathic pulmonary fibrosis. In this study, we identified four potential biomarkers (FHL2, HPCAL1, RNF182, and SLAIN1) and evaluated the potential pathogenic role of SLAIN1 in idiopathic pulmonary fibrosis. These findings may have great significance in guiding the understanding of disease mechanisms and potential therapeutic targets in idiopathic pulmonary fibrosis.

Developing a prediction model of children asthma risk using population-based family history health records.

Identifying children at high risk of developing asthma can facilitate prevention and early management strategies. We developed a prediction model of children's asthma risk using objectively collected population-based children and parental histories of comorbidities. We conducted a retrospective population-based cohort study using administrative data from Manitoba, Canada, and included children born from 1974 to 2000 with linkages to ≥1 parent. We identified asthma and prior comorbid condition diagnoses from hospital and outpatient records. We used two machine-learning models: least absolute shrinkage and selection operator (LASSO) logistic regression (LR) and random forest (RF) to identify important predictors. The predictors in the base model included children's demographics, allergic conditions, respiratory infections, and parental asthma. Subsequent models included additional multiple comorbidities for children and parents. The cohort included 195,666 children: 51.3% were males and 17.7% had asthma diagnosis. The base LR model achieved a low predictive performance with sensitivity of 0.47, 95% confidence interval (0.45-0.48), and specificity of 0.67 (0.66-0.67) using a predicted probability threshold of 0.20. Sensitivity significantly improved when children's comorbidities were included using LASSO LR: 0.71 (0.69-0.72). Predictive performance further improved by including parental comorbidities (sensitivity = 0.72 [0.70-0.73], specificity = 0.69 [0.69-0.70]). We observed similar results for the RF models. Children's menstrual disorders and mood and anxiety disorders, parental lipid metabolism disorders and asthma were among the most important variables that predicted asthma risk. Including children and parental comorbidities to children's asthma prediction models improves their accuracy.

Diagnosis of Early Bacterial Pneumonia and Sepsis After Cardiovascular Surgery: A Diagnostic Prediction Model Based on LASSO Logistic Regression.

Early postoperative bacterial pneumonia and sepsis (ePOPS), which occurs within the first 48 hours after cardiovascular surgery, is a serious life-threatening complication. Diagnosis of ePOPS is extremely challenging, and the existing diagnostic tools are insufficient. The purpose of this study was to construct a novel diagnostic prediction model for ePOPS. Least Absolute Shrinkage and Selection Operator (LASSO) with logistic regression was used to construct a model to diagnose ePOPS based on patients' comorbidities, medical history, and laboratory findings.The area under the receiver operating characteristic curve (AUC) was used to evaluate the model discrimination. A total of 1203 patients were recruited and randomly split into a training and validation set in a 7:3 ratio. By early morning on the 3rd postoperative day (POD3), 103 patients had experienced 133 episodes of bacterial pneumonia or sepsis (15 patients had both). LASSO logistic regression model showed that duration of mechanical ventilation (P=0.015), NYHA class ≥ III (P=0.001), diabetes (P<0.001), exudation on chest radiograph (P=0.011) and IL-6 on POD3 (P<0.001) were independent risk factors. Based on these factors, we created a nomogram named DICS-I with an AUC of 0.787 in the training set and 0.739 in the validation set. The DICS-I model may be used to predict the risk of ePOPS after cardiovascular surgery, and is also especially suitable for predicting the risk of IRAO. The DICS-I model could help clinicians to adjust antibiotics on the POD3.