Development of a Prediction Model and Corresponding Scoring Table for Postherpetic Neuralgia Using Six Machine Learning Algorithms: A Retrospective Study.

To evaluate the value of a machine learning model using enhanced CT radiomics features in the prediction of lymphovascular invasion (LVI) of esophageal squamous cell carcinoma (ESCC) before treatment. We reviewed and analyzed the enhanced CT images of 258 ESCC patients from June 2017 to December 2019. We randomly assigned the patients in a ratio of 7:3 to a training set (182 cases) and a validation (76 cases) set. Clinical risk factors and CT image characteristics were recorded, and multifactor logistic regression was used to screen independent risk factors of LVI of ESCC patients. We extracted the CT radiomics features using the FAE software and screened radiomics features using maximum relevance and minimum redundancy (MRMR) and least absolute shrinkage and selection operator (LASSO) algorithms, and finally, the radiomics labels of each patient were established. Five machine learning algorithms, namely, support vector machine (SVM), K-nearest neighbor (KNN), logistic regression (LR), Gauss naive Bayes (GNB), and multilayer perceptron (MLP), were used to construct the model of radiomics labels, and its clinical features were screened. The predictive efficacy of the machine learning model for LVI of ESCC was evaluated using the receiver operating characteristic (ROC) curve. Tumor thickness [OR = 1.189, 95% confidence interval (CI) 1.060-1.351, P = 0.005], tumor-to-normal wall enhancement ratio (TNR) (OR = 2.966, 95% CI 1.174-7.894, P = 0.024), and clinical N stage (OR = 5.828, 95% CI 1.752-20.811, P= 0.005) were determined as independent risk factors of LVI. We extracted 1,316 features from preoperative enhanced CT images and selected 14 radiomics features using MRMR and LASSO to construct the radiomics labels. In the test set, SVM, KNN, LR, and GNB showed high predictive performance, while the MLP model had poor performance. In the training set, the area under the curve (AUC) values were 0.945 and 0.905 in the KNN and SVM models, but these decreased to 0.866 and 0.867 in the validation set, indicating significant overfitting. The GNB and LR models had AUC values of 0.905 and 0.911 in the training set and 0.900 and 0.893 in the validation set, with stable performance and good fitting and predictive ability. The MLP model had AUC values of 0.658 and 0.674 in the training and validation sets, indicating poor performance. A multiscale combined model constructed using multivariate logistic regression has an AUC of 0.911 (0.870-0.951) and 0.893 (0.840-0.962), accuracy of 84.4% and 79.7%, sensitivity of 90.8% and 87.1%, and specificity of 80.5% and 79.0% in the training and validation sets, respectively. Machine learning models can preoperatively predict the condition of LVI effectively in patients with ESCC based on enhanced CT radiomics features. The GNB and LR models exhibit good stability and may bring a new way for the non-invasive prediction of LVI condition in ESCC patients before treatment.

Chronic Hepatitis B (CHB) is a leading cause of liver fibrosis. Accurate and non-invasive diagnosis of liver fibrosis in CHB patients is of critical clinical importance. This study aimed to develop and validate machine learning (ML)-based models for predicting significant liver fibrosis in CHB patients. This retrospective cohort study included 328 CHB patients (225 with non-significant liver fibrosis and 103 with significant liver fibrosis) from 2017 to 2022. Four ML models were constructed based on four selected features identified through the least absolute shrinkage and selection operator (LASSO) regression. Model performance was assessed using the receiver operating characteristic (ROC) curve, and the area under the curve (AUC), accuracy, sensitivity, specificity, and SHapley Additive exPlanations (SHAP) analysis. The random forest (RF) model demonstrated the highest predictive performance, with an AUC of 0.874 (95% CI: 0.813-0.934) in the training set and 0.863 (95% CI: 0.772-0.955) in the test set, outperforming extreme gradient boosting (XGBoost), logistic regression (LR), and support vector machine (SVM). Compared with the traditional fibrosis indices such as aspartate aminotransferase to platelet ratio index (APRI) (AUC = 0.585) and fibrosis-4 (FIB-4) (AUC = 0.633), the RF model (AUC = 0.863) demonstrated significantly higher predictive accuracy. SHAP analysis identified platelet count (PLT) as the most influential predictor in the RF model. The ML-based RF model offers a highly accurate, non-invasive interpretable tool for predicting significant liver fibrosis in patients with CHB, offering potential for clinical application in routine fibrosis risk assessment.

ObjectiveTo develop an interpretable stacking ensemble model for predicting in-hospital mortality in intensive care unit (ICU) patients with CKD and sepsis and to deploy it as a web-based tool for bedside clinical use.MethodsData were extracted from the MIMIC-IV 3.0 database and split into training and test sets at a 7:3 ratio. Feature selection was performed by combining the least absolute shrinkage and selection operator (LASSO) regression with the Boruta algorithm. Eight machine learning (ML) models were trained and optimized via ten-fold cross-validation and grid search. The two models with the highest area under the curve (AUC) in the training set were combined using a stacking ensemble strategy. SHapley Additive exPlanations (SHAP) were applied to improve interpretability. Model performance was compared with the SOFA score.ResultsA total of 5344 ICU patients with CKD and sepsis were included, with an in-hospital mortality rate of 19.1%. After feature selection, 16 variables were retained. In the training set, XGBoost and LightGBM performed best. The stacking model achieved an AUC of 0.757 on the test set, outperforming SOFA (AUC = 0.668). SHAP analysis identified age, Acute Physiology Score III, Simplified Acute Physiology Score II, and respiratory rate as the top predictors. The model was also deployed as a publicly accessible web application.ConclusionThe stacking ensemble model demonstrated good discriminatory performance and interpretability for predicting in-hospital mortality in ICU patients with CKD and sepsis. Its web-based deployment provides a convenient platform for early risk assessment, although external validation is needed to confirm its broader applicability.

Our study aimed to investigate the potential of radiomics with DCE-MRI for predicting Ki-67 expression in invasive ductal breast cancer. We conducted a retrospective study including 223 patients diagnosed with invasive ductal breast cancer. Radiomics features were extracted from DCE-MRI using 3D-Slicer software. Two Ki-67 expression cutoff values (20% and 29%) were examined. Patients were divided into training (70%) and test (30%) sets. The Elastic Net method selected relevant features, and five machine-learning models were established. Radiomics models were created from intratumoral, peritumoral, and combined regions. Performance was assessed using ROC curves, accuracy, sensitivity, and specificity. For a Ki-67 cutoff value of 20%, the combined model exhibited the highest performance, with area under the curve (AUC) values of 0.838 (95% confidence interval (CI): 0.774-0.897) for the training set and 0.863 (95% CI: 0.764-0.949) for the test set. The AUC values for the tumor model were 0.816 (95% CI: 0.745-0.880) and 0.830 (95% CI: 0.724-0.916), and for the peritumor model were 0.790 (95% CI: 0.711-0.857) and 0.808 (95% CI: 0.682-0.910). When the Ki-67 cutoff value was set at 29%, the combined model also demonstrated superior predictive ability in both training set (AUC: 0.796; 95% CI: 0.724-0.862) and the test set (AUC: 0.823; 95% CI: 0.723-0.911). The AUC values for the tumor model were 0.785 (95% CI: 0.708-0.861) and 0.784 (95% CI: 0.663-0.882), and for the peritumor model were 0.773 (95% CI: 0.690-0.844) and 0.729 (95% CI: 0.603-0.847). Radiomics with DCE-MRI can predict Ki-67 expression in invasive ductal breast cancer. Integrating radiomics features from intratumoral and peritumoral regions yields a dependable prognostic model, facilitating pre-surgical detection and treatment decisions. This holds potential for commercial diagnostic tools.

Background To assess the feasibility of a machine learning (ML) approach using radiomics features of perfusion defects on rest myocardial perfusion imaging (MPI) to detect the presence of hibernating myocardium. Methodology Data of patients who underwent 99mTc-sestamibi MPI and 18F-FDG PET/CT for myocardial viability assessment were retrieved. Rest MPI data were processed on ECToolbox, and polar maps were saved using theNFile PMap tool. The reference standard for defining hibernating myocardium was the presence of mismatched perfusion-metabolism defect with impaired myocardial contractility at rest. Perfusion defects on the polar maps were delineated with regions of interest (ROIs) after spatial resampling and intensity discretization. Replicable random sampling allocated 80% (257) of the perfusion defects of the patients from January 2017 to September 2022 to the training set and the remaining 20% (64) to the validation set. An independent dataset of perfusion defects from 29 consecutive patients from October 2022 to January 2023 was used as the testing set for model evaluation. One hundred ten first and second-order texture features were extracted for each ROI. After feature normalization and imputation, 14 best-ranked features were selected using a multistep feature selection process including the Logistic Regression and Fast Correlation-Based Filter. Thirteen supervised ML algorithms were trained with stratified five-fold cross-validation on the training set and validated on the validation set. The ML algorithms with a Log Loss of <0.688 and <0.672 in the cross-validation and validation steps were evaluated on the testing set. Performance matrices of the algorithms assessed included area under the curve (AUC), classification accuracy (CA), F1 score, precision, recall, and specificity. To provide transparency and interpretability, SHapley Additive exPlanations (SHAP) values were assessed and depicted as beeswarm plots. Results Two hundred thirty-nine patients (214 males; mean age 56 ± 11 years) were enrolled in the study. There were 371 perfusion defects (321 in the training and validation sets; 50 in the testing set). Based on the reference standard, 168 perfusion defects had hibernating myocardium (139 in the training and validation sets; 29 in the testing set). On cross-validation, six ML algorithms with Log Loss <0.688 had AUC >0.800. On validation, 10 ML algorithms had a Log Loss value <0.672, among which six had AUC >0.800. On model evaluation of the selected models on the unseen testing set, nine ML models had AUC >0.800 with Gradient Boosting Random Forest (xgboost) [GB RF (xgboost)] achieving the highest AUC of 0.860 and could detect the presence of hibernating myocardium in 21/29 (72.4%) perfusion defects with a precision of 87.5% (21/24), specificity 85.7% (18/21), CA 78.0% (39/50) and F1 Score 0.792. Four models depicted a clear pattern of model interpretability based on the beeswarm SHAP plots. These were GB RF (xgboost), GB (scikit-learn), GB (xgboost), and Random Forest. Conclusion Our study demonstrates the potential of ML in detecting hibernating myocardium using radiomics features extracted from perfusion defects on rest MPI images. This proof-of-concept underscores the notion that radiomics features capture nuanced information beyond what is perceptible to the human eye, offering promising avenues for improved myocardial viability assessment.

Apply bioinformatics combined with machine learning algorithms to screen potential biomarkers of neonatal sepsis (NS) and explore the correlation between biomarkers and immune cells. Expression profiling data containing NS samples and control samples were downloaded from the Gene Expression Omnibus (GEO) database. First, the differentially expressed genes (DEGs) were found. Then gene set enrichment analysis (GSEA) was carried out to reveal the significantly enriched pathways, and the core genes within these pathways were aggregated. Subsequently, weighted gene co-expression network analysis (WGCNA) was used to identify the gene modules significantly correlated with NS, from which the key genes were screened. The feature genes were selected by the use of three machine learning algorithms: least absolute shrinkage and selection operator (LASSO) regression, support vector machine recursive feature elimination (SVM-RFE), and random forest cross-validation (RF-CV), and then the potential biomarkers of NS were identified by logistic regression analyses. The dataset was randomly split into training and test sets. A logistic regression model with biomarkers was constructed using the training set, and its diagnostic value was evaluated separately on both the training and test sets. In addition, immune infiltration analysis was performed using immune cell deconvolution algorithm CIBERSORT to explore the correlation between biomarkers and immune cells. Overall, after overlapping the filtered DEGs, the core genes of GSEA, and the key genes of WGCNA, we detected 14 intersecting genes. Three machine learning algorithms further selected 4 feature genes, and logistic regression analyses identified ACSL1 and CD3D as potential biomarkers of NS. The classification accuracies of the logistic regression model were 0.883 and 0.902 on the training set and test set, respectively. The area under the curve (AUC) of the receiver operating characteristic curve (ROC) was 0.961 and 0.966, and the calibration curves were close to the ideal curve. It should be noted that these AUC values were estimated within this discovery GEO cohort and require confirmation in independent external cohorts. Immune infiltration analysis showed significant changes (P < 0.05) in the infiltration abundance of 13 immune cell types, and a strong correlation (>0.6) existed between ACSL1, CD3D and neutrophils, naive CD4+ T cells, and CD8+ T cells. ACSL1, CD3D are potential biomarkers of NS and may play an important role in the pathogenesis of NS by modulating immune cell functions such as neutrophils, naive CD4+ T cells, and CD8+ T cells. These conclusions should be regarded as exploratory biomarker discovery rather than diagnostic readiness.

We developed and validated a clinical-radiomics model for preoperative prediction of the short-term efficacy of initial drug-eluting beads transarterial chemoembolization (D-TACE) treatment in patients with hepatocellular carcinoma (HCC). In this retrospective cohort study of 113 patients with intermediate and advanced HCC, 5343 features were extracted based on three sequences of the arterial phase (AP), diffusion-weighted imaging, and T2-weighted images based on contrast-enhanced magnetic resonance imaging, and minimum redundancy maximum correlation and least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection and model construction. Multifactor logistic regression was used to build a clinical-imaging model based on clinical factors and a clinical-radiomics model. The area under the curve (AUC) and calibration curves were used to assess model performance, and the clinical value of the model was analyzed using decision curve analysis. The relationship between the actual and predicted short-term efficacy of the combined model and progression-free survival (PFS) was evaluated using Kaplan-Meier survival curves and log-rank tests. A total of 34 radiomics features were selected by LASSO, and the clinical-radiomics model had the best predictive performance (AUC = 0.902 and AUC = 0.845 for the training and testing sets, respectively), and the model based on AP had the best predictive performance among the four radiomics models (AUC = 0.89 for the training set and AUC = 0.85 for the testing set); the multifactorial logistic regression results showed that microsphere type (p = 0.042) and AP Rad-score (p = 0.01) were associated with short-term efficacy. In addition, a difference in PFS was observed in patients with HCC with different short-term efficacies predicted by the combined model. Moreover, prognosis was better in the objective versus non-objective response group. The combined clinical-radiomics model is an effective predictor of the short-term efficacy of initial D-TACE in patients with HCC, contributing to clinical and economic benefits for patients.

The study aimed to develop and externally validate multiparametric MRI (mpMRI) radiomics-based interpretable machine learning (ML) model for preoperative differentiating between benign and malignant prostate masses. Patients who underwent mpMRI with suspected malignant prostate masses were retrospectively recruited from two independent hospitals between May 2016 and May 2023. The prostate mass regions in T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) MRI images were segmented by ITK-SNAP. PyRadiomics was utilized to extract radiomic features. Inter- and intraobserver correlation analysis, t-test, Spearman correlation analysis, and the least absolute shrinkage and selection operator (LASSO) algorithm with a five-fold cross-validation were applied for feature selection. Five ML learning models were built using the chosen features. Model performance was evaluated with internal and external validation, using area under the curve (AUC), calibration curves, and decision curve analysis to select the optimal model. The interpretability of the most robust model was conducted via SHapley Additive exPlanation (SHAP). A total of 567 patients were enrolled, consisting of the training (n = 352), internal test (n = 152), and external test (n = 63) sets. In total, 2,632 radiomic features were extracted from regions of interest (ROIs) of T2WI and DWI images, which were reduced to 18 via LASSO. Five ML models were established, among which the random forest (RF) model presented the best predictive ability, with AUCs of 0.929 (95% confidential interval [CI]: 0.885-0.963) and 0.852 (95% CI: 0.758-0.934) in the internal and external test sets, respectively. The calibration and decision curve analyses confirmed the excellent clinical usefulness of the RF model. Besides, the contributing relations of the radiomic features were uncovered using SHAP. Radiomic features from mpMRI combined with machine learning facilitate accurate preoperative evaluation of the malignancy in prostate masses. SHAP can disclose the underlying prediction process of the ML model, which may promote its clinical applications.

BackgroundHuman Epidermal Growth Factor Receptor 2 (HER2), a component of the epidermal growth factor receptor family, is thought to be related to advanced prostate cancer (PCa) when overexpressed. Currently, most research on HER2 is limited to molecular pathology, with relatively few studies focused on imaging aspects.ObjectivesTo develop a predictive model by extracting high-throughput radiomics features from magnetic resonance imaging and combining them with clinical characteristics for predicting HER2 overexpression.Materials and methodsA total of 201 patients who underwent radical prostatectomy and HER2 immunohistochemistry were retrospectively enrolled. These patients were randomly divided into a training set (n=160) and a test set (n=41). Multimodal radiomics features extracted from T2-weighted imaging (T2WI) and apparent diffusion coefficient maps (ADC) were selected using Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) with ten-fold cross-validation. Predictive models were developed and evaluated based on discrimination and clinical utility.ResultsThe combined model integrating ISUP Grade, PSA and Radscore achieved an area under the curve (AUC) of 0.841 (95% CI: 0.697-0.955) in the test set, significantly outperforming the clinical model (AUC = 0.580; p = 0.02, DeLong test) and demonstrating a modest improvement over the Radscore model (AUC = 0.838 (0.693-0.951). Evaluation results showed consistent discriminatory power: 0.78 accuracy, 0.77 sensitivity, and 0.79 specificity, indicating well-balanced performance between positive and negative classes. Decision curve analysis and Waterfall plot demonstrated strong clinical applicability.ConclusionThe combined model effectively predicts HER2 overexpression in prostate cancer, with potential to inform more personalized treatment strategies for HER2-overexpressing PCa patients.

The International Association for the Study of Lung Cancer (IASLC) Pathology Committee introduced a histologic grading system for invasive lung adenocarcinoma (LUAD) in 2020. The IASLC grading system, hinging on the evaluation of predominant and high-grade histologic patterns, has proven to be practical and prognostic for invasive LUAD. However, there are still limitations in evaluating the prognosis of stage IA LUAD. Radiomics may serve as a valuable complement. To establish a model that integrates IASLC grading and radiomics, aimed at predicting the prognosis of stage IA LUAD. We conducted a retrospective analysis of 628 patients diagnosed with stage IA LUAD who underwent surgical resection between January 2015 and December 2018 at our institution. The patients were randomly divided into the training set (n=439) and testing set (n=189) at a ratio of 7:3. Overall survival (OS) and disease-free survival (DFS) were taken as the end points. Radiomics features were obtained by PyRadiomics. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO). The prediction models for OS and DFS were developed using multivariate Cox regression analysis, and the models were visualized through nomogram plots. The model's performance was evaluated using area under the curves (AUC), concordance index (C-index), calibration curves, and survival decision curve analysis (DCA). In total, nine radiomics features were selected for the OS prediction model, and 15 radiomics features were selected for the DFS prediction model. Patients with high radiomics scores were associated with a worse prognosis (p<0.001). We built separate prediction models using radiomics or IASLC alone, as well as a combined prediction model. In the prediction of OS, we observed that the combined model (C-index: 0.812±0.024, 3 years AUC: 0.692, 5 years AUC: 0.792) achieved superior predictive performance than the radiomics (C-index: 0.743±0.038, 3 years AUC: 0.633, 5 years AUC: 0.768) and IASLC grading (C-index: 0.765±0.042, 3 years AUC: 0.658, 5 years AUC: 0.743) models alone. Similar results were obtained in the models for DFS. The combination of radiomics and IASLC pathological grading proves to be an effective approach for predicting the prognosis of stage IA LUAD. This has substantial clinical relevance in guiding treatment decisions for early-stage LUAD.

BackgroundThe in-hospital mortality of patients with ST-segment elevation myocardial infarction (STEMI) increases to more than 50% following a cardiogenic shock (CS) event. This study highlights the need to consider the risk of delayed calculation in developing in-hospital CS risk models. This report compared the performances of multiple machine learning models and established a late-CS risk nomogram for STEMI patients.MethodsThis study used logistic regression (LR) models, least absolute shrinkage and selection operator (LASSO), support vector regression (SVM), and tree-based ensemble machine learning models [light gradient boosting machine (LightGBM) and extreme gradient boosting (XGBoost)] to predict CS risk in STEMI patients. The models were developed based on 1,598 and 684 STEMI patients in the training and test datasets, respectively. The models were compared based on accuracy, the area under the curve (AUC), recall, precision, and Gini score, and the optimal model was used to develop a late CS risk nomogram. Discrimination, calibration, and the clinical usefulness of the predictive model were assessed using C-index, calibration plotd, and decision curve analyses.ResultsA total of 2282 STEMI patients recruited between January 1, 2016 and May 31, 2020, were included in the complete dataset. The linear models built using LASSO and LR showed the highest overall predictive power, with an average accuracy over 0.93 and an AUC above 0.82. With a C-index of 0.811 [95% confidence interval (CI): 0.769–0.853], the LASSO nomogram showed good differentiation and proper calibration. In internal validation tests, a high C-index value of 0.821 was achieved. Decision curve analysis (DCA) and clinical impact curve (CIC) examination showed that compared with the previous score-based models, the LASSO model showed superior clinical relevance.ConclusionsIn this study, five machine learning methods were developed for in-hospital CS prediction. The LASSO model showed the best predictive performance. This nomogram could provide an accurate prognostic prediction for CS risk in patients with STEMI.

BackgroundIn recent years, multi-omics models based on a variety of biomarkers have been continuously developed and increasingly applied in the field of oncology, especially in the early diagnosis of lung cancer. This study aimed to integrate computed tomography (CT) radiomics with seven lung cancer-associated autoantibodies (AABs) to develop multi-omics predictive models for pulmonary nodule (PN) characterization.MethodsThis retrospective study enrolled 179 patients with PNs measuring from 5 to 30 mm in diameter who underwent thoracic surgery at Zhongda Hospital, Southeast University between January 2020 and December 2024. The patients were pathologically categorized into lung cancer (n=87) and non-lung cancer (n=92) groups, and then randomly allocated into training and test sets at a ratio of 7 to 3. Least absolute shrinkage and selection operator (LASSO) regression was used for feature screening to construct a clinical model based on five clinical characteristics. A radiomics prediction model was constructed based on the radiomics features identified after delineating the regions of interest and extracting the radiomics features; the rad-score for each patient was calculated to develop a multi-analytic comprehensive model by combining different markers. The diagnostic performances of the models were compared using the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value.ResultsThe multi-omics model demonstrated superior diagnostic accuracy with an AUC of 0.902 [95% confidence interval (CI): 0.817–0.986], accuracy of 82.4%, sensitivity of 88.5%, and specificity of 80.0%, outperforming the clinical (AUC =0.848; 95% CI: 0.777–0.919) and radiomics (AUC =0.854; 95% CI: 0.786–0.922) models. Notably, the radiomics model exhibited high sensitivity (96.6%) but poor specificity (63.6%), while the multi-omics model resolved this trade-off via the synergistic integration of clinical-radiomic-biomarker features, achieving significant improvements in the PPV (81.5% vs. 72.7%) compared to the clinical model.ConclusionsIntegrating CT radiomics with seven lung cancer-AABs established a robust multi-omics framework for PN diagnosis. Compared to the standalone clinical or radiomics models, this comprehensive model demonstrated superior diagnostic performance.

ObjectiveTo evaluate the clinical utility of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-derived clinicoradiological characteristics and intratumoral/peritumoral radiomic features in predicting pathological upgrades (malignant transformation) in high-risk breast lesions.Materials and methodsRetrospectively collected the data of 174 patients with high-risk breast lesions who underwent preoperative breast MRI examinations and were confirmed by biopsy pathology in Shenzhen People’s Hospital between January 1, 2019 and January 1, 2024. The dataset was randomly divided into a training set (n = 121) and a test set (n = 53) at a ratio of 7:3. Initially, during the second stage of DCE-MRI, the region of interest (ROI) was delineated along the maximum cross-section of the lesion, and then automatically expanded outward by 3 mm, 5 mm, and 7 mm as the peritumoral ROIs. The intratumoral, each peritumoral, and the combined intratumoral and peritumoral radiomic models were established respectively. Independent risk factors predictive of malignant upgrades in high-risk lesions were identified through univariate and multivariable logistic regression analyses, which were subsequently incorporated as clinical and imaging characteristics. Finally, a combined model was established by integrating the intratumoral and peritumoral radiomic features with the clinical and imaging features. The performance of each model was analyzed using the receiver operating characteristic (ROC) curves, and the area under the curve (AUC) was calculated.ResultsThe peritumoral 3 mm radiomics model achieved the highest diagnostic performance among all the peritumoral models, with the AUC values of 0.704 and 0.654 for the training and test sets, respectively. In the training set, the combined model showed the highest diagnostic performance (AUC = 0.883), which was superior to that of the clinical and imaging features model (AUC = 0.745, P = 0.003), the intratumoral radiomics model (AUC = 0.791, P = 0.027), the peritumoral 3 mm radiomics model (AUC = 0.704, P = 0.001), and the combined intratumoral and peritumoral radiomic model (AUC = 0.830, P = 0.004). In the test set, the combined model also showed the highest diagnostic performance (AUC = 0.851). The combined model constructed by integrating the intratumoral and peritumoral radiomics features with the clinical and imaging features had the best diagnostic performance, with the sensitivity, specificity, and accuracy of 79.4%, 82.7%, and 81.8% in the training set, and 72.7%, 85.7%, and 83.0% in the test set, respectively.ConclusionThe combined predictive model, which integrates intratumoral and peritumoral radiomic features with clinical and imaging data, exhibited strong diagnostic performance and a clinically applicable nomogram was constructed to stratify individualized upgrade risk, assisting clinicians in making more precise decisions.

BackgroundThis study aimed to construct predictive models for the risk of sepsis in patients with Acute pancreatitis (AP) using machine learning methods and compared optimal one with the logistic regression (LR) model and scoring systems.MethodsIn this retrospective cohort study, data were collected from the Medical Information Mart for Intensive Care III (MIMIC III) database between 2001 and 2012 and the MIMIC IV database between 2008 and 2019. Patients were randomly divided into training and test sets (8:2). The least absolute shrinkage and selection operator (LASSO) regression plus 5-fold cross-validation were used to screen and confirm the predictive factors. Based on the selected predictive factors, 6 machine learning models were constructed, including support vector machine (SVM), K-nearest neighbour (KNN), multi-layer perceptron (MLP), LR, gradient boosting decision tree (GBDT) and adaptive enhancement algorithm (AdaBoost). The models and scoring systems were evaluated and compared using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and the area under the curve (AUC).ResultsA total of 1, 672 patients were eligible for participation. In the training set, 261 AP patients (19.51%) were diagnosed with sepsis. The predictive factors for the risk of sepsis in AP patients included age, insurance, vasopressors, mechanical ventilation, Glasgow Coma Scale (GCS), heart rate, respiratory rate, temperature, SpO2, platelet, red blood cell distribution width (RDW), International Normalized Ratio (INR), and blood urea nitrogen (BUN). The AUC of the GBDT model for sepsis prediction in the AP patients in the testing set was 0.985. The GBDT model showed better performance in sepsis prediction than the LR, systemic inflammatory response syndrome (SIRS) score, bedside index for severity in acute pancreatitis (BISAP) score, sequential organ failure assessment (SOFA) score, quick-SOFA (qSOFA), and simplified acute physiology score II (SAPS II).ConclusionThe present findings suggest that compared to the classical LR model and SOFA, qSOFA, SAPS II, SIRS, and BISAP scores, the machine learning model-GBDT model had a better performance in predicting sepsis in the AP patients, which is a useful tool for early identification of high-risk patients and timely clinical interventions.

Machine Learning-Based Breast Tumor Ultrasound Radiomics for Pre-operative Prediction of Axillary Sentinel Lymph Node Metastasis Burden in Early-Stage Invasive Breast Cancer