Areas Under The ROC Curve Research Articles

The diagnostic efficiency of artificial intelligence based 2 hours Holter monitoring in premature ventricular and supraventricular contractions detection.

Electrocardiography (ECG) and 24 hours Holter monitoring (24 h-Holter) provided valuable information for premature ventricular and supraventricular contractions (PVC and PSVC). Currently, artificial intelligence (AI) based 2 hours single-lead Holter (2 h-Holter) monitoring may provide an improved strategy for PSVC/PVC diagnosis. AI combined with single-lead Holter monitoring improves PSVC/PVC detection. In total, 170 patients were enrolled between August 2022 and 2023. All patients wore both devices simultaneously; then, we compared diagnostic efficiency, including the sensitivity/specificity/positive predictive-value (PPV) and negative predictive-value (NPV) in detecting PSVC/PVC by 24 h-Holter and 2 h-Holter. The PPV and NPV in patients underwent 2 h-Holter were 76.00%/87.50% and 96.35%/98.55, respectively, and the sensitivity and specificity were 79.17%/91.30%, and 95.65%/97.84% in PSVC/PVC detection compared with 24 h-Holter. The areas under the ROC curves (AUCs) for PSVC and PVC were 0.885 and 0.741, respectively (p < .0001). The potential advantages of the 2 h-Holter were shortened wearing period, improved convenience, and excellent consistency of diagnosis.

Soluble Programmed Cell Death 1 Protein Is a Promising Biomarker to Predict Severe Liver Inflammation in Chronic Hepatitis B Patients.

Background and Aims: Liver inflammation is important in guiding the initiation of antiviral treatment and affects the progression of chronic hepatitis B(CHB). The soluble programmed cell death 1 protein (sPD-1) was upregulated in inflammatory and infectious diseases and correlated with disease severity. We aimed to investigate the correlation between serum sPD-1 levels and liver inflammation in CHB patients and their role in indicating liver inflammation. Methods: 241 CHB patients who underwent liver biopsy were enrolled. The correlation between sPD-1 levels and the degree of liver inflammation was analyzed. Univariate and multivariate logistic regression analyses were performed to analyze independent variables of severe liver inflammation. Binary logistic regression analysis was conducted to construct a predictive model for severe liver inflammation, and the receiver operating characteristic curve (ROC) was used to evaluate the diagnostic accuracy of the predictive model. Results: sPD-1 was highest in CHB patients with severe liver inflammation, which was higher than that in CHB patients with mild or moderate liver inflammation (P < 0.001). Besides, sPD-1 was weakly correlated with AST (r = 0.278, P < 0.001). Multivariable analysis showed that sPD-1 was an independent predictor of severe liver inflammation. The predictive model containing sPD-1 had areas under the ROC (AUROCs) of 0.917 and 0.921 in predicting severe liver inflammation in CHB patients and CHB patients with ALT ≤ 1× upper limit of normal (ULN), respectively. Conclusions: Serum sPD-1 level is associated with liver inflammation in CHB patients, and high levels of sPD-1 reflect severe liver inflammation. Serum sPD-1 is an independent predictor of severe liver inflammation and shows improved diagnostic accuracy when combined with other clinical indicators.

Serum cholesterol level as a predictive biomarker for prognosis of Neuroblastoma

BackgroundNeuroblastoma (NB), a type of solid tumor in children, has a poor prognosis. Few blood biomarkers can accurately predict the prognosis, including recurrence and survival, in children with NB. In this study, we found that the serum total cholesterol (Tchol) level was associated with the prognosis of patients through a retrospective study.MethodsMultivariate Cox regression model was used to identify the independent risk factors in the children with NB. Kaplan–Meier method was used to analyze the correlation between the common biomarkers, including the serum Tchol level, and the prognosis of the patients. ROC curves were used to predict the accuracy of the International Neuroblastoma Staging System (INSS) stage and Children’s Oncology Group (COG) risk stratification after adding the serum Tchol level.ResultsCompared with the other patients, serum Tchol level was significantly increased in the relapsed and died patients (P < 0.05). Subsequently, serum Tchol level was found as an independent risk factor to affect the outcome of patients (P < 0.05). Finally, we added serum Tchol level into traditional stage and risk classification system to form the new INSS stage and COG risk classification system. It was found that the areas under the ROC curve (AUC) of recurrence-free survival in the new INSS stage and COG risk classification system were increased to 0.691 (95%CI: 0.535–0.847) and 0.748 (95%CI: 0.622–0.874), respectively. Moreover, the AUC areas of overall survival in the new INSS stage and COG risk classification system were increased to 0.722 (95%CI: 0.561–0.883) and 0.668 (95%CI: 0.496–0.819), respectively.ConclusionWe found that serum Tchol level, a clinical biomarker, is a risk factor for recurrence and death among the children with NB. The serum Tchol level could significantly increase the accuracy of the prediction for NB prognosis.

Evaluation of Optic Nerve Head Microcirculation in Open-Angle Glaucoma Patients with Unilateral Visual Field Defect

Introduction: Microcirculation of optic nerve head (ONH) in open-angle glaucoma (OAG) patients with unilateral visual field (VF) loss has yet to be fully investigated, especially the perimetrically unaffected fellow eyes. Methods: Thirty-eight OAG patients with VF defect in one eye and normal VF in the other eye, and thirty-one healthy participants were analyzed. All participants underwent laser speckle flowgraphy (LSFG), spectral-domain optical coherence tomography (SD-OCT) imaging, and VF test for further analyses. LSFG measurements included mean blur rate in all area of ONH (MA), big vessel area of ONH (MV), and tissue area of ONH (MT). SD-OCT parameters included circumpapillary retinal nerve fiber layer (cpRNFL) thickness and macula thicknesses. The difference of LSFG and SD-OCT indices between glaucoma patients and healthy controls were compared. The diagnostic accuracy was analyzed with the areas under the receiver operating characteristic curves (AROCs). Results: Global cpRNFL thickness and macular thickness in unaffected eyes of OAG patients were higher than their fellow eyes and lower than healthy eyes. MA and MV in healthy eyes and unaffected eyes were significantly higher than in affected eyes. MT in unaffected eyes of OAG patients was higher than in their fellow affected eyes but lower than in healthy eyes. The AROCs were highest for cpRNFL (0.925), followed by macular thickness (0.838), and MT (0.834). Conclusions: ONH microcirculation in perimetrically unaffected fellow eyes was decreased in OAG patients with unilateral VF loss. LSFG can detect changes of ONH in high-risk eyes before detectable VF damage, which may reflect the vascular pathophysiology for glaucoma.

Comparison of waist circumference and waist-to-height ratio as predictors of clustering of cardiovascular risk factors among middle-aged people in rural Khanh Hoa, Vietnam.

Given the population-level variation in stature, a universal cut-off for waist circumference (WC) may not be appropriate for some populations. We compared the performance of WC and waist-to-height ratio (WHtR) to detect the clustering of cardiovascular disease (CVD) risk factors in rural Vietnam. We obtained data from a baseline survey of the Khanh Hoa Cardiovascular Study comprising 2942 middle-aged residents (40-60 years). We used areas under the receiver operating characteristics curve (AUROC), net reclassification index (NRI), and integrated discrimination improvement (IDI) to compare the performance of WC and WHtR in predicting CVD risk clustering (≥2 of the following risk factors: hypertension, diabetes, dyslipidemia, and elevated C-reactive protein). The optimal cut-off values for WC were 81.8 and 80.7 cm for men and women, respectively. Regarding the clustering of CVD risk factors, the AUROC (95% CI) of WC and WHtR were 0.707 (0.676 to 0.739) and 0.719 (0.689 to 0.749) in men, and 0.682 (0.654 to 0.709) and 0.690 (0.663 to 0.717) in women, respectively. Compared with WC, WHtR had a better NRI (0.229; 0.102-0.344) and IDI (0.012; 0.004-0.020) in men and a better NRI (0.154; 0.050-0.257) in women. The optimal WC cut-off for Vietnamese men was approximately 10 cm below the recommended Asian cut-off. WHtR might perform slightly better in predicting the clustering of CVD risk factors among the rural population in Vietnam.

Serum ITIH5 as a novel diagnostic biomarker in cholangiocarcinoma.

Cholangiocarcinoma often remains undetected until advanced stages due to the lack of reliable diagnostic markers. Our goal was to identify a unique secretory protein for cholangiocarcinoma diagnosis and differentiation from other malignancies, benign hepatobiliary diseases, and chronic liver conditions. We conducted bulk RNA-seq analysis to identify genes specifically upregulated in cholangiocarcinoma but not in most other cancers, benign hepatobiliary diseases, and chronic liver diseases focusing on exocrine protein-encoding genes. Single-cell RNA sequencing examined subcellular distribution. Immunohistochemistry and enzyme-linked immunosorbent assays assessed tissue and serum expression. Diagnostic performance was evaluated via receiver-operating characteristic (ROC) analysis. Inter-alpha-trypsin inhibitor heavy chain family member five (ITIH5), a gene encoding an extracellular protein, is notably upregulated in cholangiocarcinoma. This elevation is not observed in most other cancer types, benign hepatobiliary diseases, or chronic liver disorders. It is specifically expressed by malignant cholangiocytes. ITIH5 expression in cholangiocarcinoma tissues exceeded that in nontumorous bile duct, hepatocellular carcinoma, and nontumorous hepatic tissues. Serum ITIH5 levels were elevated in cholangiocarcinoma compared with controls (hepatocellular carcinoma, benign diseases, chronic hepatitis B, and healthy individuals). ITIH5 yielded areas under the ROC curve (AUCs) from 0.839 to 0.851 distinguishing cholangiocarcinoma from controls. Combining ITIH5 with carbohydrate antigen 19-9 (CA19-9) enhanced CA19-9's diagnostic effectiveness. In conclusion, serum ITIH5 may serve as a novel noninvasive cholangiocarcinoma diagnostic marker.

Identifying key factors for predicting O6-Methylguanine-DNA methyltransferase status in adult patients with diffuse glioma: a multimodal analysis of demographics, radiomics, and MRI by variable Vision Transformer

PurposeThis study aimed to perform multimodal analysis by vision transformer (vViT) in predicting O6-methylguanine-DNA methyl transferase (MGMT) promoter status among adult patients with diffuse glioma using demographics (sex and age), radiomic features, and MRI.MethodsThe training and test datasets contained 122 patients with 1,570 images and 30 patients with 484 images, respectively. The radiomic features were extracted from enhancing tumors (ET), necrotic tumor cores (NCR), and the peritumoral edematous/infiltrated tissues (ED) using contrast-enhanced T1-weighted images (CE-T1WI) and T2-weighted images (T2WI). The vViT had 9 sectors; 1 demographic sector, 6 radiomic sectors (CE-T1WI ET, CE-T1WI NCR, CE-T1WI ED, T2WI ET, T2WI NCR, and T2WI ED), 2 image sectors (CE-T1WI, and T2WI). Accuracy and area under the curve of receiver-operating characteristics (AUC-ROC) were calculated for the test dataset. The performance of vViT was compared with AlexNet, GoogleNet, VGG16, and ResNet by McNemar and Delong test. Permutation importance (PI) analysis with the Mann–Whitney U test was performed.ResultsThe accuracy was 0.833 (95% confidence interval [95%CI]: 0.714–0.877) and the area under the curve of receiver-operating characteristics was 0.840 (0.650–0.995) in the patient-based analysis. The vViT had higher accuracy than VGG16 and ResNet, and had higher AUC-ROC than GoogleNet (p<0.05). The ED radiomic features extracted from the T2-weighted image demonstrated the highest importance (PI=0.239, 95%CI: 0.237–0.240) among all other sectors (p<0.0001).ConclusionThe vViT is a competent deep learning model in predicting MGMT status. The ED radiomic features of the T2-weighted image demonstrated the most dominant contribution.

A novel tumor-associated neutrophil gene signature for predicting prognosis, tumor immune microenvironment, and therapeutic response in breast cancer

Tumor-associated neutrophils (TANs) can promote tumor progression. This study aimed to investigate the molecular signature that predict the prognosis and immune response of breast cancer (BRCA) based on TAN-related gene (TANRG) expression data. The RNA-seq data of BRCA were gathered from The Cancer Genome Atlas (TCGA) and gene expression omnibus (GEO) datasets. Univariate Cox regression analysis and the least absolute shrinkage and selection operator for selecting prognostic genes. A neo-TAN-related risk signature was constructed by multivariate Cox regression analysis. Time-dependent receiver operating characteristic (ROC) curve analyses and Kaplan–Meier analyses were performed to validate the signature in GEO cohorts and the triple-negative breast cancer (TNBC) subtype. We constructed an independent prognostic factor model with 11 TANRGs. The areas under the ROC curve (AUCs) of the TCGA training cohorts for 3-, 5-, and 7-year overall survival were 0.72, 0.73, and 0.73, respectively. The AUCs of the GEO test cohorts for 3-, 5-, and 7-year overall survival were 0.83, 0.89, and 0.94 (GSE25066) and 0.67, 0.69, and 0.73 (GSE58812), respectively. The proportion of immune subtypes differed among the different risk groups. The IC50 values differed significantly between risk groups and can be used as a guide for systemic therapy. The prognostic model developed by TANRGs has excellent predictive performance in BRCA patients. In addition, this feature is closely related to the prediction of survival, immune activity and treatment response in BRCA patients.

The use of optical coherence tomography (OCT) and OCT angiography in borderline personality disorder compared to health control subjects.

Optical coherence tomography (OCT) or OCT angiography (OCTA) has been investigated in few research studies of psychiatric disorders. No research has been done using OCT or OCTA in patients with borderline personality disorder (BPD). OCTA measured foveal avascular zone (FAZ), macular vessel density (MVD), and peripapillary vessel density (PVD). OCT measured the peripapillary retinal fiber layer (RNFL) and central retinal thickness (CRT). The study utilized the Ottawa Self-Injury Inventory, Hamilton Anxiety Rating Scale (HAMA), and Global Assessment of Functioning (GAF) to assess the symptom characteristics of individuals with BPD. Fifty-nine eyes of BPD patients and 58 eyes of normal subjects were analyzed, MVD of the superficial retinal capillary plexus declined noticeably in most subfields (p < 0.05). Significant differences were observed in the whole inner ring and outer ring index between BPD and HC groups (p < 0.05). The patients with BPD exhibited lower RNFL and CRT, the difference was significant (p < 0.05). CRT indicated a significant negative correlation with the Ottawa Self-Injury Inventory (p < 0.05). In addition, we observed that there was a negative correlation identified between the MVD of the inner ring and HAMA (p < 0.05). Meanwhile, the MVD of the outer ring was positively correlated with GAF (p < 0.05). The areas under the receiver operating characteristic curves (AUROCs) for distinguishing BPD and HC eyes in OCTA were the highest for fovea MVD (0.679), followed by outer ring MVD (0.669), inner ring MVD (0.641), FAZ (0.579). In OCT, CRT was highest for BPD (0.711), followed by RNFL (0.625). The OCT and OCTA can non-invasively detect microvascular and morphology changes of the retina in BPD patients compared to healthy control subjects.

Advanced gastrointestinal stromal tumor: reliable classification of imatinib plasma trough concentration via machine learning

AimPatients with advanced gastrointestinal stromal tumors (GISTs) exhibiting an imatinib plasma trough concentration (IM Cmin) under 1100 ng/ml may show a reduced drug response rate, leading to the suggestion of monitoring for IM Cmin. Consequently, the objective of this research was to create a customized IM Cmin classification model for patients with advanced GISTs from China.MethodsInitial data and laboratory indicators from patients with advanced GISTs were gathered, and the above information was segmented into a training set, validation set, and testing set in a 6:2:2 ratio. Key variables associated with IM Cmin were identified to construct the classification model using the least absolute shrinkage and selection operator (LASSO) regression and forward stepwise binary logistic regression. Within the training and validation sets, nine ML classification models were constructed via the resampling method and underwent comparison through the Brier scores, the areas under the receiver-operating characteristic curve (AUROC), the decision curve, and the precision-recall (AUPR) curve to determine the most suitable model for this dataset. Two methods of internal validation were used to assess the most suitable model's classification performance: tenfold cross-validation and random split-sample validation (test set), and the value of the test set AUROC was used to evaluate the model's classification performance.ResultsSix key variables (gender, daily IM dose, metastatic site, red blood cell count, platelet count, and percentage of neutrophils) were ultimately selected to construct the classification model. In the validation set, it is found by comparison that the Extreme Gradient Boosting (XGBoost) model has the largest AUROC, the lowest Brier score, the largest area under the decision curve, and the largest AUPR value. Furthermore, as evaluated via internal verification, it also performed well in the test set (AUROC = 0.725).ConclusionFor patients with advanced GISTs who receive IM, initial data and laboratory indicators could be used to accurately estimate whether the IM Cmin is below 1100 ng/ml. The XGBoost model may stand a chance to assist clinicians in directing the administration of IM.

Validation of SeptiCyte RAPID to Discriminate Sepsis from Non-Infectious Systemic Inflammation.

(1) Background: SeptiCyte RAPID is a molecular test for discriminating sepsis from non-infectious systemic inflammation, and for estimating sepsis probabilities. The objective of this study was the clinical validation of SeptiCyte RAPID, based on testing retrospectively banked and prospectively collected patient samples. (2) Methods: The cartridge-based SeptiCyte RAPID test accepts a PAXgene blood RNA sample and provides sample-to-answer processing in ~1 h. The test output (SeptiScore, range 0-15) falls into four interpretation bands, with higher scores indicating higher probabilities of sepsis. Retrospective (N = 356) and prospective (N = 63) samples were tested from adult patients in ICU who either had the systemic inflammatory response syndrome (SIRS), or were suspected of having/diagnosed with sepsis. Patients were clinically evaluated by a panel of three expert physicians blinded to the SeptiCyte test results. Results were interpreted under either the Sepsis-2 or Sepsis-3 framework. (3) Results: Under the Sepsis-2 framework, SeptiCyte RAPID performance for the combined retrospective and prospective cohorts had Areas Under the ROC Curve (AUCs) ranging from 0.82 to 0.85, a negative predictive value of 0.91 (sensitivity 0.94) for SeptiScore Band 1 (score range 0.1-5.0; lowest risk of sepsis), and a positive predictive value of 0.81 (specificity 0.90) for SeptiScore Band 4 (score range 7.4-15; highest risk of sepsis). Performance estimates for the prospective cohort ranged from AUC 0.86-0.95. For physician-adjudicated sepsis cases that were blood culture (+) or blood, urine culture (+)(+), 43/48 (90%) of SeptiCyte scores fell in Bands 3 or 4. In multivariable analysis with up to 14 additional clinical variables, SeptiScore was the most important variable for sepsis diagnosis. A comparable performance was obtained for the majority of patients reanalyzed under the Sepsis-3 definition, although a subgroup of 16 patients was identified that was called septic under Sepsis-2 but not under Sepsis-3. (4) Conclusions: This study validates SeptiCyte RAPID for estimating sepsis probability, under both the Sepsis-2 and Sepsis-3 frameworks, for hospitalized patients on their first day of ICU admission.

Guiding early revascularization using [15O]H2O PET myocardial perfusion imaging - Impact of atrial fibrillation.

Myocardial perfusion imaging (MPI) using [15O]H2O positron emission tomography (PET) is used to guide the selection of patients with angina for invasive angiography and possible revascularization. Our study evaluated whether atrial fibrillation (AF): 1) reduces global hyperemic myocardial blood flow (MBF) and 2) whether [15O]H2O PET MPI effectively guides revascularization procedures for patients with ongoing AF. We prospectively recruited 346 patients with angina and persistent or paroxysmal AF referred for baseline/hyperemic [15O]H2O PET MPI. The primary outcome was revascularization within 3 months of MPI. In the analyses, patients were divided into four groups based on whether they had ongoing AF or sinus rhythm (SR) and whether they had previously documented coronary artery disease (CAD) or not. Thus, four groups were compared: SR-noCAD, AF-noCAD, SR-CAD and AF-CAD. Hyperemic MBF was affected by both ongoing AF and prior CAD [MBF (mL/min/g): 2.82 (SR-noCAD) vs. 2.12 (AF-noCAD) vs. 2.22 (SR-CAD) vs. 1.80 (AF-CAD), two-way ANOVA p<0.0001]. In multiple linear regression ongoing AF was independently associated with reduced hyperemic MBF. Every 0.1 mL/min/g decrease in hyperemic MBF was associated with a 23% increase in odds of early revascularization. ROC-analysis of vessel specific hyperemic MBF to predict early revascularization yielded the following areas under the ROC curve (AUC): SR-noCAD: 0.95 (p<0.0001); AF-noCAD: 0.79 (p<0.0001); SR-CAD: 0.78 (p<0.0001); AF-CAD: 0.88 (p<0.0001). Ongoing AF is associated with 19-25 % reduced global hyperemic MBF as measured by [15O]H2O MPI PET. Regardless, vessel specific hyperemic MBF still predicts early revascularization in patients with AF.

Prediction by uterine artery Doppler screening of small-for-gestational-age neonates at 19-24 weeks' gestation.

Small-for-gestational-age (SGA) neonates are at increased risk of perinatal mortality and morbidity. We aimed to investigate the performance of uterine artery pulsatility index (UtA-PI) at 19-24 weeks' gestation to predict the delivery of a SGA neonate in a Chinese population. This was a retrospective cohort study using data obtained between January 2010 and June 2018. Doppler ultrasonography was performed at 19-24 weeks' gestation. SGA was defined as birth weight below the 10th centile according to the INTERGROWTH-21st fetal growth standards. The performance of UtA-PI to predict the delivery of a SGA neonate was assessed using receiver-operating-characteristics (ROC)-curve analysis. We included 6964 singleton pregnancies, of which 748 (11%) delivered a SGA neonate, including 115 (15%) women with preterm delivery. Increased UtA-PI was associated with an elevated risk of SGA, both in neonates delivered at or after 37 weeks' gestation (term SGA) and those delivered before 37 weeks (preterm SGA). The areas under the ROC curve (AUCs) for UtA-PI were 64.4% (95% CI, 61.5-67.3%) and 75.8% (95% CI, 69.3-82.3%) for term and preterm SGA, respectively. The performance of combined screening by maternal demographic/clinical characteristics and estimated fetal weight in the detection of term and preterm SGA was improved significantly by the addition of UtA-PI, although the increase in AUC was modest (2.4% for term SGA and 4.9% for preterm SGA). This is the first Chinese study to evaluate the role of UtA-PI at 19-24 weeks' gestation in the prediction of the delivery of a neonate with SGA. The addition of UtA-PI to traditional risk factors improved the screening performance for SGA, and this improvement was greater in predicting preterm SGA compared with term SGA. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Classification of bladder cancer based on immune cell infiltration and construction of a risk prediction model for prognosis.

To classify bladder cancer based on immune cell infiltration score and to construct a prognosis assessment model of patients with bladder cancer. The transcriptome data and clinical data of breast cancer patients were obtained from the The Cancer Genome Atlas (TCGA) database. Single sample gene set enrichment analysis was used to calculate the infiltration scores of 16 immune cells. The classification of breast cancer patients was achieved by unsupervised clustering, and the sensitivity of patients with different types to immunotherapy and chemotherapy was analyzed. The key modules significantly related to the infiltration of key immune cells were identified by weighted correlation network analysis (WGCNA), and the key genes in the modules were identified. A risk scoring model and a nomogram for prognosis assessment of bladder cancer patients were constructed and verified. B cells, mast cells, neutrophils, T helper cells and tumor infiltrating lymphocytes were determined to be the key immune cells of bladder cancer. The patients were clustered into two groups (Cluster 1 ´ and Custer 2) based on immune cell infiltration scores. Compared with patients with Cluster 1 ´, patients with Cluster 2 were more likely to benefit from immunotherapy (P<0.05), and patients with Cluster 2 were more sensitive to Enbeaten, Docetaxel, Cyclopamine, and Akadixin (P<0.05). 35 genes related to key immune cells were screened out by WGCNA and 4 genes (GPR171, HOXB3, HOXB5 and HOXB6) related to the prognosis of bladder cancer were further screened by LASSO Cox regression. The areas under the ROC curve (AUC) of the bladder cancer prognosis risk scoring model based on these 4 genes to predict the 1-, 3- and 5-year survival of patients were 0.735, 0.765 and 0.799, respectively. The nomogram constructed by combining risk score and clinical parameters has high accuracy in predicting the 1-, 3-, and 5-year overall survival of bladder cancer patients. According to the immune cell infiltration score, bladder cancer patients can be classified. Furthermore, bladder cancer prognosis risk scoring model and nomogram based on key immune cell-related genes have high accuracy in predicting the prognosis of bladder cancer patients.

Hybrid QUS Radiomics: A Multimodal-Integrated Quantitative Ultrasound Radiomics for Assessing Ambulatory Function in Duchenne Muscular Dystrophy.

Duchenne muscular dystrophy (DMD) is a neuromuscular disorder that affects ambulatory function. Quantitative ultrasound (QUS) imaging, utilizing envelope statistics, has proven effective in diagnosing DMD. Radiomics enables the extraction of detailed features from QUS images. This study further proposes a hybrid QUS radiomics and explores its value in characterizing DMD. Patients (n = 85) underwent ultrasound examinations of gastrocnemius through Nakagami, homodyned K (HK), and information entropy imaging. The hybrid QUS radiomics extracted, selected, and integrated the retained features derived from each QUS image for classification of ambulatory function using support vector machine. Nested five fold cross-validation of the data was conducted, with the rotational process repeated 50 times. The performance was assessed by averaging the areas under the receiver operating characteristic curve (AUROC). Radiomics enhanced the average AUROC of B-scan, Nakagami, HK, and entropy imaging to 0.790, 0.911, 0.869, and 0.890, respectively. By contrast, the hybrid QUS radiomics using HK and entropy images for diagnosing ambulatory function in DMD patients achieved a superior average AUROC of 0.971 (p < 0.001 compared with conventional radiomics analysis). The proposed hybrid QUS radiomics incorporates microstructure-related backscattering information from various envelope statistics models to effectively enhance the performance of DMD assessment.

Prognosticating Fetal Growth Restriction and Small for Gestational Age by Medical History.

This study aimed to develop and externally validate a prognostic prediction model for screening fetal growth restriction (FGR)/small for gestational age (SGA) using medical history. From a nationwide health insurance database (n=1,697,452), we retrospectively selected visits of 12-to-55-year-old females to healthcare providers. This study used machine learning (including deep learning) and 54 medical-history predictors. The best model was a deep-insight visible neural network (DI-VNN). It had area under the curve of receiver operating characteristics (AUROC) 0.742 (95% CI 0.734 to 0.750) and a sensitivity of 49.09% (95% CI 47.60% to 50.58% at with 95% specificity). Our model used medical history for screening FGR/SGA with moderate accuracy by DI-VNN. In future work, we will compare this model with those from systematically-reviewed, previous studies and evaluate if this model's usage impacts patient outcomes.

Comparison of seven surrogate insulin resistance indexes for prediction of incident coronary heart disease risk: a 10-year prospective cohort study.

There were seven novel and easily accessed insulin resistance (IR) surrogates established, including the Chinese visceral adiposity index (CVAI), the visceral adiposity index (VAI), lipid accumulation product (LAP), triglyceride glucose (TyG) index, TyG-body mass index (TyG-BMI), TyG-waist circumference (TyG-WC) and TyG-waist to height ratio (TyG-WHtR). We aimed to explore the association between the seven IR surrogates and incident coronary heart disease (CHD), and to compare their predictive powers among Chinese population. This is a 10-year prospective cohort study conducted in China including 6393 participants without cardiovascular disease (CVD) at baseline. We developed Cox regression analyses to examine the association of IR surrogates with CHD (hazard ratio [HR], 95% confidence intervals [CI]). Moreover, the receiver operating characteristic (ROC) curve was performed to compare the predictive values of these indexes for incident CHD by the areas under the ROC curve (AUC). During a median follow-up period of 10.25 years, 246 individuals newly developed CHD. Significant associations of the IR surrogates (excepted for VAI) with incident CHD were found in our study after fully adjustment, and the fifth quintile HRs (95% CIs) for incident CHD were respectively 2.055(1.216-3.473), 1.446(0.948-2.205), 1.753(1.099-2.795), 2.013(1.214-3.339), 3.169(1.926-5.214), 2.275(1.391-3.719) and 2.309(1.419-3.759) for CVAI, VAI, LAP, TyG, TyG-BMI, TyG-WC and TyG-WHtR, compared with quintile 1. Furthermore, CVAI showed maximum predictive capacity for CHD among these seven IR surrogates with the largest AUC: 0.632(0.597,0.667). The seven IR surrogates (excepted for VAI) were independently associated with higher prevalence of CHD, among which CVAI is the most powerful predictor for CHD incidence in Chinese populations.

Tobacco and alcohol co-use: Lifestyle and sociodemographic factors, and personality aspects as potential predictors in the "Seguimiento Universidad de Navarra"cohort.

Tobacco and alcohol co-use are two major lifestyle modifiable risk factors. Understanding the determinants of both behaviors helps to develop interventions to prevent these exposures. However, previous studies have focused on predictors of individual tobacco or alcohol use. This study aims to explore the potential predictors of tobacco and alcohol co-use among Spanish university graduates from the "Seguimiento Universidad de Navarra" (SUN) cohort study. A total of 7175 participants who were co-users of tobacco and alcohol were selected for this cross-sectional analysis. Their mean age was 39.1 years (12.04SD) and 57.3% were women. Univariate regression models were used to select the potential predictors of tobacco and alcohol co-use, and the areas under the ROC curves (AUC) were calculated. Multivariable logistic regression models were used to create a predictive model. Baseline potential predictors included sociodemographic factors, lifestyle habits, and perceived personality aspects. In the multivariable model, the main significant potential predictors of tobacco and alcohol co-use were driving under the influence of alcohol (odds ratio [OR] = 1.65 [1.43-1.90]), drinking 1-2 cups of coffee daily (OR = 1.50 [1.24-1.84]), drinking three or more cups of coffee daily (OR = 1.61 [1.35-1.91]), and doing more physical activity than recommended (OR = 1.18 [1.02-1.34]) when compared with the reference group. Conversely, those who were married (OR = 0.87 [0.75-0.99], ate at home 7 days a week (OR = 0.69 [0.60-0.80]), or had a high perceived level of competitiveness (OR = 0.83 [0.72-0.95]) had a lower risk of co-use (AUC 0.61 [confidence interval95% 0.59-0.63]), compared to the reference group. These results could be used by healthcare professionals, especially nurses, to effectively assess patients at higher risk of tobacco and alcohol co-use. [Correction added on 16 February 2024, after first online publication: The abstract section has been revised to provide more clarity in this version.].

Quantification of lipoproteins by proton nuclear magnetic resonance spectroscopy (1H-NMRS) improves the prediction of cardiac autonomic dysfunction in patients with type 1 diabetes.

To assess if advanced characterization of serum glycoprotein and lipoprotein profile, measured by proton nuclear magnetic resonance spectroscopy (1H-NMRS) improves a predictive clinical model of cardioautonomic neuropathy (CAN) in subjects with type 1 diabetes (T1D). Cross-sectional study (ClinicalTrials.gov Identifier: NCT04950634). CAN was diagnosed using Ewing's score. Advanced characterization of macromolecular complexes including glycoprotein and lipoprotein profiles in serum samples were measured by 1H-NMRS. We addressed the relationships between these biomarkers and CAN using correlation and regression analyses. Diagnostic performance was assessed by analyzing their areas under the receiver operating characteristic curves (AUCROC). Three hundred and twenty-three patients were included (46% female, mean age and duration of diabetes of 41 ± 13years and 19 ± 11years, respectively). The overall prevalence of CAN was 28% [95% confidence interval (95%CI): 23; 33]. Glycoproteins such as N-acetylglucosamine/galactosamine and sialic acid showed strong correlations with inflammatory markers such as high-sensitive C-reactive protein, fibrinogen, IL-10, IL-6, and TNF-α. On the contrary, we did not find any association between the former and CAN. A stepwise binary logistic regression model (R2 = 0.078; P = 0.003) retained intermediate-density lipoprotein-triglycerides (IDL-TG) [β:0.082 (95%CI: 0.005; 0.160); P = 0.039], high-density lipoprotein-triglycerides (HDL-TGL)/HDL-Cholesterol [β:3.633 (95%CI: 0.873; 6.394); P = 0.010], and large-HDL particle number [β: 3.710 (95%CI: 0.677; 6.744); P = 0.001] as statistically significant determinants of CAN. Adding these lipoprotein particles to a clinical prediction model of CAN that included age, duration of diabetes, and A1c enhanced its diagnostic performance, improving AUCROC from 0.546 (95%CI: 0.404; 0.688) to 0.728 (95%CI: 0.616; 0.840). When added to clinical variables, 1H-NMRS-lipoprotein particle profiles may be helpful to identify those patients with T1D at risk of CAN.

Clinical prediction models for cervical lymph node metastasis of papillary thyroid carcinoma.

Accurate preoperative diagnosis of lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) remains an unsolved problem. This study aimed to construct a nomogram and scoring system for predicting LNM based on the clinical characteristics of patients with PTC. 1400 patients with PTC who underwent thyroidectomy and lymph node dissection at the First Affiliated Hospital of Sun Yat-sen University were retrospectively enrolled and randomly divided into training and internal testing sets. Furthermore, 692 patients with PTC from three other medical centers were collected as external testing sets. Least absolute shrinkage and selection operator (LASSO) was used to screen the predictors, and a nomogram was constructed. In addition, a scoring system was constructed using 10-fold cross-validation. The performances of the two models were verified among datasets and compared with preoperative ultrasound (US). Six independent predictors were included in the multivariate logistic model: age, sex, US diagnosis of LNM, tumor diameter, location, and thyroid peroxidase antibody level. The areas under the receiver operating characteristic curve (AUROC) (95% confidence interval) of this nomogram in the training, internal testing, and three external testing sets were 0.816 (0.791-0.840), 0.782 (0.727-0.837), 0.759 (0.699-0.819), 0.749 (0.667-0.831), and 0.777 (0.726-0.828), respectively. The AUROC of the scoring system were 0.810 (0.785-0.835), 0.772 (0.718-0.826), 0.736 (0.675-0.798), 0.717 (0.635-0.799) and 0.756 (0.704-0.808), respectively. The prediction performances were both significantly superior to those of preoperative US (P < 0.001). The nomogram and scoring system performed well in different datasets and significantly improved the preoperative prediction of LNM than US alone.