Area Under The ROC Curve Research Articles

Virtual screening reveals fluorescent probes for detecting Pan-Zinc center activity in serum MMPs: A potential biomarker for early tumor screening

Early tumor screening is pivotal for enhancing tumor treatment efficacy and patient survival rates, yet identifying reliable biomarkers for early detection remains a challenge. Previous studies have explored different isoforms of matrix metalloproteinases (MMPs) in serum for their predictive value in tumor, but their results have been inconsistent. Herein, we introduce a novel fluorescent probe, C9 (N-oxide-8-hydroxyquinoline-5-sulfonic acid), designed to specifically label the pan zinc center activity of MMPs (PZCA-MMPs), which in a sense represents the overall MMPs activity in serum. The rational design of fluorescent probe C9 is based on its ability to bind the zinc ions in the structure of MMPs, facilitated by the oxides on hydroxyl (–OH) and nitro oxide (N→O) groups present in C9, as supported by theoretical calculations such as Gaussian and Schrödinger. Experimental validation confirmed its efficacy for detecting PZCA-MMPs in vitro and for fluorescence imaging of MMPs’ zinc ions in cellular contexts, validated through absolute integrated fluorescence intensity measurements at 510 nm. We also demonstrated through in vitro fluorescent analysis that neither metal ions nor abundant serum proteins such as albumin (BSA) and other metalloproteins interfere with the signal response of C9. Notably, in comparative analysis of serum samples from healthy controls and breast tumor patients, PZCA-MMPs showed a highly discriminatory area under the ROC curve (AUC) of 0.9377, surpassing established tumor biomarkers such as CA125, CA15-3, CA19-9, and CA72-4. In particular, for tumor patients, PZCA-MMPs can effectively distinguish between metastatic and non-metastatic patients (*P<0.05). Therefore, this provides a potential alternative biomarker for tumor screening. Future studies aim to further elucidate the clinical utility of PZCA-MMPs using a broader spectrum of clinical samples.

Deciphering the Language of Protein-DNA Interactions: A Deep Learning Approach Combining Contextual Embeddings and Multi-Scale Sequence Modeling

Deciphering the mechanisms governing protein-DNA interactions is crucial for understanding key cellular processes and disease pathways. In this work, we present a powerful deep learning approach that significantly advances the computational prediction of DNA-interacting residues from protein sequences.Our method leverages the rich contextual representations learned by pre-trained protein language models, such as ProtTrans, to capture intrinsic biochemical properties and sequence motifs indicative of DNA binding sites. We then integrate these contextual embeddings with a multi-window convolutional neural network architecture, which scans across the sequence at varying window sizes to effectively identify both local and global binding patterns.Comprehensive evaluation on curated benchmark datasets demonstrates the remarkable performance of our approach, achieving an area under the ROC curve (AUC) of 0.89 – a substantial improvement over previous state-of-the-art sequence-based predictors. This showcases the immense potential of pairing advanced representation learning and deep neural network designs for uncovering the complex syntax governing protein-DNA interactions directly from primary sequences.Our work not only provides a robust computational tool for characterizing DNA-binding mechanisms, but also highlights the transformative opportunities at the intersection of language modeling, deep learning, and protein sequence analysis. The publicly available code and data further facilitate broader adoption and continued development of these techniques for accelerating mechanistic insights into vital biological processes and disease pathways.In addition, the code and data for this work are available at https://github.com/B1607/DIRP.

Beyond pixel: Superpixel-based MRI segmentation through traditional machine learning and graph convolutional network

Background and Objective:Tendon segmentation is crucial for studying tendon-related pathologies like tendinopathy, tendinosis, etc. This step further enables detailed analysis of specific tendon regions using automated or semi-automated methods. This study specifically aims at the segmentation of Achilles tendon, the largest tendon in the human body. Methods:This study proposes a comprehensive end-to-end tendon segmentation module composed of a preliminary superpixel-based coarse segmentation preceding the final segmentation task. The final segmentation results are obtained through two distinct approaches. In the first approach, the coarsely generated superpixels are subjected to classification using Random Forest (RF) and Support Vector Machine (SVM) classifiers to classify whether each superpixel belongs to a tendon class or not (resulting in tendon segmentation). In the second approach, the arrangements of superpixels are converted to graphs instead of being treated as conventional image grids. This classification process uses a graph-based convolutional network (GCN) to determine whether each superpixel corresponds to a tendon class or not. Results:All experiments are conducted on a custom-made ankle MRI dataset. The dataset comprises 76 subjects and is divided into two sets: one for training (Dataset 1, trained and evaluated using leave-one-group-out cross-validation) and the other as unseen test data (Dataset 2). Using our first approach, the final test AUC (Area Under the ROC Curve) scores using RF and SVM classifiers on the test data (Dataset 2) are 0.992 and 0.987, respectively, with sensitivities of 0.904 and 0.966. On the other hand, using our second approach (GCN-based node classification), the AUC score for the test set is 0.933 with a sensitivity of 0.899. Conclusions:Our proposed pipeline demonstrates the efficacy of employing superpixel generation as a coarse segmentation technique for the final tendon segmentation. Whether utilizing RF, SVM-based superpixel classification, or GCN-based classification for tendon segmentation, our system consistently achieves commendable AUC scores, especially the non-graph-based approach. Given the limited dataset, our graph-based method did not perform as well as non-graph-based superpixel classifications; however, the results obtained provide valuable insights into how well the models can distinguish between tendons and non-tendons. This opens up opportunities for further exploration and improvement.

Association between the pan-immune-inflammation value and coronary collateral circulation in chronic total coronary occlusive patients

BackgroundInflammation and immunity play important roles in the formation of coronary collateral circulation (CCC). The pan-immune-inflammation value (PIV) is a novel marker for evaluating systemic inflammation and immunity. The study aimed to investigate the association between the PIV and CCC formation in patients with chronic total occlusion (CTO).MethodsThis retrospective study enrolled 1150 patients who were diagnosed with CTO through coronary angiographic (CAG) examinations from January 2013 to December 2021 in China. The Cohen-Rentrop criteria were used to catagorize CCC formation: good CCC formation (Rentrop grade 2–3) and poor CCC formation group (Rentrop grade 0–1). Based on the tertiles of the PIV, all patients were classified into three groups as follows: P1 group, PIV ≤ 237.56; P2 group, 237.56< PIV ≤ 575.18; and P3 group, PIV > 575.18.ResultsA significant relationship between the PIV and the formation of CCC was observed in our study. Utilizing multivariate logistic regression and adjusting for confounding factors, the PIV emerged as an independent risk factor for poor CCC formation. Notably, the restricted cubic splines revealed a dose–response relationship between the PIV and risk of poor CCC formation. In terms of predictive accuracy, the area under the ROC curve (AUC) for PIV in anticipating poor CCC formation was 0.618 (95% CI: 0.584–0.651, P < 0.001). Furthermore, the net reclassification index (NRI) and integrated discrimination index (IDI) for PIV, concerning the prediction of poor CCC formation, were found to be 0.272 (95% CI: 0.142–0.352, P < 0.001) and 0.051 (95% CI: 0.037–0.065, P < 0.001), respectively. It’s noteworthy that both the NRI and IDI values were higher for PIV compared to other inflammatory biomarkers, suggesting its superiority in predictive capacity.ConclusionsPIV was associated with the formation of CCC. Notably, PIV exhibited potential as a predictor for poor CCC formation and showcased superior predictive performance compared to other complete blood count-based inflammatory biomarkers.

B-type natriuretic peptide informativeness in myocardial revascularization with cardio-pulmonary bypass

The objective was to study the dynamics of B-type natriuretic peptide (BNP) and its relationship with hemodynamic parameters during on-pump coronary artery bypass grafting (CABG), and to evaluate the informativeness of the biomarker as a predictor of myocardial dysfunction.Materials and methods. The study involved 127 patients aged 59 [54–66.75] years with ischemic heart disease who underwent CABG. The BNP blood level was determined in the operating room at stages: I – before surgery (BNP1 ), II – at the end of surgery (BNP2 ). Hemodynamic parameters were analyzed at the same stages. Correlation analysis, logistic regression with the calculation of the odds ratio (OR) and 95% confidence interval (95% CI) and ROC analysis with the calculation of the area under the ROC curve (AUC) were used.Results. BNP1 blood level was 49 [25.6–91.6], BNP2 – 90 [47.8–140.2] pg/ml (p &lt; 0.0001). BNP1 correlated with central venous pressure (CVP) at stage I (rho = 0.212; p = 0.017) and with pulmonary artery wedge pressure (PAWP) at stage II (rho = 0.204; p = 0.045). BNP2 correlated with PAWP at stage II (rho = 0.204; p = 0.045). BNP1 &gt; 52.1 pg/ml was the predictor of ICU length of stay &gt; 24 hours (OR 1.0290, 95% CI 1.0154– 1.0427, p &lt; 0.0001, AUC 0.775), BNP1 &gt; 71 pg/ml was the predictor of inotropic index &gt; 5 c. u. (OR 1.0076, 95% CI 1.0015–1.0138, p = 0.014, AUC 0.705) and BNP1 &gt; 90.8 pg/ml was the predictor of vasoactive inotropic index &gt; 10 c. u. (OR 1.0070, 95% CI 1.0014–1.0126, p = 0.013, AUC 0.727). BNP2 &gt; 67.5 pg/ml was the predictor of ICU length of stay &gt; 24 hours (OR 1.0179, 95% CI 1.0073–1.0287, p &lt; 0.0009, AUC 0.763), BNP2 &gt; 94.3 pg/ml was the predictor of inotropic index &gt; 5 c. u. (OR 1.0063, 95% CI 1.0010–1.0117, p = 0.020, AUC 0.713), BNP2 &gt; 144 pg/ml was the predictor of intra-aortic balloon pumping (OR 1.0037, 95% CI 1 .0000–1.0074, p = 0.048, AUC 0.854), BNP2 &gt; 159 pg/ml was the predictor of vasoactive inotropic index &gt; 10 c. u. (OR 1.0072, 95% CI 1.0006–1.0139, p = 0.033, AUC 0.729) and BNP2 &gt; 161 pg/ml was the predictor of early mortality in the ICU (OR 1.0040, 95% CI 1, 0000-1.0080, p = 0.049, AUC 0.845). Conclusion. In 78.7% of patients undergoing on-pump CABG, BNP blood level does not exceed the upper limit of normal; by the end of surgery, the biomarker level increases by 32.9 [17.7–62.0] pg/ml. Before and at the end of surgery, BNP values are weakly correlated with CVP and PAWP and do not correlate with other hemodynamic parameters. Before surgery, BNP blood level in the range of 52.1–90.8 pg/ml are predictors of ICU stay &gt; 24 hours (AUC 0.775), inotropic scale &gt; 5 (AUC 0.705) and vasoactive-inotropic scale &gt; 10 c. u. (AUC 0.727). At the end of surgery, BNP &gt; 67.5 pg/ml is associated with an ICU stay &gt; 24 hours (AUC 0.763), and BNP &gt; 90.4 pg/ml is associated with inotropic scale &gt; 5 c. u. (AUC 0.713). The BNP, increased to 144.0–161.0 pg/ml, indicates severe myocardial dysfunction, including hemodynamic support with intra-aortic balloon pumping (AUC 0.854), vasoactive-inotropic scale &gt; 10 c. u. (AUC 0.729) and the risk of early mortality in the ICU (AUC 0.845).

An MRI multi-sequence feature imputation and fusion mutual-aid model based on sequence deletion for differentiation of high-grade from low-grade glioma

To evaluate the performance of magnetic resonance imaging (MRI) multi-sequence feature imputation and fusion mutual model based on sequence deletion in differentiating high-grade glioma (HGG) from low-grade glioma (LGG). We retrospectively collected multi-sequence MR images from 305 glioma patients, including 189 HGG patients and 116 LGG patients. The region of interest (ROI) of T1-weighted images (T1WI), T2-weighted images (T2WI), T2 fluid attenuated inversion recovery (T2_FLAIR) and post-contrast enhancement T1WI (CE_T1WI) were delineated to extract the radiomics features. A mutual-aid model of MRI multi-sequence feature imputation and fusion based on sequence deletion was used for imputation and fusion of the feature matrix with missing data. The discriminative ability of the model was evaluated using 5-fold cross-validation method and by assessing the accuracy, balanced accuracy, area under the ROC curve (AUC), specificity, and sensitivity. The proposed model was quantitatively compared with other non-holonomic multimodal classification models for discriminating HGG and LGG. Class separability experiments were performed on the latent features learned by the proposed feature imputation and fusion methods to observe the classification effect of the samples in twodimensional plane. Convergence experiments were used to verify the feasibility of the model. For differentiation of HGG from LGG with a missing rate of 10%, the proposed model achieved accuracy, balanced accuracy, AUC, specificity, and sensitivity of 0.777, 0.768, 0.826, 0.754 and 0.780, respectively. The fused latent features showed excellent performance in the class separability experiment, and the algorithm could be iterated to convergence with superior classification performance over other methods at the missing rates of 30% and 50%. The proposed model has excellent performance in classification task of HGG and LGG and outperforms other non-holonomic multimodal classification models, demonstrating its potential for efficient processing of non-holonomic multimodal data.

The Predictive Accuracy of Anogenital Distance and Genital Tubercle Angle for First-Trimester Fetal Sex Determination.

Early identification of fetal gender is crucial for managing gender-linked genetic disorders. This study aimed to evaluate the predictive performance of anogenital distance (AGD) and genital tubercle angle (GTA) for fetal sex determination during the first trimester. A multicenter retrospective cohort study was conducted on 312 fetal cases between 11 and 13 + 6 weeks of gestation from two tertiary hospitals. AGD and GTA measurements were taken from midsagittal plane images using ultrasound, with intra- and inter-reader reproducibility assessed. Binomial logistic regression and ROC curve analysis were employed to determine the diagnostic performance and optimal cutoff points. AGD had a mean of 7.16 mm in male fetuses and 4.42 mm in female fetuses, with a sensitivity of 88.8%, specificity of 94.4%, and an area under the ROC curve (AUC) of 0.931 (95% CI: 0.899-0.962) using 5.74 mm as a cutoff point. For GTA, the mean was 35.90 degrees in males and 21.57 degrees in females, with a sensitivity of 92%, specificity of 84.7%, and an AUC of 0.932 (95% CI: 0.904-0.961) using 28.32 degrees as a cutoff point. The reproducibility results were excellent for AGD (intra-operator ICC = 0.938, inter-operator ICC = 0.871) and moderate for GTA (intra-operator ICC = 0.895, inter-operator ICC = 0.695). The findings suggest that AGD and GTA are reliable markers for early fetal sex determination, with AGD showing higher reproducibility. The findings highlight the feasibility and accuracy of these non-invasive sonographic markers and their potential usefulness in guiding timely interventions and enhancing the management of gender-linked genetic conditions.

Machine learning and IoT system for real-time cough detection and classification

Our research investigates the application of machine learning and Internet of Things (IoT) technologies in healthcare, focusing on detecting and classifying coughing episodes. Leveraging deep learning architectures and a comprehensive IoT infrastructure, we developed an automated system capable of monitoring audio signals from a microphone array module to detect coughs and classify their types accurately. The study utilized the COUGHVID dataset for model training and evaluation, employing rigorous preprocessing techniques to ensure data integrity. Through comparative analysis, we identified MobileNet as the optimal model for cough detection, achieving promising results in accuracy, area under the ROC curve (AUC), and F1 score. Furthermore, our emphasis on privacy safeguards and remote medical examination facilitation underscores the practical implications of our research in enhancing healthcare delivery. Our study contributes to advancing technology-enabled healthcare solutions, offering valuable insights and solutions for improving patient care and outcomes.

An optimized model based on adaptive convolutional neural network and grey wolf algorithm for breast cancer diagnosis.

Medical image classification (IC) is a method for categorizing images according to the appropriate pathological stage. It is a crucial stage in computer-aided diagnosis (CAD) systems, which were created to help radiologists with reading and analyzing medical images as well as with the early detection of tumors and other disorders. The use of convolutional neural network (CNN) models in the medical industry has recently increased, and they achieve great results at IC, particularly in terms of high performance and robustness. The proposed method uses pre-trained models such as Dense Convolutional Network (DenseNet)-121 and Visual Geometry Group (VGG)-16 as feature extractor networks, bidirectional long short-term memory (BiLSTM) layers for temporal feature extraction, and the Support Vector Machine (SVM) and Random Forest (RF) algorithms to perform classification. For improved performance, the selected pre-trained CNN hyperparameters have been optimized using a modified grey wolf optimization method. The experimental analysis for the presented model on the Mammographic Image Analysis Society (MIAS) dataset shows that the VGG16 model is powerful for BC classification with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) of 99.86%, 99.9%, 99.7%, 97.1%, and 1.0, respectively, on the MIAS dataset and 99.4%, 99.03%, 99.2%, 97.4%, and 1.0, respectively, on the INbreast dataset.

Characterization of a novel mitophagy-related 5-genes signature for diagnosis of acute myocardial infarction

Myocardial infarction (MI) and the ensuing heart failure (HF) remain the main cause of morbidity and mortality worldwide. One of the strategies to combat MI and HF lies in the ability to accurately predict the onset of these disorders. Alterations in mitochondrial homeostasis have been reported to be involved in the pathogenesis of various cardiovascular diseases (CVDs). In this regard, perturbations to mitochondrial dynamics leading to impaired clearance of dysfunctional mitochondria have been previously established to be a crucial trigger for MI/HF.In this study, we found that MI patients could be classified into three clusters based on the expression levels of mitophagy-related genes and consensus clustering. We identified a mitophagy-related diagnostic 5-genes signature for MI using support vector machines-Recursive Feature Elimination (SVM-RFE) and random forest, with the area under the ROC curve (AUC) value of the predictive model at 0.813. Additionally, the single-cell transcriptome and pseudo-time analyses showed that the mitoscore was significantly upregulated in macrophages, endothelial cells, pericytes, fibroblasts and monocytes in patients with ischemic cardiomyopathy, while sequestosome 1 (SQSTM1) exhibited remarkable increase in the infarcted (ICM) and non-infarcted (ICMN) myocardium samples dissected from the left ventricle compared with control samples. Lastly, through analysis of peripheral blood from MI patients, we found that the expression of SQSTM1 is positively correlated with troponin-T (P < 0.0001, R = 0.4195, R2 = 0.1759). Therefore, this study provides the rationale for a cell-specific mitophagy-related gene signature as an additional supporting diagnostic for CVDs.

Relative value of novel systemic immune-inflammatory indices and classical hematological parameters in predicting depression, suicide attempts and treatment response

This study compared the power of the novel inflammatory markers systemic immune inflammation index (SII) and the system inflammation response index (SIRI) versus the classical hematological indices neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), platelet-to-lymphocyte ratio (PLR), and platelet counts in distinguishing between major depressive disorder (MDD) with and without suicide attempts and distinguishing the non-response to selective serotonin reuptake inhibitor (SSRI) treatment. A total of 139 young adult MDD patients and 54 healthy controls (HC) were included. We found that, in comparison to HC, baseline NLR, PLR, SII, and SIRI were significantly higher in MDD patients, but only NLR and SII had area under the ROC curve (AUC) values greater than 0.7. MDD patients with suicide attempts (SA) showed significantly higher baseline MLR and SIRI, and a tendency to increase NLR compared to those without SA. In terms of AUC, sensitivity, and specificity, NLR was better than MLR, SIRI, SII, and PLR in distinguishing SA. Non-responders to SSRI treatment showed a significant increase in baseline platelet count and PLR compared to responders with an AUC greater than 0.7. These findings highlight the potential benefit of combining novel and classical hematological indices in predicting depression, suicide attempts and treatment response.

Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study.

Sepsis triggers a harmful immune response due to infection, causing high mortality. Predicting sepsis outcomes early is vital. Despite machine learning's (ML) use in medical research, local validation within the Medical Information Mart for Intensive Care IV (MIMIC-IV) database is lacking. We aimed to devise a prognostic model, leveraging MIMIC-IV data, to predict sepsis mortality and validate it in a Chinese teaching hospital. MIMIC-IV provided patient data, split into training and internal validation sets. Four ML models logistic regression (LR), support vector machine (SVM), deep neural networks (DNN), and extreme gradient boosting (XGBoost) were employed. Shapley additive interpretation offered early and interpretable mortality predictions. Area under the ROC curve (AUROC) gaged predictive performance. Results were cross verified in a Chinese teaching hospital. The study included 27,134 sepsis patients from MIMIC-IV and 487 from China. After comparing, 52 clinical indicators were selected for ML model development. All models exhibited excellent discriminative ability. XGBoost surpassed others, with AUROC of 0.873 internally and 0.844 externally. XGBoost outperformed other ML models (LR: 0.829; SVM: 0.830; DNN: 0.837) and clinical scores (Simplified Acute Physiology Score II: 0.728; Sequential Organ Failure Assessment: 0.728; Oxford Acute Severity of Illness Score: 0.738; Glasgow Coma Scale: 0.691). XGBoost's hospital mortality prediction achieved AUROC 0.873, sensitivity 0.818, accuracy 0.777, specificity 0.768, and F1 score 0.551. We crafted an interpretable model for sepsis death risk prediction. ML algorithms surpassed traditional scores for sepsis mortality forecast. Validation in a Chinese teaching hospital echoed these findings.

Real-world evaluation of RetCAD deep-learning system for the detection of referable diabetic retinopathy and age-related macular degeneration

ABSTRACT Clinical Relevance The challenges of establishing retinal screening programs in rural settings may be mitigated by the emergence of deep-learning systems for early disease detection. Background Deep-learning systems have demonstrated promising results in retinal disease detection and may be particularly useful in rural settings where accessibility remains a barrier to equitable service provision. This study aims to evaluate the real-world performance of Thirona RetCAD for the detection of referable diabetic retinopathy and age-related macular degeneration in a rural Australian population. Methods Colour fundus images from participants with known diabetic retinopathy or age-related macular degeneration were randomly selected from ophthalmology clinics in four rural Australian centres. Grading was confirmed retrospectively by two retinal specialists. RetCAD produced a quantitative measure (0–100) for DR and AMD severity. The area under the ROC curve (AUC) was calculated. Sensitivity, specificity, and positive and negative predictive values were calculated at a pre-defined cut-point of ≥50. Results A total of 150 images from 82 participants were included. The mean age (SD) was 64.0 (12.8) years. Seventy-nine (52.7%) eyes had evidence of referable DR, while 54 (36.0%) had evidence of referable AMD. The AUC for referable DR detection was 0.971 (95% CI 0.950–0.936) with a sensitivity of 86.1% (76.8%–92.0%) and a specificity of 91.6% (82.8%−96.1%) at the pre-defined cut-point. Using the Youden Index method, the optimal cut-point was 41.2 (sensitivity 93.7%, specificity 90.1%). The AUC for the detection of referable AMD was 0.880 (0.824–0.936). At the pre-defined cut-point sensitivity was 88.9% (77.8%–94.8%) and specificity was 66.7% (56.8%–75.3%). The optimal cut-point was 52.6 (sensitivity 87.0%, specificity 75.0%). Conclusion RetCAD is comparable with but does not outperform equivalent deep-learning systems for retinal disease detection. RetCAD may be suitable as an automated screening tool in a rural Australian setting.

Exploring the prognostic landscape of oral squamous cell carcinoma through mitochondrial damage-related genes

Oral squamous cell carcinoma (OSCC), the most prevalent form of oral cancer, poses significant challenges to the medical community due to its high recurrence rate and low survival rate. Mitochondrial Damage-Related Genes (MDGs) have been closely associated with the occurrence, metastasis, and progression of OSCC. Consequently, we constructed a prognostic model for OSCC based on MDGs and identified potential mitochondrial damage-related biomarkers. Gene expression profiles and relevant clinical information were obtained from The Cancer Genome Atlas (TCGA) database. Differential analysis was conducted to identify MDGs associated with OSCC. COX analysis was employed to screen seven prognosis-related MDGs and build a prognostic prediction model for OSCC. Cases were categorized into low-risk or high-risk groups based on the optimal risk score threshold. Kaplan-Meier (KM) analysis revealed significant survival differences (P < 0.05). Additionally, the area under the ROC curve (AUC) for patient survival at 1 year, 3 years, and 5 years were 0.687, 0.704, and 0.70, respectively, indicating a high long-term predictive accuracy of the prognostic model. To enhance predictive accuracy, age, gender, risk score, and TN staging were incorporated into a nomogram and verified using calibration curves. Risk scoring based on MDGs was identified as a potential independent prognostic biomarker. Furthermore, BID and SLC25A20 were identified as two potential independent mitochondrial damage-related prognostic biomarkers, offering new therapeutic targets for OSCC.

Serum Cystatin C levels increase with increasing visceral fat area in patients with type 2 diabetes mellitus

The present study aimed to explore the association between serum cystatin C (Cys-C) levels and visceral fat area (VFA) in patients with type 2 diabetes mellitus (T2DM). A total of 208 previously diagnosed T2DM patients who visited our hospital from September 2019 to December 2021 were included and divided into three groups based on tertiles of Cys-C levels, namely, Groups C1, C2, and C3. The clinical data of the subjects were collected, biochemical parameters such as Cys-C levels were determined, and bioelectrical impedance analysis was applied to determine the VFA and subcutaneous fat area (SFA). The VFA in Group C1 was lower than that in Groups C2 and C3 (all P < 0.05), with no significant difference in VFA between Groups C2 and C3 (P > 0.05). Spearman’s correlation analysis revealed that the serum Cys-C level was positively correlated with age, VFA, SFA, insulin resistance index, waist circumference, body mass index, systolic blood pressure, serum creatinine level, and blood uric acid level (r = 0.543, 0.353, 0.168, 0.148, 0.365, 0.264, 0.25, 0.497, and 0.155, respectively; P < 0.05) and negatively correlated with glycated haemoglobin levels (r = -0.175, P < 0.05). Univariate linear regression analysis revealed that VFA was positively correlated with the Cys-C level (β = 0.002, 95% CI = 0.001–0.003, P < 0.05), with an increase of 0.002 mg/L in the Cys-C level for each 1 cm2 increase in VFA. Further multivariate linear regression analysis was performed with the serum Cys-C level as the dependent variable and age, VFA, SFA, insulin resistance (HOMA-IR), WC, BMI, SBP, Cr, UA, and HbA1c as the independent variables. The results suggested that VFA was positively correlated with serum Cys-C level (β = 0.001, 95% CI = 0.000–0.002, P < 0.05), with serum Cys-C levels increasing by 0.001 mg/L for every 1 cm2 increase in VFA. Using a VFA ≥ 100 cm2 as the criterion for visceral obesity, ROC analysis revealed that the Cys-C level was a better predictor of visceral obesity, with an area under the ROC curve (AUC) of 0.701 (95% CI = 0.631–0.771, P < 0.05), an optimal cut-off of 0.905 mg/L, and a sensitivity and specificity of 58.3% and 75.2%, respectively. The results suggested that the serum Cys-C level was correlated with the VFA in patients with T2DM and that Cys-C may play a vital role in T2DM patients with visceral obesity.

Radiomics signature for automatic hydronephrosis detection in unenhanced Low-Dose CT

PurposeTo investigate the diagnostic performance of an automatic pipeline for detection of hydronephrosis on kidney's parenchyma on unenhanced low-dose CT of the abdomen. MethodsThis retrospective study included 95 patients with confirmed unilateral hydronephrosis in an unenhanced low-dose CT of the abdomen. Data were split into training (n = 67) and test (n = 28) cohorts. Both kidneys for each case were included in further analyses, whereas the kidney without hydronephrosis was used as control. Using the training cohort, we developed a pipeline consisting of a deep-learning model for automatic segmentation (a Convolutional Neural Network based on nnU-Net architecture) of the kidney's parenchyma and a radiomics classifier to detect hydronephrosis. The models were assessed using standard classification metrics, such as area under the ROC curve (AUC), sensitivity and specificity, as well as semantic segmentation metrics, including Dice coefficient and Jaccard index. ResultsUsing manual segmentation of the kidney’s parenchyma, hydronephrosis can be detected with an AUC of 0.84, a sensitivity of 75% and a specificity of 82%, a PPV of 81% and a NPV of 77%. Automatic kidney segmentation achieved a mean Dice score of 0.87 and 0.91 for the right and left kidney, respectively. Additionally, automatic segmentation achieved an AUC of 0.83, a sensitivity of 86%, specificity of 64%, PPV of 71%, and NPV of 82%. ConclusionOur proposed radiomics signature using automatic kidney's parenchyma segmentation allows for accurate hydronephrosis detection on unenhanced low-dose CT scans of the abdomen independently of widened renal pelvis. This method could be used in clinical routine to highlight hydronephrosis to radiologists as well as clinicians, especially in patients with concurrent parapelvic cysts and might reduce time and costs associated with diagnosing hydronephrosis.

Based on hematoma and perihematomal tissue NCCT imaging radiomics predicts early clinical outcome of conservatively treated spontaneous cerebral hemorrhage

Spontaneous intracerebral hemorrhage (ICH) is a very serious kind of stroke. If the outcome of patients can be accurately assessed at the early stage of disease occurrence, it will be of great significance to the patients and clinical treatment. The present study was conducted to investigate whether non-contrast computer tomography (NCCT) models of hematoma and perihematomal tissues could improve the accuracy of short-term prognosis prediction in ICH patients with conservative treatment. In this retrospective analysis, a total of 166 ICH patients with conservative treatment during hospitalization were included. Patients were randomized into a training group (N = 132) and a validation group (N = 34) in a ratio of 8:2, and the functional outcome at 90 days after clinical treatment was assessed by the modified Rankin Scale (mRS). Radiomic features of hematoma and perihematomal tissues of 5 mm, 10 mm, 15 mm were extracted from NCCT images. Clinical factors were analyzed by univariate and multivariate logistic regression to identify independent predictive factors. In the validation group, the mean area under the ROC curve (AUC) of the hematoma was 0.830, the AUC of the perihematomal tissue within 5 mm, 10 mm, 15 mm was 0.792, 0.826, 0.774, respectively, and the AUC of the combined model of hematoma and perihematomal tissue within 10 mm was 0.795. The clinical-radiomics nomogram consisting of five independent predictors and radiomics score (Rad-score) of the hematoma model were used to assess 90-day functional outcome in ICH patients with conservative treatment. Our findings found that the hematoma model had better discriminative efficacy in evaluating the early prognosis of conservatively managed ICH patients. The visual clinical-radiomics nomogram provided a more intuitive individualized risk assessment for 90-day functional outcome in ICH patients with conservative treatment. The hematoma could remain the primary therapeutic target for conservatively managed ICH patients, emphasizing the need for future clinical focus on the biological significance of the hematoma itself.

Facial Emotion Recognition with Deep Neural Network: A Study of Visual Geometry Group-16 (VGG16) Technique with Data Augmentation for Improved Precision

Emotions play a significant role in both verbal and nonverbal communication. Facial emotion recognition has applications in various sectors where we can get real-time feedback about student activeness by detecting their expression. In this paper, we aim to provide an improved deep-learning technique to detect emotions by using publicly available datasets to perform this detection. To get more data for the well-being of the Machine Learning Model, we have used data augmentation using the TensorFlow framework. Visual Geometry Group-16 (VGG16) is a convolutional neural network of 16 layers deep. There has been an alteration to the default VGG16 structure to get better classification results. Various optimization algorithms and loss functions increase the model’s accuracy. We have used many evaluation parameters from the technical side, like precision, accuracy, recall, Area Under the Receiver Operating Characteristic Curve (AUC), and F1 Score. The proposed model has an accuracy of 89% while having a precision of 81 percent for classification. We have achieved an F1 Score of 0.42 and an area under the ROC curve (AUC) of 0.734. Overall, it would be beneficial for analyzing and categorizing positive and negative emotions, which would aid in detecting signs of stress, anxiety, and burnout, as well as taking preventive actions to enhance well-being.

Factors affecting biochemical pregnancy loss (BPL) in preimplantation genetic testing for aneuploidy (PGT-A) cycles: machine learning-assisted identification

PurposeTo determine the factors influencing the likelihood of biochemical pregnancy loss (BPL) after transfer of a euploid embryo from preimplantation genetic testing for aneuploidy (PGT-A) cycles.MethodsThe study employed an observational, retrospective cohort design, encompassing 6020 embryos from 2879 PGT-A cycles conducted between February 2013 and September 2021. Trophectoderm biopsies in day 5 (D5) or day 6 (D6) blastocysts were analyzed by next generation sequencing (NGS). Only single embryo transfers (SET) were considered, totaling 1161 transfers. Of these, 49.9% resulted in positive pregnancy tests, with 18.3% experiencing BPL. To establish a predictive model for BPL, both classical statistical methods and five different supervised classification machine learning algorithms were used. A total of forty-seven factors were incorporated as predictor variables in the machine learning models.ResultsThroughout the optimization process for each model, various performance metrics were computed. Random Forest model emerged as the best model, boasting the highest area under the ROC curve (AUC) value of 0.913, alongside an accuracy of 0.830, positive predictive value of 0.857, and negative predictive value of 0.807. For the selected model, SHAP (SHapley Additive exPlanations) values were determined for each of the variables to establish which had the best predictive ability. Notably, variables pertaining to embryo biopsy demonstrated the greatest predictive capacity, followed by factors associated with ovarian stimulation (COS), maternal age, and paternal age.ConclusionsThe Random Forest model had a higher predictive power for identifying BPL occurrences in PGT-A cycles. Specifically, variables associated with the embryo biopsy procedure (biopsy day, number of biopsied embryos, and number of biopsied cells) and ovarian stimulation (number of oocytes retrieved and duration of stimulation), exhibited the strongest predictive power.

Gestation-dependent increase in cervicovaginal pro-inflammatory cytokines and cervical extracellular matrix proteins is associated with spontaneous preterm delivery within 2 weeks of index assessment in South African women.

Inflammation-induced remodelling of gestational tissues that underpins spontaneous preterm birth (sPTB, delivery < 37 weeks' gestation) may vary by race and context. To explore relationships between markers of these pathological processes, we (a) characterised the cervicovaginal fluid (CVF) cytokine profiles of pregnant South African women at risk of PTB; (b) determined CVF matrix-metalloproteinase-9 (MMP-9) and its regulator tissue inhibitor of metalloproteinase-1 (TIMP-1); and (c) explored the predictive potential of these markers for sPTB. The concentrations of 10 inflammatory cytokines and MMP-9 and TIMP-1 were determined by ELISA in CVF samples from 47 non-labouring women at high risk of PTB. We studied CVF sampled at three gestational time points (GTPs): GTP1 (20-22 weeks, n = 37), GTP2 (26-28 weeks, n = 40), and GTP3 (34-36 weeks, n = 29) and analysed for changes in protein concentrations and predictive capacities (area under the ROC curve (AUC) and 95% confidence interval (CI)) for sPTB. There were 11 (GTP1), 13 (GTP2), and 6 (GTP3) women who delivered preterm within 85.3 ± 25.9, 51.3 ± 15.3, and 11.8 ± 7.5 (mean ± SD) days after assessment, respectively. At GTP1, IL-8 was higher (4-fold, p = 0.02), whereas GM-CSF was lower (~1.4-fold, p = 0.03) in the preterm compared with term women with an average AUC = 0.73. At GTP2, IL-1β (18-fold, p < 0.0001), IL-8 (4-fold, p = 0.03), MMP-9 (17-fold, p = 0.0007), MMP-9/TIMP-1 ratio (9-fold, p = 0.004), and MMP-9/GM-CSF ratio (87-fold, p = 0.005) were higher in preterm compared with term women with an average AUC = 0.80. By contrast, IL-10 was associated with term delivery with an AUC (95% CI) = 0.75 (0.55-0.90). At GTP3, IL-1β (58-fold, p = 0.0003), IL-8 (12-fold, p = 0.002), MMP-9 (296-fold, p = 0.03), and TIMP-1 (35-fold, p = 0.01) were higher in preterm compared with term women with an average AUC = 0.85. Elevated IL-1β was associated with delivery within 14 days of assessment with AUC = 0.85 (0.67-0.96). Overall, elevated MMP-9 at GTP3 had the highest (13.3) positive likelihood ratio for distinguishing women at risk of sPTB. Lastly, a positive correlation between MMP-9 and TIMP-1 at all GTPs (ρ ≥ 0.61, p < 0.01) for women delivering at term was only observed at GTP1 for those who delivered preterm (ρ = 0.70, p < 0.03). In this cohort, sPTB is associated with gestation-dependent increase in pro-inflammatory cytokines, decreased IL-10 and GM-CSF, and dysregulated MMP-9-TIMP-1 interaction. Levels of cytokine (especially IL-1β) and ECM remodelling proteins rise significantly in the final 2 weeks before the onset of labour when sPTB is imminent. The signalling mechanisms for these ECM remodelling observations remain to be elucidated.