Objective: To explore the predictive value of circulating lymphocyte subpopulation characteristics for the prognosis of stage III-IV non-small cell lung cancer (NSCLC) patients treated with epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKI).
Methods: Seventy-two cases of stage III-IV NSCLC patients treated with EGFR-TKI were retrospectively selected as study subjects. The therapeutic effects of the patients were classified into three categories: complete remission (CR) or partial remission (PR) was classified as the remission group; Stable disease (SD) was classified as the stable disease group. Progression disease (PD) is classified as the progression disease group. The clinical data (general information and circulating lymphocyte subpopulation count) of the patients with different treatment effects were compared. The patients were followed up for 5 years, and factors influencing the progression-free survival (PFS) and overall survival (OS) were screened using the COX regression model. Receiver Operating Characteristic (ROC) was plotted to get the optimal stage value of circulating lymphocytes. Changes in PFS and OS of the patients were compared using the KM survival curve.
Results: Analysis of circulating lymphocyte subsets showed that the counts of CD4 + CD45RA + CD62L + T cells in the three groups of patients presented a gradient distribution of remission group > stable disease group > progression disease group. The count of CD19 + B cells in the progression disease group (148.79 ± 39.62) was higher than that in the remission group (118.34 ± 36.71). CD4 + CD45RA + CD62L + T cells were an independent influencing factor of PFS in patients (P < 0.05). ROC curve analysis confirmed that the area under the curve (AUC) of CD4 + CD45RA + CD62L + T cell count for predicting the prognosis of NSCLC patients was 0.840 (95% CI) with a cut-off value of 126.47 and a Youden index of 0.570. The PFS of patients in the high-level group of CD4 + CD45RA + CD62L + T cells was significantly higher than that in the low-level group (P < 0.05).
Conclusion: Circulating lymphocyte subsets were associated with the therapeutic effect of stage III-IV NSCLC patients treated with EGFR-TKI and can be used as a prognostic indicator of PFS in patients treated with EGFR-TKI, but a comprehensive assessment should be made in combination with clinical factors (such as stage and TKI generation).
Objectives: This study aimed to develop and validate a CT radiomics-based explainable machine learning model for precise diagnosing of malignancy and benignity specifically in endometrial cancer (EC) patients.
Methods: A total of 83 EC patients from two centers, including 46 with malignant and 37 with benign conditions, were included, with data split into a training set (n = 59) and a testing set (n = 24). The regions of interest (ROIs) were manually segmented from pre-surgical CT scans, and 1132 radiomic features were extracted from the pre-surgical CT scans using Pyradiomics. Six explainable machine learning (ML) modeling algorithms were implemented, respectively, for determining the optimal radiomics pipeline. The diagnostic performance of the radiomic model was evaluated by using sensitivity, specificity, accuracy, precision, F1 score, area under the receiver operating characteristic curve (AUROC), and area under the precision-recall curve (AUPRC). To enhance clinical understanding and usability, we separately implemented SHAP analysis and feature mapping visualization and evaluated the calibration curve and decision curve.
Results: By comparing six modeling strategies, the Random Forest model emerged as the optimal choice for diagnosing EC, with a training AUROC of 1.00 and a testing AUROC of 0.96. SHAP identified the most important radiomic features, revealing that all selected features were significantly associated with EC (p < 0.05). Radiomics feature maps also provide a feasible assessment tool for clinical applications. Decision curve analysis (DCA) indicated a higher net benefit for our model compared to the "All" and "None" strategies, suggesting its clinical utility in identifying high-risk cases and reducing unnecessary interventions.
Conclusion: CT radiomics-based explainable ML model achieved high diagnostic performance, which could be used as an intelligent auxiliary tool for the diagnosis of endometrial cancer.
Edible polymeric composite hydrogel films offer a promising solution for cultured meat production. These films are made by incorporating natural polysaccharides, synthetic biocompatible polymers, and antioxidants within the scaffolds. This approach can help combat global climate change and meet the increasing demand for sustainable food sources. The utilization of edible polysaccharides in the fabrication of hydrogels is a cost-effective and sustainable approach, which serves as effective scaffolding in the cultivation of meat. The polymeric composite hydrogel films, designated as "CSCP" (curcumin-starch-carrageenan-PVA) with varying concentrations of polymers, consist of curcumin (an antioxidant and coloring agent), starch (potato), kappa (κ)-carrageenan, and poly(vinyl alcohol) (PVA), with PVA being classified as generally recognized as safe (GRAS) for use in food applications. These edible polymeric composite hydrogel films were prepared with glycerol, serving as a plasticizer, and succinic acid, a crosslinker, through solvent casting and thermal treatment methods. Analytical techniques, including field-emission scanning electron microscopy (FE-SEM), X-ray diffraction (XRD), Fourier transform infrared (FTIR) spectroscopy, and tensile strength testing, were employed to evaluate the morphology, crystalline nature, composition, and mechanical properties of the fabricated CSCP scaffolds. The incorporation of glycerol and succinic acid facilitates the plasticizing and cross-linking of the polymeric materials via hydroxyl and carboxyl group interactions during film formation. Increasing the potato starch content in the CSCP-2 composite hydrogel film reduced its mechanical strength. This is because the starch disrupted the polymer's crystalline regions. The resulting amorphous structure improved the film's flexibility and elasticity. Nevertheless, the increased potato starch content adversely affects interfacial adhesion, reducing tensile strength. The swelling ratio of the CSCP-2 composite hydrogel film slightly decreases with higher potato starch content, which limits hydrogen bonding interactions with water. Notably, the CSCP composite hydrogel films support adhesion and proliferation of bovine muscle satellite cells (MuSCs) with good cytocompatibility for up to 21 days. However, a slight decrease in metabolic activity on CSCP-2 films was observed. This was likely due to nutrient depletion and limited oxygen diffusion caused by cell multilayering. Overall, the starch-based edible CSCP composite hydrogel films exhibit significant potential as scaffolds for culturing bovine muscle satellite cells (myosatellite cells), paving the way for large-scale production of three-dimensional (3D) cultured meat.
Background: Carotid body (CB) ablation can reduce sympathetic activity and blood pressure but impair the body's ability to regulate hypoxia. This study explores the efficacy and safety of using microbubble contrast agents combined with high mechanical index diagnostic ultrasound irradiation (HMIUI) to modulate CB activity in treatment of hypertension in rabbits.
Methods: Obese hypertensive rabbits were randomly divided into three groups: unilateral intervention group (UIG, n = 6), bilateral intervention group (BIG, n = 10), and control group (CG, n = 7). Rabbits received intravenous injection of sulfur hexafluoride microbubbles for 15 min, and irradiation at the carotid bifurcation by continuous diagnostic ultrasound FLASH mode simultaneously. Blood pressure (BP), hypoxic ventilatory response (HVR), peripheral chemoreceptor sensitivity (PCS), and baroreceptor sensitivity (BRS) were measured, and values were compared with before the intervention and 1 month after. In addition, pathology and electron microscopy were used to observe the histological and ultrastructural changes of CB.
Results: In both UIG and BIG groups, systolic and diastolic blood pressure significantly decreased compared to pre-intervention (p < 0.05). Compared to the control group, the BIG group showed a decrease of 10 mmHg exceeding in systolic and diastolic blood pressures. HVR and PCS decreased by nearly 50% from pre-intervention. Changes in CB injury and fibrous tissue proliferation were found by Histological. TUNEL assay showed varying degrees of apoptosis in the treated CB, and immunofluorescence confirmed the reducing expression of type I and II cells.
Conclusions: Ultrasound microbubbles combined with HMIUI effectively modulate CB function and reduce blood pressure in an obese hypertensive rabbit model in the short term.
Introduction: Epilepsy due to hypothalamic hamartoma (HH) is associated with epileptic encephalopathy and often requires surgical intervention, as medications are ineffective at reducing the seizures. However, the first step of disentangling the impact of the surgery on the broader whole-brain networks, a biomarker of encephalopathy compared to controls, is not quantified. Subtle pre- and post-operative networks can elude conventional rs-fMRI analysis.
Methods: We retrospectively analyzed rs-fMRI from 56 HH patients scanned before and 6 months after surgery. We developed a two-stage contrastive learning-based algorithm to classify the motor, vision, language, frontal, and temporal networks as pre- vs post-operative. In stage one, a multimodal contrastive encoder jointly ingests 3D spatial Independent Component Analysis (ICA) maps and their corresponding 1D temporal ICA time series to learn embeddings that distinguish pre-operative from post-operative states for each network while separating embeddings of different networks. In stage two, a lightweight classifier refines these embeddings, augmented by original ICA inputs, to classify each network as pre-operative or post-operative.
Results: Visualization of the learned feature space with t-SNE revealed clear separation by pre- vs post-surgical condition across all five networks. Across networks, mean accuracy ranged from 0.85 to 0.90, sensitivity from 0.79 to 0.90, specificity from 0.87 to 0.93, F1-score from 0.83 to 0.90 and AUC from 0.90 to 0.94 in stratified cross validation.
Conclusions: Contrastive learning can sensitively detect functional shifts in critical cortical networks that previous traditional analyses may overlook. These findings inform broader shifts in whole-brain network functioning following effective HH surgery and establish a featurewise distinction between preoperative and postoperative states, motivating future studies that compare HH patients to healthy controls to quantify network recovery.
Background: Prostate cancer (PC) is an epithelial malignant tumor that occurs in the prostate. N6 methylpurine (m6A) methylation regulates the tumor immune microenvironment. This study aimed to investigate the expression of m6A regulatory factor in PC and its relationship with prognosis.
Methods: PC tissues and adjacent tissues were collected from PC patients who underwent surgical resection. The content of m6A regulator YTH m6A RNA binding protein 1 (YTHDF1) and insulin-like growth factor binding protein 2 (IGFBP2) was examined using Immunohistochemistry (IHC). The survival prognosis was predicted through Kaplan Meier survival curve. The patients were grouped into good and poor prognosis group according to whether recurrence and metastasis occurred within the 62 months of follow-up. Logistic regression analysis was adopted to analyze the risk factors.
Results: YTHDF1 and IGFBP2 were localized in the cytoplasm of PC tissues. The positive expression rate of YTHDF1 in cancer tissues was 69.81% (37/53), which was much higher than the 33.96% (18/53) in adjacent tissues (P < 0.01). The positive expression rate of IGFBP2 in cancer tissues was 62.26% (33/53), which was markedly higher than the 28.30% (15/53) in adjacent tissues (P < 0.01). The proportion of TNM stage III + IV, high Gleason score and PSA > 15 ng/mL was visibly higher in patients with positive expression of YTHDF1 than in patients with negative expression of YTHDF1 (P < 0.05). The proportion of TNM stage III + IV, high Gleason score and PSA > 15 ng/mL in IGFBP2 positive patients was sensibly higher than that in IGFBP2 negative patients (P < 0.05). YTHDF1 positive group had a median survival time of 35 months, which was evidently shorter than 44 months of YTHDF1 negative group (P < 0.05). The IGFBP2 positive group had a median survival time of 32 months, which was clearly shorter than 45 months of IGFBP2 negative group (P < 0.05). In addition, TNM stage, Gleason score, PSA, YTHDF1 and IGFBP2 were independent risk factors for poor prognosis of PC (P < 0.05).
Conclusions: YTHDF1 and IGFBP2 were independent risk factors for poor prognosis of PC patients. They may be involved in the progression of prostate cancer, and serve as potential biomarkers for evaluating the prognosis of patients. However, its clinical translation value needs to be further verified by large sample and multi-center studies.
Traditional research on drug addiction assessment relies primarily on psychological scales, self-reports from drug users, and subjective judgments from doctors, ands lacks objective physiological indicators and quantitative evaluation. This study introduces a visual trigger paradigm designed to elicit drug cravings in individuals with substance addiction, employing Electroencephalogram (EEG) and Near-Infrared Spectroscopy (NIRS) for data acquisition. The dataset comprises recordings from 20 healthy individuals and 36 individuals with drug addiction. A deep learning algorithm named AR-TSNET, which utilizes feature-level fusion, is proposed to classify. The deep learning network uses two modules called Tception and Sception to process EEG and NIRS data. Tception extracts features from EEG data while Sception extracts features from NIRS data. Different attention mechanisms are incorporated to better align with the characteristics of the data. The attention mechanism assigns weights to features, reducing the interference of redundant features. Residual connections are utilized to address the issue of information loss caused by increased network depth, thereby enhancing the stability and robustness of the model. The classification accuracy achieved through k-fold cross-validation is 92.6%. The confusion matrix and ROC curve fully demonstrate the excellent performance of the model. A comparison of single-modal and bimodal evaluation metrics confirms the superior performance of bimodal data with higher information content. These results provide preliminary evidence that the proposed method is a promising and effective approach for assessing the severity of drug addiction. By leveraging advanced deep learning techniques, the method demonstrates not only high accuracy and reliability but also the potential for broader applications in addiction research and clinical practice. Furthermore, its straightforward implementation and objective nature offer valuable insights into addiction severity while reducing reliance on subjective assessments.
Background: The urosepsis after percutaneous nephrolithotomy (PCNL) is a critical health risk necessitating prompt medical identification and intervention. Nevertheless, a deficiency exists in the availability of a tool for precise and timely predictive analysis. The purpose is to establish a machine learning (ML) model using radiomic features and clinical data to predict urosepsis following PCNL.
Method: This study retrospectively included 401 patients with kidney stones from two centers who underwent PCNL. To enhance the dataset's equilibrium, the synthetic minority over-sampling technique for regression with Gaussian noise (SMOGN) was used to resample the training set. The screening of radiomics features and the construction of radiomics scores were completed by applying the Absolute Shrinkage Selection Operator (LASSO). Subsequently, the critical clinical indicators for urosepsis were pinpointed through the application of a multivariate logistic regression. The performance of seven ML algorithms was compared for the combined dataset that incorporated clinical variables and radiomics scores. The efficacy of these models was assessed through the implementation of a fivefold cross-validation process. Ultimately, the Shapley Additive exPlanations (SHAP) methodology was utilized to provide a visual and interpretative analysis of the optimal model.
Result: Among 401 patients, 30 cases (7.48%) were diagnosed with urosepsis. The radiomics score, established by 13 radiomics features, was combined with six important clinical features (including urine nitrite positivity, stone volume, mean intrarenal pressures, urine white blood cells, and operation time) to construct a combined dataset. Comparative analysis of seven machine learning (ML) models revealed that CatBoost demonstrated superior predictive performance. The model achieved area under the receiver operating characteristic curve (AUC-ROC) values of 0.88, 0.94, and 0.89 on the training, internal test, and external validation sets, respectively. Corresponding area under the precision-recall curve (AUC-PR) values were 0.92, 0.75, and 0.63. The SHAP value method identifies key features influencing prediction outcomes, with the radiomics score and urine nitrite positivity being the top contributors to the model. We deployed the optimal prediction model to a web for clinical application ( https://predictive-model-for-urosepsis.streamlit.app/ ).
Conclusion: This study constructed a predictive model that incorporates clinical risk characteristics and radiomics scores to assess the risk of urosepsis after PCNL, with SHAP visualization for clinical physicians to formulate evaluation strategies.
Objectives: To address the absence of a systematic evaluation method for network architecture selection in ophthalmic ultrasound image detection tasks, this study proposes a modular ablation analysis framework based on orthogonal experimental design.
Methods: A clinical data set comprising 1121 ocular ultrasound images was established. YOLOv10-v12 were decoupled into backbone, neck, and head modules. A three-stage evaluation was conducted: (1) single-module benchmarking, performed via controlled variable experiments; (2) orthogonal combination experiments using an L9(34) array, analyzed through range analysis and interaction heatmaps; and (3) optimal architecture selection, implemented via Pareto front analysis. The best model was applied to ocular tissue localization, and a segmented sound velocity matching algorithm was used to automatically measure biometric parameters, including anterior chamber depth, lens thickness, and axial length.
Results: The backbone improved both accuracy and efficiency, while the neck and head exhibited a speed-accuracy trade-off. The neck most significantly influenced detection accuracy, and the head dominated computational efficiency. The optimal combination (Bv11-Nv11-Hv10) achieved 64.0% mAP at 26 FPS, while the mobile-optimized variant (Bv10-Nv10-Hv11) attained 63.5% mAP with only 8.6 MB parameters. Automatic and manual measurements showed strong agreement (mean absolute error ≤ 0.133 mm, ICC ≥ 0.839).
Conclusions: This study validates the feasibility of cross-version module combination. The proposed framework offers a systematic, quantitative decision-making basis for network design in ophthalmic ultrasound, balancing accuracy, speed, and deployment feasibility. Clinical results confirm high consistency between automatic and manual measurements, supporting automated and precise ocular biometry.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：