Objective To explore the feasibility of long non-coding RNAs (lncRNAs) as biomarkers for radiation-induced intestinal injury. Methods Mice were exposed to 15 Gy of ⁶⁰Co γ-rays to the abdominal area. The pathological changes in intestinal tissues were analyzed at 72 h post-irradiation to confirm the successful establishment of the radiation-induced intestinal injury model. Real-time quantitative PCR was conducted to detect the expression of candidate radiation-responsive lncRNAs in the jejunum, jejunal crypts, colon tissues, and plasma of irradiated mice. Human intestinal epithelial cell line HIEC-6 and human colon epithelial cell line NCM460 were exposed to 0, 5, 10, and 15 Gy of ⁶⁰Co γ-rays. The expression levels of candidate lncRNAs were measured at 4, 24, 48, and 72 h post-irradiation to observe their changes with the irradiation dose. Results Pathological analysis showed that abdominal irradiation with 15 Gy successfully established an acute radiation-induced intestinal injury mouse model. Real-time quantitative PCR showed that Dino, Lncpint, Meg3, Dnm3os, Trp53cor1, Pvt1, and Neat1 were significantly upregulated following the occurrence of radiation-induced intestinal injury (P < 0.05). Among them, Meg3 and Dnm3os in mouse plasma were significantly upregulated (P < 0.05), while Gas5 was significantly downregulated (P < 0.05). In HIEC-6 and NCM460 cells, the expression levels of DINO, MEG3, DNM3OS, and GAS5 showed dose-dependent patterns at certain time points (P < 0.05). Conclusion The lncRNAs encoded by MEG3, DNM3OS, and GAS5 in intestinal epithelial cells are responsive to ionizing radiation. Consistent differential expression changes were detected in mouse plasma and intestinal tissues, indicating their potential as biomarkers for radiation-induced intestinal injury.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

During orthodontic treatment, clinical monitoring of patients is a crucial factor in determining treatment success. It aids in timely problem detection and resolution, ensuring adherence to the intended treatment plan. In recent years, digital technology has increasingly permeated orthodontic clinical diagnosis and treatment, facilitating clinical decision-making, treatment planning, and follow-up monitoring. This review summarizes recent advancements in digital technology for monitoring orthodontic tooth movement, related complications, and appliance-wearing compliance. It aims to provide insights for researchers and clinicians to enhance the application of digital technology in orthodontics, improve treatment outcomes, and optimize patient experience. The digitization of diagnostic data and the visualization of dental models make chair-side follow-up monitoring more convenient, accurate, and efficient. At the same time, the emergence of remote monitoring technology allows orthodontists to promptly identify oral health issues in patients and take corresponding measures. Furthermore, the multimodal data fusion method offers valuable insights into the monitoring of the root-alveolar relationship. Artificial intelligence technology has made initial strides in automating the identification of orthodontic tooth movement, associated complications, and patient compliance evaluation. Sensors are effective tools for monitoring patient adherence and providing data-driven support for clinical decision-making. The application of digital technology in orthodontic monitoring holds great promise. However, challenges like technical bottlenecks, ethical considerations, and patient acceptance remain.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

ObjectiveThis study aims to develop and validate a novel multimodal predictive model， termed criss-cross network（CCNet）-directed graph neural network（DGNN）（CGN）， for accurate assessment of pulmonary nodule progression in high-risk individuals for lung cancer， by integrating longitudinal chest computed tomography（CT） imaging with both traditional Chinese and western clinical evaluation data. MethodsA cohort of 4 432 patients with pulmonary nodules was retrospectively analyzed. A twin CCNet was employed to extract spatiotemporal representations from paired sequential CT scans. Structured clinical assessment and imaging-derived features were encoded via a multilayer perceptron， and a similarity-based alignment strategy was adopted to harmonize multimodal imaging features across temporal dimensions. Subsequently， a DGNN was constructed to integrate heterogeneous features， where nodes represented modality-specific embeddings and edges denoted inter-modal information flow. Finally， model optimization was performed using a joint loss function combining cross-entropy and cosine similarity loss， facilitating robust classification of nodule progression status. ResultsThe proposed CGN model demonstrated superior predictive performance on the held-out test set， achieving an area under the receiver operating characteristic curve（AUC） of 0.830， accuracy of 0.843， sensitivity of 0.657， specificity of 0.712， Cohen's Kappa of 0.417， and F₁ score of 0.544. Compared with unimodal baselines， the CGN model yielded a 36%-48% relative improvement in AUC. Ablation studies revealed a 2%-22% increase in AUC when compared to simplified architectures lacking key components， substantiating the efficacy of the proposed multimodal fusion strategy and modular design. Incorporation of traditional Chinese medicine （TCM）-specific symptomatology led to an additional 5% improvement in AUC， underscoring the complementary value of integrating TCM and western clinical data. Through gradient-weighted activation mapping visualization analysis， it was found that the model's attention predominantly focused on nodule regions and effectively captured dynamic associations between clinical data and imaging-derived features. ConclusionThe CGN model， by synergistically combining cross-attention encoding with directed graph-based feature integration， enables effective alignment and fusion of heterogeneous multimodal data. The incorporation of both TCM and western clinical information facilitates complementary feature enrichment， thereby enhancing predictive accuracy for pulmonary nodule progression. This approach holds significant potential for supporting intelligent risk stratification and personalized surveillance strategies in lung cancer prevention.

Aim To investigate the impact of Cinobu-facini on the proliferation,invasion,and apoptosis of HepG2 cells and the underlying mechanism.Methods The proliferation of HepG2 cells was assessed using the CCK-8 method following treatment with Cinobufaci-ni.The invasion capability of HepG2 cells was evalua-ted through Transwell assay after exposure to Cinobufa-cini.The apoptosis rates of HepG2 cells post Cinobufa-cini intervention were measured using flow cytometry,and the expression levels of VEGF in the culture medi-um of HepG2 cells were determined using enzyme-linked immunoassay.Furthermore,qRT-PCR and Western blot analyses were conducted to assess the im-pact of Cinobufacini on mRNA and protein expression levels related to the CXCL5/FOXD1/VEGF pathway.The interaction between CXCL5 and FOXD1 was inves-tigated via co-immunoprecipitation.Results Cinobufa-cini treatment led to a gradual decrease in HepG2 cell viability in a dose-dependent manner compared to the control group(P＜0.05).Moreover,Cinobufacini sig-nificantly suppressed HepG2 cell invasion(P＜0.05)while enhancing cell apoptosis(P＜0.05).Notably,Cinobufacini exhibited inhibitory effects on the CX-CL5/FOXD1/VEGF pathway,as evidenced by re-duced expression of related mRNA and proteins(P＜0.05).FOXD1 was identified as the binding site of CXCL5.Overexpression of CXCL5 resulted in in-creased proliferation and VEGF secretion by HepG2 cells(P＜0.05),and increased expression of FOXD1 and VEGF(P＜0.05).However,Cinobufacini inter-vention effectively inhibited liver cancer cell prolifera-tion and invasion(P＜0.05),promoted apoptosis(P＜0.05),reduced VEGF secretion by HepG2 cells(P＜0.05),and downregulated the expression of CXCL5 and FOXD1 in HepG2 cells(P＜0.05);but com-pared with the unexpressed group of Cinobufacini,its ability to inhibit cell activity was weakened(P＜0.05),and its ability to inhibit the expression of CX-CL5,FOXD1,and VEGF was weakened(P＜0.05).Conclusion Cinobufacini may inhibit HepG2 cell pro-liferation and invasion and promote HepG2 cell apopto-sis by regulating the CXCL5/FOXD1/VEGF pathway.

Objective To establish the finite element model of spinal canal reconstruction and internal fixation,analysis influence of spinal canal reconstruction and internal fixation on spinal stability,and verify the effectiveness and reliability of spinal canal reconstruction and internal fixation in spinal canal surgery.Methods A 30-year-old male healthy volunteer with a height of 172 cm and weight of 75 kg was selected and his lumbar CT data were collected to establish a finite element model of normal lumbar Lo3-L,and the results were compared with in vitro solid results and published finite element analysis results to verify the validity of the model.They were divided into normal group,laminectomy group and spinal canal reconstruction group according to different treatment methods.Under the same boundary fixation and physiological load conditions,six kinds of ac-tivities were performed,including forward bending,backward extension,left bending,right bending,left rotation and right rota-tion,and the changes of range of motion(ROM)of L3-L4,L4-L5 segments and overall maximum ROM of L3-L5 were analyzed under the six conditions.Results The ROM displacement range of each segment of the constructed L3-L5 finite element model was consistent with the in vitro solid results and previous literature data,which confirms the validity of the model.In L3-L4,ROM of spinal canal reconstruction group was slightly increased than that of normal group during posterior extension(＞5％dif-ference),and ROM of other conditions was similar to that of normal group(＜5％difference).ROM in laminectomy group was significantly increase than that in normal group and spinal canal reconstruction group under the condition of flexion,extension,left and right rotation.In L4-L5,ROM in spinal canal reconstruction group was similar to that in normal group(＜5％differ-ence),while ROM in laminectomy group was significantly higher than that in normal group and spinal canal reconstruction group(＞5％difference).In the overall maximum ROM of L3-L5,spinal canal reconstruction group was only slightly higher than normal group under the condition of posterior extension(＞5％difference),while laminectomy was significantly higher than normal group and spinal canal reconstruction group under the condition of anterior flexion,posterior extension,left and right rotation(＞5％difference).The changes of each segment ROM and overall ROM of L3-L5 showed laminectomy group＞spinal canal reconstruction group＞normal group.Conclusion Laminectomy could seriously affect biomechanical stability of the spine,but application of spinal canal reconstruction and internal fixation could effectively reduce ROM displacement of the responsi-ble segment of spine and maintain its biomechanical stability.