Objective To develop and validate a machine learning model based on preoperative clinical characteristics, laboratory indices, and radiological features for the non-invasive prediction of spread through air spaces (STAS) in patients with early-stage lung adenocarcinoma. Methods Preoperative data from patients with early-stage lung adenocarcinoma who underwent surgical resection at Northern Jiangsu People's Hospital between January 2020 and August 2025 were retrospectively collected. The data included clinical characteristics, laboratory indices, and radiological features. Patients were divided into a STAS-positive and a STAS-negative group based on postoperative pathological findings. The dataset was randomly split into a training set and a testing set at a 7 : 3 ratio. Feature variables were selected using the maximum relevance and minimum redundancy (mRMR) algorithm and the least absolute shrinkage and selection operator (LASSO) regression. Five machine learning models were constructed: logistic regression (LR), random forest (RF), support vector machine (SVM), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). The shapley additive explanations (SHAP) method was employed to interpret the optimal prediction model. Results A total of 377 patients were included, comprising 177 (46.9%) males and 200 (53.1%) females, with a mean age of (63.31±9.73) years. There were 261 patients in the training set and 116 patients in the testing set. In the training set, statistically significant differences were observed between the STAS-positive group (n=130) and STAS-negative group (n=131) across multiple features, including age, sex, neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), clinical T stage, and maximum solid component diameter (P<0.05). A final set of 10 feature variables was selected by combining mRMR and LASSO regression, and five machine learning models (LR, RF, SVM, LightGBM, XGBoost) were developed. The XGBoost model demonstrated optimal performance in both the training and testing sets, achieving AUCs of 0.947 [95%CI (0.920, 0.975)] and 0.943 [95%CI (0.894, 0.993)], respectively. DCA indicated that the XGBoost model provided a high net clinical benefit across a wide range of threshold probabilities. SHAP analysis revealed that the vessel convergence sign, clinical T stage, age, consolidation-to-tumor ratio (CTR), and MLR were the features with the highest contributions to STAS prediction. Conclusion The XGBoost model effectively predicts preoperative STAS status in early-stage lung adenocarcinoma, exhibiting excellent discriminative performance and good clinical interpretability. Key predictors such as the vessel convergence sign, clinical T stage, age and CTR provide a crucial reference for preoperative risk assessment and the individualized selection of surgical strategies, ultimately benefiting patients.

ObjectiveTo investigate the effect of trophoblast-derived mesenchymal stem cell （T-MSC） on concanavalin A （Con A）-induced immune-mediated liver injury in mice， as well as its association with the changes in inflammatory response. MethodsMorphological assessment， flow cytometry， and tri-lineage differentiation assay were used to observe the biological characteristics of T-MSC. In the pilot experiment， mice were divided into PBS group， T-MSC monotherapy group， and Con A groups at a concentration of 10， 15， or 20 mg/kg to evaluate the safety of T-MSC monotherapy on liver function and determine the appropriate dose for modeling. In the formal experiment， mice were divided into healthy control group （HC group）， Con A group， and Con A+T-MSC group， with 5 mice in each group. The mice were given injection of Con A （15 mg/kg） via the caudal vein to establish a mouse model of immune-mediated liver injury， while the mice in the T-MSC monotherapy group were given transfusion of 1×10⁶ T-MSCs via the caudal vein at 3 hours after modeling， and samples were collected 12 hours later. The serum levels of alanine aminotransferase （ALT）， aspartate aminotransferase （AST）， and lactate dehydrogenase （LDH） were measured； liver histopathological changes were observed， and Ishak inflammatory activity score and inflammatory necrosis area were assessed； the serum levels of inflammatory cytokines were measured； transcriptome sequencing， immunofluorescence assay， and Western blot were used to measure the changes in inflammation-related molecules in liver tissue. The Shapiro-Wilk test was used to assess the normality of continuous data， and the homogeneity of variance test was also performed； a one-way analysis of variance was used for comparison of normally distributed data with homogeneity of variance between multiple groups， and the Tukey’s post-hoc test was used for further comparison between two groups； the Kruskal-Wallis H test was used for comparison of non-normally distributed data with heterogeneity of variance between multiple groups， and the Wilcoxon test was used for further comparison between two groups. ResultsT-MSC had a long spindle shape， showed the characteristics of fibroblast-like morphology and adherent growth， and possessed the osteogenic， chondrogenic， and adipogenic differentiation abilities. Flow cytometry showed high expression levels of CD90， CD105， and CD73 in T-MSC， with a positive rate of 96.8%， 99.0%， and 99.9%， respectively， while there was low or no expression of CD31， human leukocyte antigen DR， CD45， and CD34， with a positive rate of 0.120%， 0， 0.061%， and 0， respectively. Administration of T-MSC alone did not cause obvious abnormalities in ALT， AST， or LDH. Con A at the concentrations of 10， 15， and 20 mg/kg all increased the serum levels of biochemical parameters for liver injury in a dose-dependent manner， with mortality observed in the 20 mg/kg group. In the formal experiment， compared with the HC group， the Con A group had significant increases in the serum levels of ALT， AST， and LDH （P<0.01）， and after T-MSC treatment， there were significant reductions in these markers compared with the Con A group （P<0.01）. HE staining showed that the Con A group had disordered structure of the liver， accompanied by marked inflammatory cell infiltration and focal/patchy necrosis， and these pathological changes were alleviated after T-MSC treatment. Compared with the HC group， the Con A group had significant increases in Ishak score and the percentage of inflammatory necrosis area （P<0.001）， while there were significant reductions in these indicators after T-MSC treatment compared with the Con A group （P<0.01）. ELISA showed that compared with the HC group， the Con A group had significant increases in the serum levels of interleukin-21 （IL-21）， interleukin-1β （IL-1β）， interleukin-2 （IL-2）， interleukin-17A （IL-17A）， and tumor necrosis factor-α （TNF-α） （P<0.05）， and there were significant reductions in these markers after T-MSC treatment compared with the Con A group （P<0.05）， with no significant differences in IL-21， IL-1β， IL-17A， and TNF-α compared with the HC group （P>0.05）； although there was a significant reduction in the level of IL-2， the Con A+T-MSC group still had a significantly higher level of IL-2 than the HC group （P=0.001）. In contrast， compared with the HC group， the Con A group had a significant increase in IL-10 （P<0.05）， with a further increase after T-MSC treatment （P<0.05）. The transcriptome analysis showed that T-MSC treatment downregulated the expression of the inflammation- and chemokine-related genes including Ccl2， Cxcl10， Il-21， and Il-6 and inhibited the inflammation-related pathways such as TNF， IL-17， nuclear factor-κB， and JAK-STAT. Immunofluorescence assay showed that compared with the HC group， the Con A group had a significant increase in the expression of IL-21 in the liver （P<0.001）， and there was a significant reduction in IL-21 after T-MSC treatment compared with the Con A group （P<0.001）； the results of Western blot showed the same trend. ConclusionT-MSC can alleviate Con A-induced immune-mediated liver injury in mice， as evidenced by the improvement in liver biochemical parameters， the alleviation of histopathological damage， and the overall downregulation of inflammation-related molecules. T-MSC exerts marked anti-inflammatory and immunomodulatory effects in this model， and IL-21 shows a significant change in inflammatory response and can be used as a candidate molecule for further investigation.

Objective:To explore the high-risk factors affecting the severity of neonatal necrotizing enterocolitis (NEC).Methods:This study involved 153 NEC patients admitted to the Neonatology Department of the Children's Hospital of Soochow University from January 1, 2017, to December 30, 2023. Based on the severity of NEC determined by Bell's criteria, these patients were divided into two groups: mild group (Bell stage Ⅱ, n=70) and severe group (Bell stage Ⅲ, n=83). Clinical data including general conditions, clinical treatment and disease status before the onset of NEC, laboratory test results, and perinatal conditions of the mothers were retrospectively collected. Univariate analysis (rank-sum test and Chi-square test) and multivariate analysis (logistic regression analysis) were used to explore the risk factors affecting the severity of NEC. Results:The proportion of infants with gestational age<37 weeks or birth weight<1 500 g, the rate of antibiotic usage, sepsis or shock were higher in the severe group than in the mild group [91.6% (76/83) vs. 75.7% (53/70); 55.4% (46/83) vs. 34.3% (24/70); 85.5% (71/83) vs. 71.4% (50/70); 55.4% (46/83) vs. 17.1% (12/70); 30.1% (25/83) vs. 8.6% (6/70); with χ 2 values of 7.22, 6.84, 4.57, 23.64, and 10.91, respectively, all P<0.05]. Furthermore, the severe group had a late initiation of breastfeeding and longer durations of peripherally inserted central catheter (PICC) placement and parenteral nutrition [2.00 d (1.00-2.00 d) vs. 1.00 d (1.00-2.00 d); 0.00 d (0.00-18.00 d) vs. 0.00 d (0.00-7.50 d); 14.00 d (5.00-21.00 d) vs. 10.50 d (0.00-18.25 d), with Z values of -2.90, -1.98, and -2.09, respectively, all P<0.05]. (2) Within 48 h before the onset, the severe group had higher proportions of infants with decreased white blood cell count, decreased platelet count, electrolyte imbalance, and metabolic acidosis than the mild group [53.0% (44/83) vs. 14.3% (10/70); 49.4% (41/83) vs. 10.0% (7/70); 38.6% (32/83) vs. 14.3% (10/70); 37.3% (31/83) vs. 14.3% (10/70), with χ2 values of 24.94, 27.38, 11.23, and 10.30, respectively, all P<0.05]. Besides, the levels of procalcitonin and C-reactive protein were higher in the severe group than in the mild group [2.31 ng/ml (0.26-11.71 ng/ml) vs. 0.22 ng/ml (0.00-2.19 ng/ml); 58.50 mg/L (14.34-125.25 mg/L) vs. 8.20 mg/L (0.23-34.56 mg/L), with Z values of -3.88 and -5.02, respectively, both P<0.05]. (3) Multivariate logistic regression analysis showed that prolonged duration of PICC placement, decreased platelet count, electrolyte imbalance, metabolic acidosis, and concurrent sepsis were independent risk factors affecting the severity of NEC [ OR (95% CI) values were 1.104 (1.020-1.196), 5.364 (1.667-17.253), 4.047 (1.171-13.986), 4.333 (1.290-14.556), and 3.290 (1.005-10.774), respectively, with all P<0.05]. Conclusions:Prolonged duration of PICC placement, concurrent sepsis, decreased platelet count, electrolyte imbalance, and metabolic acidosis in NEC patients are more likely to lead to severe cases. In clinical practice, attention should be paid to relevant indicators, and abnormal changes should be identified and intervened in a timely manner to reduce the occurrence of severe NEC.

Objective:To explore the high-risk factors affecting the severity of neonatal necrotizing enterocolitis (NEC).Methods:This study involved 153 NEC patients admitted to the Neonatology Department of the Children's Hospital of Soochow University from January 1, 2017, to December 30, 2023. Based on the severity of NEC determined by Bell's criteria, these patients were divided into two groups: mild group (Bell stage Ⅱ, n=70) and severe group (Bell stage Ⅲ, n=83). Clinical data including general conditions, clinical treatment and disease status before the onset of NEC, laboratory test results, and perinatal conditions of the mothers were retrospectively collected. Univariate analysis (rank-sum test and Chi-square test) and multivariate analysis (logistic regression analysis) were used to explore the risk factors affecting the severity of NEC. Results:The proportion of infants with gestational age<37 weeks or birth weight<1 500 g, the rate of antibiotic usage, sepsis or shock were higher in the severe group than in the mild group [91.6% (76/83) vs. 75.7% (53/70); 55.4% (46/83) vs. 34.3% (24/70); 85.5% (71/83) vs. 71.4% (50/70); 55.4% (46/83) vs. 17.1% (12/70); 30.1% (25/83) vs. 8.6% (6/70); with χ 2 values of 7.22, 6.84, 4.57, 23.64, and 10.91, respectively, all P<0.05]. Furthermore, the severe group had a late initiation of breastfeeding and longer durations of peripherally inserted central catheter (PICC) placement and parenteral nutrition [2.00 d (1.00-2.00 d) vs. 1.00 d (1.00-2.00 d); 0.00 d (0.00-18.00 d) vs. 0.00 d (0.00-7.50 d); 14.00 d (5.00-21.00 d) vs. 10.50 d (0.00-18.25 d), with Z values of -2.90, -1.98, and -2.09, respectively, all P<0.05]. (2) Within 48 h before the onset, the severe group had higher proportions of infants with decreased white blood cell count, decreased platelet count, electrolyte imbalance, and metabolic acidosis than the mild group [53.0% (44/83) vs. 14.3% (10/70); 49.4% (41/83) vs. 10.0% (7/70); 38.6% (32/83) vs. 14.3% (10/70); 37.3% (31/83) vs. 14.3% (10/70), with χ2 values of 24.94, 27.38, 11.23, and 10.30, respectively, all P<0.05]. Besides, the levels of procalcitonin and C-reactive protein were higher in the severe group than in the mild group [2.31 ng/ml (0.26-11.71 ng/ml) vs. 0.22 ng/ml (0.00-2.19 ng/ml); 58.50 mg/L (14.34-125.25 mg/L) vs. 8.20 mg/L (0.23-34.56 mg/L), with Z values of -3.88 and -5.02, respectively, both P<0.05]. (3) Multivariate logistic regression analysis showed that prolonged duration of PICC placement, decreased platelet count, electrolyte imbalance, metabolic acidosis, and concurrent sepsis were independent risk factors affecting the severity of NEC [ OR (95% CI) values were 1.104 (1.020-1.196), 5.364 (1.667-17.253), 4.047 (1.171-13.986), 4.333 (1.290-14.556), and 3.290 (1.005-10.774), respectively, with all P<0.05]. Conclusions:Prolonged duration of PICC placement, concurrent sepsis, decreased platelet count, electrolyte imbalance, and metabolic acidosis in NEC patients are more likely to lead to severe cases. In clinical practice, attention should be paid to relevant indicators, and abnormal changes should be identified and intervened in a timely manner to reduce the occurrence of severe NEC.

Malignant tumors represent a significant health challenge, critically impacting human well-being. Malignant tumors have become one of the leading causes of death worldwide. According to statistics from the World Health Organization, nearly one-sixth of global deaths in 2020 were caused by malignant tumors. The burden of malignant tumors in our country is also increasing. In recent years, with population aging and changes in lifestyle, the incidence and mortality rates of malignant tumors in China have been steadily rising, malignant tumors have gradually become one of the main causes of death in China. Developing effective diagnostic and treatment methods is of great significance in reducing the burden of malignant tumors in our country. Historically, the focus has been on leveraging the biochemical cues of tumors for both diagnosis and treatment. While valuable, this strategy does not recapitulate the full complexity of tumor diagnosis and management. Recently, the integration of biomechanics and mechanobiology with oncology has highlighted the importance of mechanical cues, which have emerged as new hallmarks of tumors, regulating tumor initiation and development are expected to open potential novel routes for cancer diagnosis and therapeutic interventions. Despite the advances, a thorough literature review suggests a pronounced gap in our understanding of the mechanical properties of tumors. The clinical community has not yet completely recognized the diagnostic and therapeutic relevance of the mechanical cues of tumors. To bridge this knowledge gap, we propose and introduce the paradigm of "Tumor Mechanomedicine". We provide a comprehensive overview of the multi-scale mechanical characteristics of tumors, exploring their influence on tumor biology, from the aspects of tumor biomechanics, tumor mechanobiology, tumor mechanodiagnostics, and tumor mechanotherapeutics. By elucidating the diagnostic and therapeutic potential of these mechanical cues, we aim to furnish the oncology community with fresh insights, paving the way for innovative solutions to persistent clinical conundrums.

Malignant tumors represent a significant health challenge, critically impacting human well-being. Malignant tumors have become one of the leading causes of death worldwide. According to statistics from the World Health Organization, nearly one-sixth of global deaths in 2020 were caused by malignant tumors. The burden of malignant tumors in our country is also increasing. In recent years, with population aging and changes in lifestyle, the incidence and mortality rates of malignant tumors in China have been steadily rising, malignant tumors have gradually become one of the main causes of death in China. Developing effective diagnostic and treatment methods is of great significance in reducing the burden of malignant tumors in our country. Historically, the focus has been on leveraging the biochemical cues of tumors for both diagnosis and treatment. While valuable, this strategy does not recapitulate the full complexity of tumor diagnosis and management. Recently, the integration of biomechanics and mechanobiology with oncology has highlighted the importance of mechanical cues, which have emerged as new hallmarks of tumors, regulating tumor initiation and development are expected to open potential novel routes for cancer diagnosis and therapeutic interventions. Despite the advances, a thorough literature review suggests a pronounced gap in our understanding of the mechanical properties of tumors. The clinical community has not yet completely recognized the diagnostic and therapeutic relevance of the mechanical cues of tumors. To bridge this knowledge gap, we propose and introduce the paradigm of "Tumor Mechanomedicine". We provide a comprehensive overview of the multi-scale mechanical characteristics of tumors, exploring their influence on tumor biology, from the aspects of tumor biomechanics, tumor mechanobiology, tumor mechanodiagnostics, and tumor mechanotherapeutics. By elucidating the diagnostic and therapeutic potential of these mechanical cues, we aim to furnish the oncology community with fresh insights, paving the way for innovative solutions to persistent clinical conundrums.

Malignant tumors represent a significant health challenge, critically impacting human well-being. Malignant tumors have become one of the leading causes of death worldwide. According to statistics from the World Health Organization, nearly one-sixth of global deaths in 2020 were caused by malignant tumors. The burden of malignant tumors in our country is also increasing. In recent years, with population aging and changes in lifestyle, the incidence and mortality rates of malignant tumors in China have been steadily rising, malignant tumors have gradually become one of the main causes of death in China. Developing effective diagnostic and treatment methods is of great significance in reducing the burden of malignant tumors in our country. Historically, the focus has been on leveraging the biochemical cues of tumors for both diagnosis and treatment. While valuable, this strategy does not recapitulate the full complexity of tumor diagnosis and management. Recently, the integration of biomechanics and mechanobiology with oncology has highlighted the importance of mechanical cues, which have emerged as new hallmarks of tumors, regulating tumor initiation and development are expected to open potential novel routes for cancer diagnosis and therapeutic interventions. Despite the advances, a thorough literature review suggests a pronounced gap in our understanding of the mechanical properties of tumors. The clinical community has not yet completely recognized the diagnostic and therapeutic relevance of the mechanical cues of tumors. To bridge this knowledge gap, we propose and introduce the paradigm of "Tumor Mechanomedicine". We provide a comprehensive overview of the multi-scale mechanical characteristics of tumors, exploring their influence on tumor biology, from the aspects of tumor biomechanics, tumor mechanobiology, tumor mechanodiagnostics, and tumor mechanotherapeutics. By elucidating the diagnostic and therapeutic potential of these mechanical cues, we aim to furnish the oncology community with fresh insights, paving the way for innovative solutions to persistent clinical conundrums.

Malignant tumors represent a significant health challenge, critically impacting human well-being. Malignant tumors have become one of the leading causes of death worldwide. According to statistics from the World Health Organization, nearly one-sixth of global deaths in 2020 were caused by malignant tumors. The burden of malignant tumors in our country is also increasing. In recent years, with population aging and changes in lifestyle, the incidence and mortality rates of malignant tumors in China have been steadily rising, malignant tumors have gradually become one of the main causes of death in China. Developing effective diagnostic and treatment methods is of great significance in reducing the burden of malignant tumors in our country. Historically, the focus has been on leveraging the biochemical cues of tumors for both diagnosis and treatment. While valuable, this strategy does not recapitulate the full complexity of tumor diagnosis and management. Recently, the integration of biomechanics and mechanobiology with oncology has highlighted the importance of mechanical cues, which have emerged as new hallmarks of tumors, regulating tumor initiation and development are expected to open potential novel routes for cancer diagnosis and therapeutic interventions. Despite the advances, a thorough literature review suggests a pronounced gap in our understanding of the mechanical properties of tumors. The clinical community has not yet completely recognized the diagnostic and therapeutic relevance of the mechanical cues of tumors. To bridge this knowledge gap, we propose and introduce the paradigm of "Tumor Mechanomedicine". We provide a comprehensive overview of the multi-scale mechanical characteristics of tumors, exploring their influence on tumor biology, from the aspects of tumor biomechanics, tumor mechanobiology, tumor mechanodiagnostics, and tumor mechanotherapeutics. By elucidating the diagnostic and therapeutic potential of these mechanical cues, we aim to furnish the oncology community with fresh insights, paving the way for innovative solutions to persistent clinical conundrums.

Malignant tumors represent a significant health challenge, critically impacting human well-being. Malignant tumors have become one of the leading causes of death worldwide. According to statistics from the World Health Organization, nearly one-sixth of global deaths in 2020 were caused by malignant tumors. The burden of malignant tumors in our country is also increasing. In recent years, with population aging and changes in lifestyle, the incidence and mortality rates of malignant tumors in China have been steadily rising, malignant tumors have gradually become one of the main causes of death in China. Developing effective diagnostic and treatment methods is of great significance in reducing the burden of malignant tumors in our country. Historically, the focus has been on leveraging the biochemical cues of tumors for both diagnosis and treatment. While valuable, this strategy does not recapitulate the full complexity of tumor diagnosis and management. Recently, the integration of biomechanics and mechanobiology with oncology has highlighted the importance of mechanical cues, which have emerged as new hallmarks of tumors, regulating tumor initiation and development are expected to open potential novel routes for cancer diagnosis and therapeutic interventions. Despite the advances, a thorough literature review suggests a pronounced gap in our understanding of the mechanical properties of tumors. The clinical community has not yet completely recognized the diagnostic and therapeutic relevance of the mechanical cues of tumors. To bridge this knowledge gap, we propose and introduce the paradigm of "Tumor Mechanomedicine". We provide a comprehensive overview of the multi-scale mechanical characteristics of tumors, exploring their influence on tumor biology, from the aspects of tumor biomechanics, tumor mechanobiology, tumor mechanodiagnostics, and tumor mechanotherapeutics. By elucidating the diagnostic and therapeutic potential of these mechanical cues, we aim to furnish the oncology community with fresh insights, paving the way for innovative solutions to persistent clinical conundrums.