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.

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.

Objective To develop a radiomics nomogram based on contrast-enhanced CT (CECT) for preoperative prediction of high-risk and low-risk thymomas. Methods Clinical data of patients with thymoma who underwent surgical resection and pathological confirmation at Northern Jiangsu People's Hospital from January 2018 to February 2023 were retrospectively analyzed. Feature selection was performed using the Pearson correlation coefficient and least absolute shrinkage and selection operator (LASSO) method. An ExtraTrees classifier was used to construct the radiomics signature model and the radiomics signature. Univariate and multivariable logistic regression was applied to analyze clinical-radiological characteristics and identify variables for developing a clinical model. The radiomics nomogram model was developed by combining the radiomics signature and clinical features. Model performance was evaluated using area under the curve (AUC), sensitivity, specificity, accuracy, negative predictive value, and positive predictive value. Calibration curves and decision curves were plotted to assess model accuracy and clinical values. Results A total of 120 patients including 59 females and 61 males with an average age of 56.30±12.10 years. There were 84 patients in the training group and 36 in the validation group, 62 in the low-risk thymoma group and 58 in the high-risk thymoma group. Radiomics features (1 038 in total) were extracted from the arterial phase of CECT scans, among which 6 radiomics features were used to construct the radiomics signature. The radiomics nomogram model, combining clinical-radiological characteristics and the radiomics signature, achieved an AUC of 0.872 in the training group and 0.833 in the validation group. Decision curve analysis demonstrated better clinical efficacy of the radiomics nomogram than the radiomics signature and clinical model. Conclusion The radiomics nomogram based on CECT showed good diagnostic value in distinguishing high-risk and low-risk thymoma, which may provide a noninvasive and efficient method for clinical decision-making.

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.