OBJECTIVES: Non-small cell lung cancer (NSCLC) is associated with poor prognosis, with 30% of patients diagnosed at an advanced stage. Mutations in the EGFR and KRAS genes are important prognostic factors for NSCLC, and targeted therapies can significantly improve survival in these patients. Although tissue biopsy remains the gold standard for detecting gene mutations, it has limitations, including invasiveness, sampling errors due to tumor heterogeneity, and poor reproducibility. This study aims to develop machine learning models based on radiomic features to predict EGFR and KRAS gene mutation status in NSCLC patients, thereby providing a reference for precision oncology. METHODS: Imaging and mutation data from eligible NSCLC patients were obtained from the publicly available Lung-PET-CT-Dx dataset in The Cancer Imaging Archive (TCIA). A three-dimensional-convolutional neural network (3D-CNN) was used to extract imaging features from the regions of interest (ROI). The LightGBM algorithm was employed to build classification models for predicting EGFR and KRAS gene mutation status. Model performance was evaluated using 5-fold cross-validation, with receiver operator characteristic (ROC) curves, area under the curve (AUC), accuracy, sensitivity, and specificity used for validation. RESULTS: The models effectively predicted EGFR and KRAS mutations in NSCLC patients, achieving an AUC of 0.95 for EGFR mutations and 0.90 for KRAS. The models also demonstrated high accuracy (EGFR 89.66%; KRAS 87.10%), sensitivity (EGFR 93.33%; KRAS 87.50%), and specificity (EGFR 85.71%; KRAS 86.67%). CONCLUSIONS A radiogenomics-machine learning predictive model can serve as a non-invasive tool for anticipating EGFR and KRAS gene mutation status in NSCLC patients.
Humans ; Carcinoma, Non-Small-Cell Lung/diagnostic imaging* ; Lung Neoplasms/diagnostic imaging* ; Mutation ; Proto-Oncogene Proteins p21(ras)/genetics* ; ErbB Receptors/genetics* ; Machine Learning ; Positron Emission Tomography Computed Tomography ; Female ; Male ; Neural Networks, Computer ; Middle Aged ; Aged

Objective To investigate the inhibitory effect of Scutellaria baicalensis combined with 5-Fu on Lewis tumor bearing mouse lung cancer based on the JAK2/STAT3 signaling pathway.Methods To detect the changes in body mass,food intake and tumor volume of Lewis tumor-bearing mice after intervention of Scutellaria baicalensis(20 mg/kg)combined with 5-Fu.Pathological changes in tumor tissue were observed by HE staining,expression levels of proliferation related protein Ki67 were observed by immunohistochemical staining,changes in cell apoptosis levels in tumor tissue were observed by TUNEL staining,and changes in expression levels of JAK2,p-JAK2,STAT3,and p-STAT3 proteins in tumor tissue were observed by immunohistochemical staining.Results Compared with the model group,the tumor volume of mice after combined intervention significantly decreased(P＜0.01)and body mass increased(P＜0.05),but there was no significant change food intake.The expression of proliferation related protein Ki67 in tumor tissue was significantly reduced,and the number of apoptotic cells labeled with TUNEL was significantly increased;The expression of p-JAK2 and p-STAT3 proteins is elevated.Conclusions Scutellaria baicalensis decoction can inhibit the JAK2/STAT3 signaling pathway and increase the inhibitory effect of 5-Fu on mouse lung cancer.

Objective:To dry fresh Ginseng Radix et Rhizoma using different drying conditions; To investigate the effects of different drying conditions on the drying characteristics and medicinal quality of Ginseng Radix et Rhizoma.Methods:With moisture, powder color, extract, total polysaccharide and ginsenoside contents of Rg 1, Re, Rf, Rb 1, Rc, Rb 2 and Rd as indexes, the drying characteristics of Ginseng Radix et Rhizoma were studied based on Weibull function model, and the quality of Ginseng Radix et Rhizoma after drying was evaluated by entropy weight-TOPSIS model. Results:The drying method for Ginseng Radix et Rhizoma from its origin can be achieved by controlling the relative humidity of the drying medium to 50%, drying at 70 ℃ for 24 h, and then reducing the drying temperature to 60 ℃ until the moisture content was below 12.0%. This method could achieve high drying efficiency and produce high-quality Ginseng Radix et Rhizoma.Conclusions:The drying process of Ginseng Radix et Rhizoma is a falling rate process controlled by internal moisture diffusion. The drying rate of fresh Ginseng Radix et Rhizoma is affected by temperature and humidity. There is a certain correlation between the color of powder and the content of moisture, alcohol-soluble extractives and ginsenosides.

Objective:This study aims to develop a laboratory-based predictive model for early neurological deterioration (END) in patients with acute cerebral infarction (ACI) using baseline data collected at hospital admission.Methods:This study was a retrospective cohort study. Clinical and baseline laboratory test data from 502 patients with ACI admitted to the Department of Neurology at our hospital between January 1, 2022 and May 31, 2025. Of these patients, 313 were male and 189 were female, with a median age of 67 years (interquartile range: 58-73). Patients were classified into an END group and a non-END group according to the occurrence of END within 7 days of admission. Subsequently, using the caret package in R (version 4.4.2), the dataset was randomly divided into a training set ( n=351) and a validation set ( n=151) at a 7∶3 ratio, with END status as the stratification variable and a fixed random seed to ensure reproducibility. Following baseline characteristic comparisons between groups, these datasets were used for model development and validation, respectively. The differences in clinical indicators between the two patients groups were assessed using the chi-square test and the Wilcoxon rank sum test. In the training group, Lasso regression was utilized to identify variables significantly associated with END. Seven machine learning algorithms-decision tree (DT), random forest (RF), light gradient boosting machine (LGBM), extreme gradient boosting (XGB), K-nearest neighbors (KNN), support vector machine (SVM), and logistic regression (LR)-were employed to develop predictive models. The optimal hyperparameters were determined via grid search integrated with 5-fold cross-validation. The final algorithm was selected based on comprehensive model performance evaluation. Additionally, clinical data of 79 patients with ACI, collected between June 1 to August 31, 2025, were compiled as an independent test set for external validation. The cohort comprised 49 males and 30 females, with a median age of 68 years (interquartile range: 57-72). The SHapley Additive exPlanations (SHAP) method was employed to access feature importance and model interpretability. SHAP dependence plots and interaction plots were utilized to emplore the nonlinear relationships and interaction effects among the featurevariables. Results:Among the 502 patients, 166 experienced END during 7 days of hospitalization. Lasso regression identified nine significant predictors: history of hyperlipidemia, admission NIHSS score, lymphocyte-to-monocyte ratio (LMR), hemoglobin, D-dimer, albumin, neuron-specific enolase (NSE), homocysteine (HCY), and vitamin B12. The area under the receiver operating characteristic curve (AUC) for the seven machine learning models ranged from 0.709 to 0.946. The XGB model achieved the highest predictive performance, with an AUC of 0.946 (95% CI 0.924-0.960) in the training cohort and 0.867 (95% CI 0.902-0.933) in the validation cohort. SHAP analysis revealed that the top five variables contributing to END prediction were admission NIHSS score, HCY, D-dimer, history of hyperlipidemia, and vitamin B12. Conclusion:This study successfully developed a laboratory-based prediction model for END using the XGB machine learning algorithm, which demonstrated strong predictive performance.

Objective:To assess the preliminary efficacy and safety of modified Société Internationale d′Oncologie Pédiatrique Epithelial Liver Tumor Study Group (SIOPEL)-4 protocol for pediatric hepatoblastoma (HB) with lung metastases.Methods:This prospective cohort study enrolled 27 newly diagnosed pediatric HB with lung metastases who received the modified SIOPEL-4 protocol at Shanghai Children′s Medical Center, Shanghai Jiao Tong University School of Medicine, and Shanghai Children′s Hospital between January 2020 to December 2023. Clinical characteristics, lung response rates to induction chemotherapy, treatment outcomes, prognostic factors and sever chemotherapy toxicities at different stages were analyzed. Survival analysis was performed by Kaplan-Meier method. Univariate prognostic analysis was conducted by Log-Rank test.Results:Of the 27 patients, there were 17 males and 10 females, with the age of 21 (15, 33) months. During the follow-up of 31 (12, 45) months for 17 continuous complete remission patients, 4 cases disease progression (2 cases death) and 6 cases relapse were observed. The 2-year event free survival (EFS) and overall survival (OS) rate was (58±11)% and (89±7)%, respectively. All the 27 patients had response to block 1-3 induction chemotherapy (cisplatin+doxorubicin), with 14 cases (52%) achieving complete response and 13 cases (48%) achieving partial response of lung metastatic lesions, the 2-year EFS rate was (81±12)% and (34±14)%, respectively ( χ 2=6.76, P=0.009), the 2-year OS rate was 100% and (79±13)%, respectively ( χ2=2.12, P=0.145). Patients with caudate lobe tumors or ≥10 pulmonary metastatic nodules had significantly lower EFS rates ( χ2=5.36, 7.84, P=0.021, 0.005, respectively). The incidence of grade 3/4 neutropenia after block 1-3 induction chemotherapy, CD (carboplatin+doxorubicin), and VI (vincristine+irinotecan) consolidation chemotherapy was 90% (73/81), 75% (58/77), and 31% (11/35), respectively. The incidence of grade 3/4 thrombocytopenia was 77% (62/81), 69% (53/77), and 14% (5/35), respectively. The incidence of grade 3/4 infections was 64% (52/81), 25% (19/77), and 20% (7/35), respectively. The differences between the groups were statistically significant ( χ2=43.51, 42.69, 33.00, all P<0.001). Two patients (10%) of the 20 evaluable patients for ototoxicity occurred grade 3 and higher hearing impairment, with 1 patient requiring a hearing aid. Conclusions:The modified SIOPEL-4 regimen shows good preliminary efficacy and safety in treating pediatric HB with lung metastases. The prognosis for patients with residual lesions in the lungs after induction chemotherapy needs to be improved. Attention should be given to the ototoxicity induced by high-dose cisplatin chemotherapy.

Objective:To investigate the effects of anisodamine hydrobromide (654-1), 654-1+ norepinephrine and norepinephrine on early hemodynamic indexes of piglets with septic shock.Methods:A total of 38 healthy Bama pigs were selected as the study subjects, 32 of which were treated with lipopolysaccharide to create septic shock piglet model, and the other 6 were sham operation group. The animals were randomly divided into control group ( n=8), drug treatment group [654-1 group ( n=8), 654-1+ norepinephrine group ( n=8), norepinephrine group ( n=8)]. Hemodynamic parameters were recorded at T 0 (basic state), T 1 (successful shock modeling), T 2 (1 h after successful modeling), T 3 (2 h after successful modeling), T 4 (4 h after successful modeling), T 5 (6 h after successful modeling) and T 6 (8 h after successful modeling) respectively, including: Mean arterial pressure (MAP), cardiac index (CI), whole-heart end-diastolic volume index (GEDI), lactic acid (LAC). Results:Except for the sham operation group, MAP of all treatment groups at T 1 was significantly lower than that at T 0 (all P<0.05). MAP of all treatment groups at T 2-T 6 was significantly higher than that at T 1 (all P<0.05). T 1 MAP of all treatment groups was significantly lower than that of the sham operation group (all P<0.05). MAP at T 2-T 6 in the norepinephrine group and the 654-1+ norepinephrine group was higher than that in the control group (all P<0.05), and MAP at T 2-T 4 in the 654-1 group was significantly lower than that in the 654-1+ norepinephrine group (all P<0.05). LAC of all treatment groups at T 1-T 3 was significantly higher than that at T 0 (all P<0.05) except the sham operation group. LAC in the group 654-1 at T 4 to T 6 was significantly lower than that at T 1 (all P<0.05). LAC in the group 654-1 at T 4-T 6 was significantly lower than that in the norepinephrine group and the control group (all P<0.05). The CI of norepinephrine group at T 2, T 5 and T 6 was lower than that at T 0 (all P<0.05). There was no significant difference in CI between T 2 and T 6 compared with T 1 (all P>0.05). CI of the 654-1+ norepinephrine group at T 4 was significantly lower than that of T 0 ( P<0.05); The CI of the 654-1 group at T 2 was significantly higher than that of T 1 ( P<0.05). CI at T 1 in the 654-1+ norepinephrine group was significantly lower than that in the sham operation group (all P<0.05). The GEDI at T 1 to T 5 in the 654-1 group was significantly lower than that at T 0 in the 6541+ norepinephrine group (all P<0.05), and the GEDI at T 1 to T 2 was significantly lower than that at T 0 in the 6541+ norepinephrine group (all P<0.05), while the GEDI at T 2 and T 4 was higher than that at T 1 (all P<0.05). Conclusions:MAP decreased significantly in septic shock, LAC increased significantly in the early stage of shock. 654-1 can improve MAP in early stage of septic shock, and significantly reduce LAC level in early stage of septic shock.

Objective To investigate the inhibitory effect of Scutellaria baicalensis combined with 5-Fu on Lewis tumor bearing mouse lung cancer based on the JAK2/STAT3 signaling pathway.Methods To detect the changes in body mass,food intake and tumor volume of Lewis tumor-bearing mice after intervention of Scutellaria baicalensis(20 mg/kg)combined with 5-Fu.Pathological changes in tumor tissue were observed by HE staining,expression levels of proliferation related protein Ki67 were observed by immunohistochemical staining,changes in cell apoptosis levels in tumor tissue were observed by TUNEL staining,and changes in expression levels of JAK2,p-JAK2,STAT3,and p-STAT3 proteins in tumor tissue were observed by immunohistochemical staining.Results Compared with the model group,the tumor volume of mice after combined intervention significantly decreased(P＜0.01)and body mass increased(P＜0.05),but there was no significant change food intake.The expression of proliferation related protein Ki67 in tumor tissue was significantly reduced,and the number of apoptotic cells labeled with TUNEL was significantly increased;The expression of p-JAK2 and p-STAT3 proteins is elevated.Conclusions Scutellaria baicalensis decoction can inhibit the JAK2/STAT3 signaling pathway and increase the inhibitory effect of 5-Fu on mouse lung cancer.

Objective:To investigate the effects of anisodamine hydrobromide (654-1), 654-1+ norepinephrine and norepinephrine on early hemodynamic indexes of piglets with septic shock.Methods:A total of 38 healthy Bama pigs were selected as the study subjects, 32 of which were treated with lipopolysaccharide to create septic shock piglet model, and the other 6 were sham operation group. The animals were randomly divided into control group ( n=8), drug treatment group [654-1 group ( n=8), 654-1+ norepinephrine group ( n=8), norepinephrine group ( n=8)]. Hemodynamic parameters were recorded at T 0 (basic state), T 1 (successful shock modeling), T 2 (1 h after successful modeling), T 3 (2 h after successful modeling), T 4 (4 h after successful modeling), T 5 (6 h after successful modeling) and T 6 (8 h after successful modeling) respectively, including: Mean arterial pressure (MAP), cardiac index (CI), whole-heart end-diastolic volume index (GEDI), lactic acid (LAC). Results:Except for the sham operation group, MAP of all treatment groups at T 1 was significantly lower than that at T 0 (all P<0.05). MAP of all treatment groups at T 2-T 6 was significantly higher than that at T 1 (all P<0.05). T 1 MAP of all treatment groups was significantly lower than that of the sham operation group (all P<0.05). MAP at T 2-T 6 in the norepinephrine group and the 654-1+ norepinephrine group was higher than that in the control group (all P<0.05), and MAP at T 2-T 4 in the 654-1 group was significantly lower than that in the 654-1+ norepinephrine group (all P<0.05). LAC of all treatment groups at T 1-T 3 was significantly higher than that at T 0 (all P<0.05) except the sham operation group. LAC in the group 654-1 at T 4 to T 6 was significantly lower than that at T 1 (all P<0.05). LAC in the group 654-1 at T 4-T 6 was significantly lower than that in the norepinephrine group and the control group (all P<0.05). The CI of norepinephrine group at T 2, T 5 and T 6 was lower than that at T 0 (all P<0.05). There was no significant difference in CI between T 2 and T 6 compared with T 1 (all P>0.05). CI of the 654-1+ norepinephrine group at T 4 was significantly lower than that of T 0 ( P<0.05); The CI of the 654-1 group at T 2 was significantly higher than that of T 1 ( P<0.05). CI at T 1 in the 654-1+ norepinephrine group was significantly lower than that in the sham operation group (all P<0.05). The GEDI at T 1 to T 5 in the 654-1 group was significantly lower than that at T 0 in the 6541+ norepinephrine group (all P<0.05), and the GEDI at T 1 to T 2 was significantly lower than that at T 0 in the 6541+ norepinephrine group (all P<0.05), while the GEDI at T 2 and T 4 was higher than that at T 1 (all P<0.05). Conclusions:MAP decreased significantly in septic shock, LAC increased significantly in the early stage of shock. 654-1 can improve MAP in early stage of septic shock, and significantly reduce LAC level in early stage of septic shock.

Objective:To assess the preliminary efficacy and safety of modified Société Internationale d′Oncologie Pédiatrique Epithelial Liver Tumor Study Group (SIOPEL)-4 protocol for pediatric hepatoblastoma (HB) with lung metastases.Methods:This prospective cohort study enrolled 27 newly diagnosed pediatric HB with lung metastases who received the modified SIOPEL-4 protocol at Shanghai Children′s Medical Center, Shanghai Jiao Tong University School of Medicine, and Shanghai Children′s Hospital between January 2020 to December 2023. Clinical characteristics, lung response rates to induction chemotherapy, treatment outcomes, prognostic factors and sever chemotherapy toxicities at different stages were analyzed. Survival analysis was performed by Kaplan-Meier method. Univariate prognostic analysis was conducted by Log-Rank test.Results:Of the 27 patients, there were 17 males and 10 females, with the age of 21 (15, 33) months. During the follow-up of 31 (12, 45) months for 17 continuous complete remission patients, 4 cases disease progression (2 cases death) and 6 cases relapse were observed. The 2-year event free survival (EFS) and overall survival (OS) rate was (58±11)% and (89±7)%, respectively. All the 27 patients had response to block 1-3 induction chemotherapy (cisplatin+doxorubicin), with 14 cases (52%) achieving complete response and 13 cases (48%) achieving partial response of lung metastatic lesions, the 2-year EFS rate was (81±12)% and (34±14)%, respectively ( χ 2=6.76, P=0.009), the 2-year OS rate was 100% and (79±13)%, respectively ( χ2=2.12, P=0.145). Patients with caudate lobe tumors or ≥10 pulmonary metastatic nodules had significantly lower EFS rates ( χ2=5.36, 7.84, P=0.021, 0.005, respectively). The incidence of grade 3/4 neutropenia after block 1-3 induction chemotherapy, CD (carboplatin+doxorubicin), and VI (vincristine+irinotecan) consolidation chemotherapy was 90% (73/81), 75% (58/77), and 31% (11/35), respectively. The incidence of grade 3/4 thrombocytopenia was 77% (62/81), 69% (53/77), and 14% (5/35), respectively. The incidence of grade 3/4 infections was 64% (52/81), 25% (19/77), and 20% (7/35), respectively. The differences between the groups were statistically significant ( χ2=43.51, 42.69, 33.00, all P<0.001). Two patients (10%) of the 20 evaluable patients for ototoxicity occurred grade 3 and higher hearing impairment, with 1 patient requiring a hearing aid. Conclusions:The modified SIOPEL-4 regimen shows good preliminary efficacy and safety in treating pediatric HB with lung metastases. The prognosis for patients with residual lesions in the lungs after induction chemotherapy needs to be improved. Attention should be given to the ototoxicity induced by high-dose cisplatin chemotherapy.

Objective:This study aims to develop a laboratory-based predictive model for early neurological deterioration (END) in patients with acute cerebral infarction (ACI) using baseline data collected at hospital admission.Methods:This study was a retrospective cohort study. Clinical and baseline laboratory test data from 502 patients with ACI admitted to the Department of Neurology at our hospital between January 1, 2022 and May 31, 2025. Of these patients, 313 were male and 189 were female, with a median age of 67 years (interquartile range: 58-73). Patients were classified into an END group and a non-END group according to the occurrence of END within 7 days of admission. Subsequently, using the caret package in R (version 4.4.2), the dataset was randomly divided into a training set ( n=351) and a validation set ( n=151) at a 7∶3 ratio, with END status as the stratification variable and a fixed random seed to ensure reproducibility. Following baseline characteristic comparisons between groups, these datasets were used for model development and validation, respectively. The differences in clinical indicators between the two patients groups were assessed using the chi-square test and the Wilcoxon rank sum test. In the training group, Lasso regression was utilized to identify variables significantly associated with END. Seven machine learning algorithms-decision tree (DT), random forest (RF), light gradient boosting machine (LGBM), extreme gradient boosting (XGB), K-nearest neighbors (KNN), support vector machine (SVM), and logistic regression (LR)-were employed to develop predictive models. The optimal hyperparameters were determined via grid search integrated with 5-fold cross-validation. The final algorithm was selected based on comprehensive model performance evaluation. Additionally, clinical data of 79 patients with ACI, collected between June 1 to August 31, 2025, were compiled as an independent test set for external validation. The cohort comprised 49 males and 30 females, with a median age of 68 years (interquartile range: 57-72). The SHapley Additive exPlanations (SHAP) method was employed to access feature importance and model interpretability. SHAP dependence plots and interaction plots were utilized to emplore the nonlinear relationships and interaction effects among the featurevariables. Results:Among the 502 patients, 166 experienced END during 7 days of hospitalization. Lasso regression identified nine significant predictors: history of hyperlipidemia, admission NIHSS score, lymphocyte-to-monocyte ratio (LMR), hemoglobin, D-dimer, albumin, neuron-specific enolase (NSE), homocysteine (HCY), and vitamin B12. The area under the receiver operating characteristic curve (AUC) for the seven machine learning models ranged from 0.709 to 0.946. The XGB model achieved the highest predictive performance, with an AUC of 0.946 (95% CI 0.924-0.960) in the training cohort and 0.867 (95% CI 0.902-0.933) in the validation cohort. SHAP analysis revealed that the top five variables contributing to END prediction were admission NIHSS score, HCY, D-dimer, history of hyperlipidemia, and vitamin B12. Conclusion:This study successfully developed a laboratory-based prediction model for END using the XGB machine learning algorithm, which demonstrated strong predictive performance.