Objective:To construct a machine learning model based on localization CT-based radiomics, dosiomics and clinical features for predicting radiotherapy response in non-small cell lung cancer (NSCLC) and validate its application value.Methods:A retrospective case series study was conducted. A total of 138 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022 were selected. The efficacy was evaluated according to the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, and the patients were stratified according to the objective remission (complete remission+partial remission). Random stratified sampling was used to divide the 138 patients into a training group (96 cases) and an internal validation group (42 cases) at a ratio of 7∶3. Additionally, 33 patients who received radiotherapy at Jining Cancer Hospital from January 2019 to December 2022 were included as the external validation group. Based on the pre-radiotherapy data of the radiotherapy planning system, PyRadiomics software package was used to extract 107 radiomics features and 107 dosiomics features for each patient. Pearson correlation analysis and LASSO regression analysis were used for dimensionality reduction screening; the final selected features were weighted and integrated to generate radiomics-dosiomics scores (RDS), which were then input into logistic regression (LR), support vector machine (SVM), extremely randomized forest (Extra Trees), K-nearest neighbor algorithm (KNN), lightweight gradient boosting machine (Light GBM), and multi-layer perceptron (MLP) machine learning algorithms to construct 6 radiomics-dosiomics models (RDM) for predicting the objective remission. RECIST 1.1 standard was used to evaluate objective remission as the gold standard, receiver operating characteristic (ROC) curve of 6 RDM for predicting objective remission was plotted, and the optimal algorithm for RDM was selected. Univariate and multivariate logistic regression were performed on demographic characteristics, hematological indicators and radiotherapy parameters of the training group to screen independent risk factors for NSCLC patients who received radiotherapy but did not achieve objective remission. These factors were input into the optimal machine learning algorithm to construct a clinical model (CM). Combined with features from RDS and CM, the clinical feature-radiomics-dosiomics combined model (CRDM) was established, and the nomogram of the model for predicting objective remission in NSCLC patients with radiotherapy was drawn. ROC curves were used to evaluate the efficacy of CM, RDM and CRDM in predicting the objective remission in NSCLC patients with radiotherapy in the training group, internal validation group and external validation group.Results:Four radiomics features (including grayscale variance, low grayscale long-range operation emphasis, low grayscale area emphasis, and small area low grayscale area emphasis, all of which were texture features) and 6 dosiomics features [including 1 first-order feature (robust mean absolute deviation), 4 texture features (grayscale non-uniformity, large area emphasis, large area high grayscale emphasis, contrast) and 1 shape feature (shortest axis length)] were selected. ROC curve analysis showed that the area under the curve (AUC) of the RDM constructed using SVM algorithm for judging the objective remission in the training group and the internal validation group was 0.907 (95% CI: 0.836-0.977) and 0.822 (95% CI: 0.685-0.959), which were higher than RDM constructed using other algorithms, and the sensitivity (96.2% and 91.7%), specificity (78.6% and 76.7%) and accuracy (83.3% and 81.0%) at the optimal cut-off values were all higher. Considering the stability and generalization ability of the model, SVM algorithm was ultimately used to construct RDM, CM and CRDM uniformly. Based on training group data, univariate and multivariate logistic regression analysis showed that elevated platelet-to-lymphocyte ratio (PLR) ( OR = 1.001, 95% CI: 1.000-1.003, P = 0.035) and increased target volume of radiotherapy plan ( OR = 1.001, 95% CI: 1.000-1.001, P = 0.008) were independent risk factors for failure to achieve objective remission. ROC curve analysis showed that in the training group and the internal validation group, the AUC of CRDM predicting objective remission were 0.914 (95% CI: 0.856-0.972) and 0.864 (95% CI: 0.754-0.974), respectively, which were better than CM [AUC were 0.735 (95% CI: 0.612-0.857) and 0.697 (95% CI: 0.507-0.888)] and RDM, respectively. In the external validation group, the AUC of CRDM, CM and RDM were 0.778 (95% CI: 0.500-1.000), 0.667 (95% CI: 0.434-0.899) and 0.741 (95% CI: 0.463-1.000), respectively. Conclusions:The CRDM constructed by combining radiomics, dosiomics and clinical features can comprehensively and accurately evaluate the radiotherapy response of NSCLC patients, and may have important clinical application value in achieving precision medicine and optimizing treatment strategies.

Objective:To develop and validate a combined model integrating radiomics, dosiomics, and clinical parameters based on CT simulation and dosimetric images in order to predict the occurrence of radiation pneumonitis (RP) in patients with non-small cell lung cancer (NSCLC).Methods:A retrospective study was conducted on the clinic data of 143 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022. Patients were randomly stratified into a training group ( n = 100) and an internal validation group ( n = 43) at a 7∶3 ratio. Moreover, clinic data were collected from 34 NSCLC patients who received radiotherapy at the Jining Cancer Hospital between January 2019 and December 2022 as an external validation group. All three groups (the training group, internal validation, and external validation groups) were further categorized into two groups based on the RP severity (i.e., RP ≥ grade 2 and RP < grade 2). Their radiotherapy dose, CT simulation, and 3D dose distribution images were collected. Then, the total lung minus planning target volume (TL-PTV) was defined as the region of interest (ROI) for radiomics and dosiomic feature extraction, followed by feature dimensionality reduction. Consequently, key features associated with RP were determined. Four predictive models were developed using machine learning approaches (especially multilayer perceptron, MLP): a clinical model (CM), a radiomics model (RM), a dosiomics model (DM), and a radiomics and dosiomics nomogram (RDN), with a nomogram subsequently constructed. Ultimately, the performance and clinical feasibility of these models were assessed using receiver operating characteristic (ROC), area under the curve (AUC), and decision curve analysis (DCA). Results:A total of 1 834 radiomic features and 1 834 dosiomic features were extracted. Using the occurrence of RP ≥ grade 2 as the marker variable, 14 radiomic features, 15 dosiomic features, and three clinical features were selected from the training group to construct the prediction models (CM, RM, DM, and RDN). The performance and generalizability of these models were subsequently validated in both the internal validation and external validation groups. Specifically, the RDN exhibited AUCs of 0.915 (95% CI: 0.852-0.978), 0.879 (95% CI: 0.777-0.982), and 0.838 (95% CI: 0.701-0.975) in the three groups, respectively. A nomogram was established for RDN by integrating the radiomics score (R-score), dosiomics score (D-score), mean lung dose (MLD), V20, and V30. This nomogram allowed for individualized risk estimation of RP and facilitated personalized radiotherapy planning. Conclusions:The RDN model that is developed based on CT simulation and 3D dose distribution images and integrates radiomics, dosiomics, and clinical features can effectively predict the RP risk of NSCLC patients. The integration of multidimensional data contributes to the formation of the optimal predictive model, offering guidance for clinicians.

Objective:To construct a machine learning model based on localization CT-based radiomics, dosiomics and clinical features for predicting radiotherapy response in non-small cell lung cancer (NSCLC) and validate its application value.Methods:A retrospective case series study was conducted. A total of 138 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022 were selected. The efficacy was evaluated according to the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, and the patients were stratified according to the objective remission (complete remission+partial remission). Random stratified sampling was used to divide the 138 patients into a training group (96 cases) and an internal validation group (42 cases) at a ratio of 7∶3. Additionally, 33 patients who received radiotherapy at Jining Cancer Hospital from January 2019 to December 2022 were included as the external validation group. Based on the pre-radiotherapy data of the radiotherapy planning system, PyRadiomics software package was used to extract 107 radiomics features and 107 dosiomics features for each patient. Pearson correlation analysis and LASSO regression analysis were used for dimensionality reduction screening; the final selected features were weighted and integrated to generate radiomics-dosiomics scores (RDS), which were then input into logistic regression (LR), support vector machine (SVM), extremely randomized forest (Extra Trees), K-nearest neighbor algorithm (KNN), lightweight gradient boosting machine (Light GBM), and multi-layer perceptron (MLP) machine learning algorithms to construct 6 radiomics-dosiomics models (RDM) for predicting the objective remission. RECIST 1.1 standard was used to evaluate objective remission as the gold standard, receiver operating characteristic (ROC) curve of 6 RDM for predicting objective remission was plotted, and the optimal algorithm for RDM was selected. Univariate and multivariate logistic regression were performed on demographic characteristics, hematological indicators and radiotherapy parameters of the training group to screen independent risk factors for NSCLC patients who received radiotherapy but did not achieve objective remission. These factors were input into the optimal machine learning algorithm to construct a clinical model (CM). Combined with features from RDS and CM, the clinical feature-radiomics-dosiomics combined model (CRDM) was established, and the nomogram of the model for predicting objective remission in NSCLC patients with radiotherapy was drawn. ROC curves were used to evaluate the efficacy of CM, RDM and CRDM in predicting the objective remission in NSCLC patients with radiotherapy in the training group, internal validation group and external validation group.Results:Four radiomics features (including grayscale variance, low grayscale long-range operation emphasis, low grayscale area emphasis, and small area low grayscale area emphasis, all of which were texture features) and 6 dosiomics features [including 1 first-order feature (robust mean absolute deviation), 4 texture features (grayscale non-uniformity, large area emphasis, large area high grayscale emphasis, contrast) and 1 shape feature (shortest axis length)] were selected. ROC curve analysis showed that the area under the curve (AUC) of the RDM constructed using SVM algorithm for judging the objective remission in the training group and the internal validation group was 0.907 (95% CI: 0.836-0.977) and 0.822 (95% CI: 0.685-0.959), which were higher than RDM constructed using other algorithms, and the sensitivity (96.2% and 91.7%), specificity (78.6% and 76.7%) and accuracy (83.3% and 81.0%) at the optimal cut-off values were all higher. Considering the stability and generalization ability of the model, SVM algorithm was ultimately used to construct RDM, CM and CRDM uniformly. Based on training group data, univariate and multivariate logistic regression analysis showed that elevated platelet-to-lymphocyte ratio (PLR) ( OR = 1.001, 95% CI: 1.000-1.003, P = 0.035) and increased target volume of radiotherapy plan ( OR = 1.001, 95% CI: 1.000-1.001, P = 0.008) were independent risk factors for failure to achieve objective remission. ROC curve analysis showed that in the training group and the internal validation group, the AUC of CRDM predicting objective remission were 0.914 (95% CI: 0.856-0.972) and 0.864 (95% CI: 0.754-0.974), respectively, which were better than CM [AUC were 0.735 (95% CI: 0.612-0.857) and 0.697 (95% CI: 0.507-0.888)] and RDM, respectively. In the external validation group, the AUC of CRDM, CM and RDM were 0.778 (95% CI: 0.500-1.000), 0.667 (95% CI: 0.434-0.899) and 0.741 (95% CI: 0.463-1.000), respectively. Conclusions:The CRDM constructed by combining radiomics, dosiomics and clinical features can comprehensively and accurately evaluate the radiotherapy response of NSCLC patients, and may have important clinical application value in achieving precision medicine and optimizing treatment strategies.

Objective:To develop and validate a combined model integrating radiomics, dosiomics, and clinical parameters based on CT simulation and dosimetric images in order to predict the occurrence of radiation pneumonitis (RP) in patients with non-small cell lung cancer (NSCLC).Methods:A retrospective study was conducted on the clinic data of 143 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022. Patients were randomly stratified into a training group ( n = 100) and an internal validation group ( n = 43) at a 7∶3 ratio. Moreover, clinic data were collected from 34 NSCLC patients who received radiotherapy at the Jining Cancer Hospital between January 2019 and December 2022 as an external validation group. All three groups (the training group, internal validation, and external validation groups) were further categorized into two groups based on the RP severity (i.e., RP ≥ grade 2 and RP < grade 2). Their radiotherapy dose, CT simulation, and 3D dose distribution images were collected. Then, the total lung minus planning target volume (TL-PTV) was defined as the region of interest (ROI) for radiomics and dosiomic feature extraction, followed by feature dimensionality reduction. Consequently, key features associated with RP were determined. Four predictive models were developed using machine learning approaches (especially multilayer perceptron, MLP): a clinical model (CM), a radiomics model (RM), a dosiomics model (DM), and a radiomics and dosiomics nomogram (RDN), with a nomogram subsequently constructed. Ultimately, the performance and clinical feasibility of these models were assessed using receiver operating characteristic (ROC), area under the curve (AUC), and decision curve analysis (DCA). Results:A total of 1 834 radiomic features and 1 834 dosiomic features were extracted. Using the occurrence of RP ≥ grade 2 as the marker variable, 14 radiomic features, 15 dosiomic features, and three clinical features were selected from the training group to construct the prediction models (CM, RM, DM, and RDN). The performance and generalizability of these models were subsequently validated in both the internal validation and external validation groups. Specifically, the RDN exhibited AUCs of 0.915 (95% CI: 0.852-0.978), 0.879 (95% CI: 0.777-0.982), and 0.838 (95% CI: 0.701-0.975) in the three groups, respectively. A nomogram was established for RDN by integrating the radiomics score (R-score), dosiomics score (D-score), mean lung dose (MLD), V20, and V30. This nomogram allowed for individualized risk estimation of RP and facilitated personalized radiotherapy planning. Conclusions:The RDN model that is developed based on CT simulation and 3D dose distribution images and integrates radiomics, dosiomics, and clinical features can effectively predict the RP risk of NSCLC patients. The integration of multidimensional data contributes to the formation of the optimal predictive model, offering guidance for clinicians.

Objective:To investigate the value of radiomics nomogram based on standardized pre-treatment chest enhanced CT in predicting the mutation status of epidermal growth factor receptor (EGFR) for patients with lung adenocarcinoma.Methods:A retrospective analysis was conducted on pre-treatment chest enhanced CT images and clinical data of 262 patients from the affiliated hospital of Jining Medical University with pathologically proven primary lung adenocarcinoma who received EGFR gene testing, including EGFR wild type ( n=122) and mutant type ( n=140). The patients were divided into training group ( n=183) and testing group ( n=79) according to a ratio of 7∶3 by stratified sampling method. Standardized pre-processed the images, delineated the ROI and extracted the radiomics features. Least absolute shrinkage and selection operator (LASSO) algorithm was used to reduce the dimension and select key features. The standardized radiomics model, clinical model and the combined model were established by Logistic Regression (LR) machine learning method. Calculated the Rad-score and drew the nomogram. ROC curve and Delong were used to evaluate and compare the predictive performance of different models. Results:23 standardized enhanced CT radiomics features and 4 clinical features were selected. The predictive performance of standardized radiomics model was better than that of non-standardized radiomics model [area under curve (AUC): 0.863 vs. 0.805, t=2.19, P<0.05]. The AUCs of the combined model and standardized radiomics model were higher than that of the clinical model (training group: 0.885, 0.863 vs. 0.774, t=3.57, 2.17, P<0.05; testing group: 0.873, 0.829 vs. 0.763, t=2.19, 2.02, P<0.05). The radiomics nomogram was built based on Rad-score, age, sex, smoking history and BMI. Conclusions:The combined model and standardized radiomics model could effectively predict the mutation status of EGFR gene in lung adenocarcinoma patients before treatment, providing valuable clinical insights.

Objective:To develop and verify a nomogram to predict disease-free survival(DFS)and overall survival(OS)for patients undergoing cervical cancer surgery,which may provide reference for evaluating the prognosis of cervical cancer patients undergoing surgery.Methods:The clinical,pathological and follow-up data of patients who underwent radical operation for cervical cancer in Xijing Hospital,Air Force Medical University from March 2013 to October 2018 were analyzed retrospectively.Based on Cox regression analysis,Bayesian Informa-tion Criterion(BIC)backward stepwise selection method and R square screening variables,Net Reclassification Index(NRI)and Integrated Discrimination Improvement(IDI)were used to compare the predictive efficiency of the model,and a nomogram with better predictive efficiency was selected.The consistency index(C-index)and the receiver operating characteristic curve(ROC)were used to test the efficiency of the nomogram.Results:A total of 950 patients with cervical cancer were enrolled in this study.The risk factors for constructing the DFS nomogram were FIGO stage(2018),parametrium invasion,invasion depth,and maximum tumor diameter.The C-index for DFS in the training cohort and the verification cohort were 0.754 and 0.720,respectively.The area under ROC of the training cohort for 1-,3-and 5-years was 0.74(95%CI 0.65-0.82),0.77(95%CI 0.71-0.83)and 0.79(95%CI0.74-0.85),and the areas under ROC of verification cohort 1-,3-and 5-years were 0.72(95%CI 0.58-0.87),0.75(95%CI 0.64-0.86)and 0.72(95%CI 0.61-0.84),respectively.The risk factors for con-structing the OS nomogram were FIGO stage(2018),histological type,LVSI,parametrium invasion,surgical mar-gin,and invasion depth.The C-index for OS in the training cohort and the verification cohort were 0.737 and 0.759,respectively.The area under ROC of the 3-and 5-year training cohort were 0.76(95%CI 0.69-0.83)and 0.78(95%CI 0.72-0.84),and the areas under ROC of verification cohort 3-and 5-years were 0.76(95%CI 0.65-0.87)and 0.79(95%CI 0.69-0.88),respectively.Conclusions:This study is based on real-world big data to construct nomogram of DFS for 1,3,and 5 years and OS for 3,and 5 years for cervical cancer,which have ideal predictive effects and help clinical physicians correctly evaluate the prognosis of cervical cancer surgery patients.It provides strong reference basis for diagnosis,treatment,and prognosis evaluation.

Ulcerative colitis （UC） is a chronic non-specific digestive disease with abdominal pain， diarrhea， and blood and mucus in stool as the main clinical manifestations and inflammatory injury of colorectal mucosa and submucosa as the main pathological changes. With the change in living habits and dietary structure of people， the incidence and cancer morbidity in UC are rising rapidly all over the world， which has seriously reduced the quality of life and caused a huge social burden. Till now， the pathogenesis has not been elucidated. In western medicine， aminosalicylates， corticosteroids， and immunosuppressors are commonly used to relieve symptoms. However， the long-term application will lead to problems such as decreased efficacy and increased adverse reactions. There are more studies of traditional Chinese medicine （TCM） in the treatment of UC by reducing the inflammatory response， alleviating oxidative stress， protecting the intestinal mucosal barrier， and regulating intestinal microecological imbalance by virtue of the advantages of integrated regulation based on multiple links， levels， and targets. In view of this， the present study reviewed the effect and mechanism of active ingredients of TCM， TCM extracts， TCM pairs， classic TCM compounds， and TCM combined with chemical agents in the treatment of UC based on relevant research articles in recent 10 years to provide references for seeking effective drugs.

Objective A high performance liquid chromatographic (HPLC) method was established for the simultaneous determination of xylitol and L-xylulose in fermentation broth.Methods The chromatographic conditions were as follows:C18 column (250 mm ×4.6 mm) with the temperature 35℃, acetonitrile-water (85∶15,v/v)as mobile phase with the flow rate of 0.8 mL/min.Xylitol was detected by refractive index (RI) detector at 33℃and L-xylulose was determined by ultraviolet ( UV) detector at 210 nm at room temperature.Results This method showed good linearity over the range from 0.50~30.00 g/L with a correlation coefficient of 0.9995 for xylitol and 0.30~30.00 g/L with a correlation coefficient of 0.9986 for L-xylulose. Moreover, the limit of quantification (LOQ) for xylitol and L-xylulose were 0.58 and 0.40,respectively.The limit of determination (LOD) for xylitol and L-xylulose were 0.18 and 0.15,respectively.The relative standard deviations (RSDs) of intraday and interday for xylitol were less than 0.64%and 0.80%,respectively.The intraday and interday RSDs for L-xylulose were less than 0.31%and 0.59%.The recoveries of xylitol and L-xylulose in fermentation broth were between 99.00%-101.00%.Conclusion There was no interference from other constitutes in the fermentation broth by this method.The methods were suitable for the simultaneous determination of the substrate xylitol and the product L-xylulose in fermentation process.

Objective To investigate the clinical application of serum retinal binding protein and cystain C determination in hem-orrhagic fever with renal syndrome(HFRS).Methods The serum concentrations of RBP,CysC,Urea and Cr were detected for 124 patients with HFRS(patients group)and 100 healthy people who underwent physical examination during the same period(control group),the date were analysed by SPSS19.0 software.Results The concentrations of RBP,CysC,Urea and Cr increased signifi-cantly in febrile stage of HFRS,arrived at peak in oliguria stage,and then declined gradually,there were statistically significant differences between each stage and negative control stage(P <0.05).RBP and CysC had a good positive correlation with Urea and Cr,the correlation coefficient between RBP and Urea or Cr were 0.826 and 0.892,respectively(P <0.05)while with CysC were 0. 841 and 0.924,respectively(P <0.05).The positive rates of RBP,CysC,Urea,Cr in febrile stage were 85.48%,95.16%,69.35%, 83.06% respectively,while in convalescent stage were 67.74%,74.19%,46.77% and 58.06% respectively.Conclusion RBP and CysC are good indicators for diagnosing HFRS,which also have good correlation with Urea and Cr,which are recommended in clini-cal application.

Objective To investigate the correlation between fasting plasma glucose(FPG)and body mass index(BMI)among examination groups in Baoji area.Methods 55 328 cases of medical examination were measured height,weight and calculated BMI,then these were detected FPG,the test results were analyzed by statistics.Results The levels of FPG and BMI were significant differences between different gender groups and different age groups;Male and female with abnormal FPG detec-tion rates were 9.90%,5.50%;FPG abnormal detection rate of male higher than female (χ2=335.47,P<0.005).The sub-j ects were divided into four groups according to their BMI:low-weight,normal,overweight and obesity.The relevance ratio of 4 groups with abnormal FPG were 2.71%,5.93%,11.65% and 13.75%,with diabetes were 1.38%,3.18%,6.02% and 6.39%,with impaired fasting glucose (IFG)were 0.8%,2.75%,5.64% and 7.37%.The detection rate of abnormal FPG, IFG and DM detection rate increased with increasing BMI levels (P<0.005).Conclusion The levels of FPG was upward trend with increasing BMI,increased prevalence of diabetes in overweight and obese people.The middle-aged population is the focus of monitoring and intervention of obesity.Control BMI is an effective measure to reduce the occurrence of diabetes.