Objective:To explore the feasibility of selecting appropriate respiratory motion management strategies for patients undergoing stereotactic radiotherapy for liver cancer using chi-square feature testing and machine learning techniques.Methods:A retrospective analysis was conducted on 95 liver cancer patients who underwent respiratory motion evaluation at Xiangya Hospital of Central South University between March 2022 and August 2024. Chi-square testing was used to screen features related to respiratory motion evaluation in liver cancer patients. Based on these features, predictive models were constructed using 4 machine learning classification algorithms: support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), and adaptive boosting (AdaBoost). The predictive performance of these models was evaluated using accuracy, sensitivity, specificity, F1 value, and area under the curve (AUC).Results:The accuracy values for the SVM, RF, GBDT and AdaBoost models were 0.75, 0.75, 0.70, and 0.82, respectively. The sensitivity values were 0.82, 0.82, 0.64, and 0.82, respectively. The specificity values were 0.63, 0.63, 0.63, and 0.75, respectively. The F1 scores were 0.78, 0.78, 0.67, and 0.82, respectively. The AUC values were 0.85, 0.80, 0.76, and 0.85, respectively.Conclusions:The predictive models constructed by combining chi-square feature testing and machine learning methods can effectively predict the selection of respiratory motion management strategies. Among the models, the AdaBoost model demonstrated the best predictive performance for selecting respiratory motion management strategies.

Objective:To explore the feasibility of selecting appropriate respiratory motion management strategies for patients undergoing stereotactic radiotherapy for liver cancer using chi-square feature testing and machine learning techniques.Methods:A retrospective analysis was conducted on 95 liver cancer patients who underwent respiratory motion evaluation at Xiangya Hospital of Central South University between March 2022 and August 2024. Chi-square testing was used to screen features related to respiratory motion evaluation in liver cancer patients. Based on these features, predictive models were constructed using 4 machine learning classification algorithms: support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), and adaptive boosting (AdaBoost). The predictive performance of these models was evaluated using accuracy, sensitivity, specificity, F1 value, and area under the curve (AUC).Results:The accuracy values for the SVM, RF, GBDT and AdaBoost models were 0.75, 0.75, 0.70, and 0.82, respectively. The sensitivity values were 0.82, 0.82, 0.64, and 0.82, respectively. The specificity values were 0.63, 0.63, 0.63, and 0.75, respectively. The F1 scores were 0.78, 0.78, 0.67, and 0.82, respectively. The AUC values were 0.85, 0.80, 0.76, and 0.85, respectively.Conclusions:The predictive models constructed by combining chi-square feature testing and machine learning methods can effectively predict the selection of respiratory motion management strategies. Among the models, the AdaBoost model demonstrated the best predictive performance for selecting respiratory motion management strategies.

OBJECTIVE To investigate the improvement effects of Runchang granules on the constipation in mice and its potential mechanism. METHODS The mice were randomly divided into normal control group， model group， Runchang granules low-dose and high-dose groups （5， 10 g/kg）， mosapride group （0.003 g/kg， positive control）， with 6 mice in each group. The latter 4 groups were given loperamide intragastrically （0.004 g/kg）， twice a day， for 3 consecutive days. Normal control group and model group were given purified water intragastrically， and administration groups were given relevant medicine intragastrically for 7 consecutive days. After the last medication， fecal moisture content and intestinal motility of mice were determined， while the structures of colon and ileum， and the secretion of colonic mucus were observed. Protein expressions of tyrosine kinase receptor （c-kit）， mucin 2 （MUC2） and stem cell factor （SCF） were determined in colon； meanwhile， the mRNA expression levels of inflammatory factors [tumor necrosis factor-α （TNF-α）， interleukin-6 （IL-6）， IL-1β， inducible nitric oxide synthase （iNOS）] as well as factors related to promoting intestinal motility [neuronal nitric oxide synthase （nNOS）， smooth muscle myosin light chain kinase （smMLCK）， 5-hydroxytryptamine 4 receptor （5-HT4R）， MUC2， SCF， c-kit] were determined. RESULTS Compared with model group， the fecal water content， intestinal propulsion rate， protein expression of c-kit in colon， relative expressions of MUC2 and SCF protein， and mRNA expressions of factors related to promoting intestinal motility （except for nNOS and SCF in Runchang granules low-dose group） were all increased significantly in Runchang granules low-dose and high-dose groups， and mosapride group （P＜0.05 or P＜0.01）. mRNA expression levels of inflammatory factors were decreased significantly（P＜0.05 or P＜0.01）. Both colon and ileum injuries improved， and the secretion of colon mucus was increased significantly in Runchang granules high-dose group （P＜0.01）. CONCLUSIONS Runchang granules have laxative effect and can improve constipation in mice， and its mechanism may be related to the promotion of the secretion of colon mucus and MUC2 expression， and the activation of SCF/c-kit signaling pathway.

ObjectiveTo explore the method of establishing a disease-syndrome combined model of irritable bowel syndrome （IBS-D） with spleen and kidney yang deficiency in mice. MethodsModel establishment： Twenty mice were randomly divided into a normal group and a model group， with 10 mice in each group. The model group was given 50 mg/（kg·d） of 0℃ ice adenine suspension by gavage for 14 days， plus tail-clamping stimulation and restrained in centrifuge tubes for 7 days， and 10 g/（kg·d） of 0 ℃ ice senna decoction by gavage for 5 days to prepare IBS-D spleen and kidney yang deficiency syndrome model. The normal group was given 0.4 ml of sterile water by gavage once a day for 14 days. Behavioral characteristics， food intake， fecal water content， body weight， and rectal temperature were observed in both groups. Pain threshold， gastric residual rate， intestinal propulsion rate， and the content of short-chain fatty acids （SCFAs）， serotonin （5-HT）， adrenocorticotropic hormone （ACTH）， corticosterone （CORT）， and D-xylose in the serum were detected after modeling. Model validation： Forty mice were randomly divided into a blank group （n=10） and a modeling group （n=30）. After successful modeling using the above method， the modeling group was divided into a model control group， Sishen Pill （四神丸） group， and pinaverium bromide group， with 10 mice in each group. The Sishen Pill group was given 5 g/（kg·d） of Sishen Pill decoction by gavage， and the pinaverium bromide group was given 21.63 mg/（kg·d） of pinaverium bromide solution by gavage， while the blank group and the model control group were given 0.70 ml/d of sterile water by gavage， all for 7 days. The indicators were detected as the same with model establishment. ResultsMice in the model group had poor mental status， lethargy， dull hair and loose feces. Compared with the normal group， the model group exhibited reduced food intake and increased fecal water content ； on the 14th day of modeling， the model group showed a slower body weight gain rate and decreased rectal tempe-rature； after 14 days， the model group had increased small intestinal propulsion rate， and serum SCFAs and 5-HT levels with reduced serum levels of ACTH， CORT， and D-xylose （P＜0.05 or P＜0.01）. Model validation indicated that the Sishen Pill group showed improvements in mental state， activity levels， fur smoothness and curling and gathering symptoms， while these symptoms in the pinaverium bromide group were not significantly improved. Compared to the model control group， the Sishen Pill group and pinaverium bromide group had reduced fecal water content and increased food intake， as well as increased body weight gain and elevated rectal temperature on day 4. On the 7th day of administration， the pinaverium bromide group showed lower rectal temperature than Sishen Pill group， and Sishen Pill group showed decreased serum SCFAs and 5-HT levels with increased ACTH， CORT， and D-xylose levels （P＜0.05 or P＜0.01）， while the pinaverium bromide group exhibited reduced 5-HT and elevated CORT level （P＜0.01）. ConclusionA combination of ice adenine plus ice senna leaf gavage， tail clamping， and centrifuge tube restraint can successfully establish a disease-syndrome combined mouse model of IBS-D with spleen-kidney Yang deficiency.

Objective To investigate the anti-inflammatory effect and mechanism of sappanone A(SA)on lipopolysaccharide(LPS)-induced RAW264.7 cell model based on JAK2-STAT3 signaling pathway.Methods MTT assay was used to detect the effects of sappanone A,LPS and AG490 on RAW264.7 cell viability.The LPS-induced inflammatory model in RAW264.7 cells was established,and the secretion level of interleukin-6(IL-6)in the supernatant was detected by ELISA.mRNA expressions of IL-6,Janus kinase 2(JAK2)and signal transducer and activator of transcription 3(STAT3)were tested by RT-PCR.The protein expressions of JAK2,phosphorylated JAK2(p-JAK2),STAT3 and phosphorylated STAT3(p-STAT3)were determined by Western Blot.Results Compared with control group,IL-6 secretion level was significantly increased,mRNA expressions of IL-6,JAK2 and STAT3 were up-regulated,and protein expressions of p-JAK2 and p-STAT3 were increased(all P＜0.01)in model group.Compared with model group,high-dosed sappanone A(5 μg·mL-1)was significantly decreased the secretion of IL-6,down-regulated the mRNA expressions of IL-6,JAK2 and STAT3,and inhibited the protein expressions of p-JAK2 and p-STAT3(all P＜0.01).Conclusion Sappanone A may play an anti-inflammatory role by inhibiting the JAK2-STAT3 signaling pathway and hence inhibiting the secretion of IL-6.