Objective To investigate the construction and value of radiation pneumonitis(RP)predic-tive model based on machine learning algorithm.Methods A retrospective analysis was conducted on the clin-ical data in 77 patients with breast cancer receiving radiotherapy and regular follow-up in this hospital from August 2019 to September 2022.The affected side lung was delineated on the localization CT as the area of in-terest and the radiomics features were extracted,meanwhile the affected side lung dosimetric parameters were extracted.After feature screening,the patients were divided into the training set and testing set by a 7∶3 rati-o.The features of positioning CT radiomics were extracted and combined with the dosimetry parameters of the affected side lung,and the model was established by using stochastic gradient descent(SGD)algorithm.The performance of the model was validated by using the area under the receiver operating characteristic(ROC)curve(AUC)and decision curve analysis(DCA).Results Among 77 patients,24 cases developed RP after ra-diotherapy end with an incidence rate of 31.17％.Compared with the patients without RP occurrence,V5,V10,V15,V20,V25,V30 and mean lung dose(MLD)in the patients with RP occurrence were higher,and the differ-ence was statistically significant(P＜0.05).In the training set,36 cases did not develop RP.17 cases devel-oped RP,in the testing set,17 cases did not develop RP and 7 cases developed RP.The affected side lung dosi-metric parameters had no statistical difference between the training set and testing set with and without RP occurrence(P＞0.05).After characteristics screening,the 8 optimal characteristics combinations were finally obtained.The average AUC of SGD model in 50％off cross-validation of the training set was 0.900 and AUC in the test set was 0.882.Conclusion The positioning CT radiomics features combined with dosimetry param-eters of the affected side lung has the good predictive value for RP after breast cancer radiotherapy.

Objective:To investigate the early recognition of coronary artery lesions(CAL)in Kawasaki disease(KD)and its relationship with monocyte/high-density lipoprotein cholesterol(HDL-C)ratio(MHR).Methods:A total of 216 children with KD who were hospitalized in Affiliated Hospital of Nantong University from June 2019 to June 2022 were selected as the research subjects,and divided into training set(162 cases)and test set(54 cases).The clinical data of the children were collected,and the children in the training set were divided into the CAL group(45 cases)and the NCAL group(117 cases)according to the diagnostic results of echo-cardiography,and the differences in clinical data and laboratory test results were compared between the two groups;Logistic regres-sion analysis was used to analyze the risk factors of CAL in children with KD;Pearson was used to analyze the correlation between MHR and CAL in children with KD.According to the MHR quantile,the children in the CAL group were divided into low MHR group(≤0.28),medium MHR group(0.29～0.42)and high MHR group(≥0.43),and they were analyzed and compared.Cox regression model was used to analyze the relationship between MHR and CAL risk in children with KD,and a predictive model was constructed based on the independent risk factors of CAL in children with KD.Results:There were 162 KD children with fever,and summer was a high incidence period;compared with the NCAL group,the CAL group had statistically significant differences in age,gender,fever time,KD type,MHR,WBC,PLT,NLR,and CRP(all P<0.05);Pearson correlation analysis showed that MHR was positively cor-related with the degree of coronary artery dilatation in children with CAL(r=0.743,P=0.001).and the risk of CAL in the KD children in the high MHR group was significantly higher than that in the low MHR group(HR=2.857,95%CI:1.329～6.431,P=0.003);Logis-tic regression analysis showed that gender,fever time,MHR,WBC,NLR and CRP were independent risk factors for CAL in children with KD.A prediction model was constructed based on the independent risk factors of CAL:Logit(P)=1.342+0.359×gender+0.181×ever time+1.064×MHR+0.459×WBC+0.146×NLR+0.211×CRP,P=e logit(P)/1+e logit(P),the AUC of this model was 0.874(95%CI:0.799～0.892),compared with the test set(AUC was 0.881,95%CI:0.785～0.913),the difference was not statistically sig-nificant(P>0.05);the AUC of MHR for predicting CAL in children with KD was 0.796,the sensitivity was 0.896,and the specificity was 0.824,which could be used as an early predictor of CAL in children with KD.Conclusion:MHR has a certain predictive value in the diagnosis of CAL in children with KD,and can reflect the degree of CAL in children with KD to a certain extent.Therefore,it is necessary to pay attention to the changes of MHR in children with KD in clinical practice.