Objective:To explore the value of a model combining 18F-FDG PET/CT radiomics and clinical factors in prediction of lymphovascular invasion (LVI) in rectal cancer. Methods:This retrospective cohort study was conducted on 120 patients (86 males and 34 females; age (62.2±11.6) years) with rectal adenocarcinoma from the Affiliated Hospital of Qingdao University between January 2017 and November 2023. Patients were divided into a training set ( n=96) and testing set ( n=24) at the ratio of 8∶2 using simple random sampling without replacement with a fixed random seed. An external validation cohort consisted of 31 patients (17 males and 14 females; age (61.2±8.2) years) with rectal adenocarcinoma from Affiliated Hospital of Jining Medical University and Linyi Cancer Hospital between January 2020 and June 2024 was obtained. PET/CT-derived features were selected to build radiomics model. The χ2 test and logistic regression were used to identify clinical predictors of LVI for clinical modeling. A combined radiomics-clinical nomogram was developed, after that ROC analysis was conducted to evaluate the predictive performance. Results:Significant differences were found between LVI-positive ( n=40) and LVI-negative ( n=56) subgroups in body weight, carbohydrate antigen (CA) 19-9, metabolic tumor volume (MTV), and peak of SUV (SUV peak) in the training set ( χ2 values: 4.01-13.64, all P<0.05). Binary logistic regression identified body weight (odds ratio ( OR)=0.320, 95% CI: 0.095-0.906, P=0.033), CA19-9 ( OR=0.402, 95% CI: 0.120-0.917, P=0.033), and MTV ( OR=0.192, 95% CI: 0.090-0.575, P=0.002) as independent predictors of LVI, forming the clinical model. Thirteen PET features and fifteen CT features were selected and a radiomics model was built. ROC curve analysis showed that AUCs for the clinical model in the training, testing, and external validation sets were 0.765, 0.567, and 0.777, respectively; AUCs for the radiomics model were 0.925, 0.881, and 0.823; AUCs for the joint model were 0.938, 0.889, and 0.841. Conclusion:The joint model of 18F-FDG PET/CT radiomics and clinical factors can effectively predict LVI in rectal cancer, guiding preoperative therapy and surgical planning.

Objective:To establish an early warning model of oral infection risk in patients with acute leukemia undergoing chemotherapy and to verify its predictive efficacy, so as to provide reference for formulating strategies to prevent oral infections.Methods:A retrospective study was conducted to select 288 patients with acute leukemia undergoing chemotherapy from January 2021 to January 2023 in Hematology Hospital of Chinese Academy of Medical Sciences (Institute of Hematology, Chinese Academy of Medical Sciences) as the training set. According to whether they developed oral infection after chemotherapy, they were divided into the infected group and the non-infected group. The risk factors of oral infection in patients with acute leukemia undergoing chemotherapy were investigated, and a risk warning model was established. A total of 246 acute leukemia undergoing chemotherapy patients admitted to the same hospital from February 2023 to February 2024 were selected as the validation set to conduct external verification of the model.Results:The oral infection rate was 19.44% (56/288) in the training set. There were 21 males and 35 females in the infected group (56 cases), with 49 cases<60 years old and 7 cases ≥60 years old. There were 102 males and 130 females in the non infected group (232 cases), with 196 cases<60 years old and 36 cases ≥60 years old. Multivariate analysis showed that neutrophil count <1.5×10 9/L, nutritional risk screening 2002≥3 points, high-dose of methotrexate, antibiotic types ≥3, poor oral self-cleaning habits, oral pH ≤6.5 were the risk factors for oral infection in patients with acute leukemia undergoing chemotherapy ( OR values were 2.716-10.074, all P<0.05). Based on this, the risk early warning model was as follows: Logit ( P)=-5.849+2.310× neutrophil count <1.5×10 9/L+1.363× nutritional risk screening 2002≥3 points +1.150× high-dose methotrexate +1.132× antibiotic types ≥3 + 1.044× oral pH ≤6.5 + 0.999× poor oral self-cleaning habits. The area under receiver operator characteristics curves (ROC) curve of this model Logit ( P) was 0.892, the maximum approximate entry index was 0.653, the sensitivity was 0.804, and the specificity was 0.849. Hosmer-Lemeshow test results indicated that χ2=4.91, P=0.768. For external validation, the goodness of fit test results were χ2=6.47, P=0.595. The area under ROC curve was 0.884, the sensitivity was 0.832, and the specificity was 0.825. Conclusions:The established early warning model of oral infection risk in patients with acute leukemia undergoing chemotherapy has good predictive value, which is helpful for medical staff to conduct early risk assessment of oral infection in such patients, and formulate countermeasures to reduce the incidence and improve the treatment effect of the disease.

Objective:To establish an early warning model of oral infection risk in patients with acute leukemia undergoing chemotherapy and to verify its predictive efficacy, so as to provide reference for formulating strategies to prevent oral infections.Methods:A retrospective study was conducted to select 288 patients with acute leukemia undergoing chemotherapy from January 2021 to January 2023 in Hematology Hospital of Chinese Academy of Medical Sciences (Institute of Hematology, Chinese Academy of Medical Sciences) as the training set. According to whether they developed oral infection after chemotherapy, they were divided into the infected group and the non-infected group. The risk factors of oral infection in patients with acute leukemia undergoing chemotherapy were investigated, and a risk warning model was established. A total of 246 acute leukemia undergoing chemotherapy patients admitted to the same hospital from February 2023 to February 2024 were selected as the validation set to conduct external verification of the model.Results:The oral infection rate was 19.44% (56/288) in the training set. There were 21 males and 35 females in the infected group (56 cases), with 49 cases<60 years old and 7 cases ≥60 years old. There were 102 males and 130 females in the non infected group (232 cases), with 196 cases<60 years old and 36 cases ≥60 years old. Multivariate analysis showed that neutrophil count <1.5×10 9/L, nutritional risk screening 2002≥3 points, high-dose of methotrexate, antibiotic types ≥3, poor oral self-cleaning habits, oral pH ≤6.5 were the risk factors for oral infection in patients with acute leukemia undergoing chemotherapy ( OR values were 2.716-10.074, all P<0.05). Based on this, the risk early warning model was as follows: Logit ( P)=-5.849+2.310× neutrophil count <1.5×10 9/L+1.363× nutritional risk screening 2002≥3 points +1.150× high-dose methotrexate +1.132× antibiotic types ≥3 + 1.044× oral pH ≤6.5 + 0.999× poor oral self-cleaning habits. The area under receiver operator characteristics curves (ROC) curve of this model Logit ( P) was 0.892, the maximum approximate entry index was 0.653, the sensitivity was 0.804, and the specificity was 0.849. Hosmer-Lemeshow test results indicated that χ2=4.91, P=0.768. For external validation, the goodness of fit test results were χ2=6.47, P=0.595. The area under ROC curve was 0.884, the sensitivity was 0.832, and the specificity was 0.825. Conclusions:The established early warning model of oral infection risk in patients with acute leukemia undergoing chemotherapy has good predictive value, which is helpful for medical staff to conduct early risk assessment of oral infection in such patients, and formulate countermeasures to reduce the incidence and improve the treatment effect of the disease.

Objective:To explore the value of a model combining 18F-FDG PET/CT radiomics and clinical factors in prediction of lymphovascular invasion (LVI) in rectal cancer. Methods:This retrospective cohort study was conducted on 120 patients (86 males and 34 females; age (62.2±11.6) years) with rectal adenocarcinoma from the Affiliated Hospital of Qingdao University between January 2017 and November 2023. Patients were divided into a training set ( n=96) and testing set ( n=24) at the ratio of 8∶2 using simple random sampling without replacement with a fixed random seed. An external validation cohort consisted of 31 patients (17 males and 14 females; age (61.2±8.2) years) with rectal adenocarcinoma from Affiliated Hospital of Jining Medical University and Linyi Cancer Hospital between January 2020 and June 2024 was obtained. PET/CT-derived features were selected to build radiomics model. The χ2 test and logistic regression were used to identify clinical predictors of LVI for clinical modeling. A combined radiomics-clinical nomogram was developed, after that ROC analysis was conducted to evaluate the predictive performance. Results:Significant differences were found between LVI-positive ( n=40) and LVI-negative ( n=56) subgroups in body weight, carbohydrate antigen (CA) 19-9, metabolic tumor volume (MTV), and peak of SUV (SUV peak) in the training set ( χ2 values: 4.01-13.64, all P<0.05). Binary logistic regression identified body weight (odds ratio ( OR)=0.320, 95% CI: 0.095-0.906, P=0.033), CA19-9 ( OR=0.402, 95% CI: 0.120-0.917, P=0.033), and MTV ( OR=0.192, 95% CI: 0.090-0.575, P=0.002) as independent predictors of LVI, forming the clinical model. Thirteen PET features and fifteen CT features were selected and a radiomics model was built. ROC curve analysis showed that AUCs for the clinical model in the training, testing, and external validation sets were 0.765, 0.567, and 0.777, respectively; AUCs for the radiomics model were 0.925, 0.881, and 0.823; AUCs for the joint model were 0.938, 0.889, and 0.841. Conclusion:The joint model of 18F-FDG PET/CT radiomics and clinical factors can effectively predict LVI in rectal cancer, guiding preoperative therapy and surgical planning.