A diagnostic scoring model of ENKTCL in the nose-Waldeyer's ring based on logistic regression: Differential diagnosis from DLBCL.

Objective: To establish a logistic regression model based on CT and MRI imaging features and Epstein-Barr (EB) virus nucleic acid to develop a diagnostic score model to differentiate extranodal NK/T nasal type (ENKTCL) from diffuse large B cell lymphoma (DLBCL). Methods: This study population was obtained from two independent hospitals. A total of 89 patients with ENKTCL (n = 36) or DLBCL (n = 53) from January 2013 to May 2021 were analyzed retrospectively as the training cohort, and 61 patients (ENKTCL=27; DLBCL=34) from Jun 2021 to Dec 2022 were enrolled as the validation cohort. All patients underwent CT/MR enhanced examination and EB virus nucleic acid test within 2 weeks before surgery. Clinical features, imaging features and EB virus nucleic acid results were analyzed. Univariate analyses and multivariate logistic regression analyses were performed to identify independent predictors of ENKTCL and establish a predictive model. Independent predictors were weighted with scores based on regression coefficients. A receiver operating characteristic (ROC) curve was created to determine the diagnostic ability of the predictive model and score model. Results: We searched for significant clinical characteristics, imaging characteristics and EB virus nucleic acid and constructed the scoring system via multivariate logistic regression and converted regression coefficients to weighted scores. The independent predictors for ENKTCL diagnosis in multivariate logistic regression analysis, including site of disease (nose), edge of lesion (blurred), T2WI (high signal), gyrus like changes, EB virus nucleic acid (positive), and the weighted score of regression coefficient was 2, 3, 4, 3, 4 points. The ROC curves, AUCs and calibration tests were carried out to evaluate the scoring models in both the training cohort and the validation cohort. The AUC of the scoring model in the training cohort were 0.925 (95% CI, 0.906-0.990) and the cutoff point was 5 points. In the validation cohort, the AUC was 0.959 (95% CI, 0.915-1.000) and the cutoff value was 6 points. Four score ranges were as follows: 0-6 points for very low probability of ENKTCL, 7-9 points for low probability; 10-11 points for middle probability; 12-16 points for very high probability. Conclusion: The diagnostic score model of ENKTCL based on Logistic regression model which combined with imaging features and EB virus nucleic acid. The scoring system was convenient, practical and could significantly improve the diagnostic accuracy of ENKTCL and the differential diagnosis of ENKTCL from DLBCL.

A nomogram diagnostic prediction model of pancreatic metastases of small cell lung carcinoma based on clinical characteristics, radiological features and biomarkers.

Objective: To investigate clinical characteristics, radiological features and biomarkers of pancreatic metastases of small cell lung carcinoma (PM-SCLC), and establish a convenient nomogram diagnostic predictive model to differentiate PM-SCLC from pancreatic ductal adenocarcinomas (PDAC) preoperatively. Methods: A total of 299 patients with meeting the criteria (PM-SCLC n=93; PDAC n=206) from January 2016 to March 2022 were retrospectively analyzed, including 249 patients from hospital 1 (training/internal validation cohort) and 50 patients from hospital 2 (external validation cohort). We searched for meaningful clinical characteristics, radiological features and biomarkers and determined the predictors through multivariable logistic regression analysis. Three models: clinical model, CT imaging model, and combined model, were developed for the diagnosis and prediction of PM-SCLC. Nomogram was constructed based on independent predictors. The receiver operating curve was undertaken to estimate the discrimination. Results: Six independent predictors for PM-SCLC diagnosis in multivariate logistic regression analysis, including clinical symptoms, CA199, tumor size, parenchymal atrophy, vascular involvement and enhancement type. The nomogram diagnostic predictive model based on these six independent predictors showed the best performance, achieved the AUCs of the training cohort (n = 174), internal validation cohort (n = 75) and external validation cohort (n = 50) were 0.950 (95%CI, 0.917-0.976), 0.928 (95%CI, 0.873-0.971) and 0.976 (95%CI, 0.944-1.00) respectively. The model achieved 94.50% sensitivity, 83.20% specificity, 86.80% accuracy in the training cohort and 100.00% sensitivity, 80.40% specificity, 86.70% accuracy in the internal validation cohort and 100.00% sensitivity, 88.90% specificity, 87.50% accuracy in the external validation cohort. Conclusion: We proposed a noninvasive and convenient nomogram diagnostic predictive model based on clinical characteristics, radiological features and biomarkers to preoperatively differentiate PM-SCLC from PDAC.

A scoring model for radiologic diagnosis of gastric leiomyomas (GLMs) with contrast-enhanced computed tomography (CE-CT): Differential diagnosis from gastrointestinal stromal tumors (GISTs).

OBJECTIVES: To investigate CT findings and develop a diagnostic score model to differentiate GLMs from GISTs. METHODS: This retrospective study included 109 patients with pathologically confirmed GLMs (n = 46) and GISTs (n = 63) from January 2013 to August 2018 who received CE-CT before surgery. Demographic and radiological features was collected, including lesion location, contour, presence or absence of intralesional necrosis and ulceration, growth pattern, whether the tumor involved EGJ, the long diameter (LD) /the short diameter (SD) ratio, pattern and degree of lesion enhancement. Univariate analyses and multivariate logistic regression analyses were performed to identify independent predictors and establish a predictive model. Independent predictors for GLMs were weighted with scores based on regression coefficients. A receiver operating characteristic (ROC) curve was created to determine the diagnostic ability of the model. Overall score distribution was divided into four groups to show differentiating probability of GLMs from GISTs. RESULTS: Five CT features were the independent predictors for GLMs diagnosis in multivariate logistic regression analysis, including esophagogastric junction (EGJ) involvement (OR, 367.9; 95 % CI, 5.8-23302.8; P =  0.005), absence of necrosis (OR, 11.9; 95 % CI, 1.0-138. 1; P =  0.048) and ulceration (OR, 151.9; 95 % CI, 1.4-16899.6; P =  0.037), degree of enhancement (OR, 9.3; 95 % CI, 3.2-27.4; P <  0.001), and long diameter/ short diameter (LD/SD) ratio (OR,170.9; 95 % CI, 8.4-3493.4; P =  0.001). At a cutoff of 9 points, AUC for this score model was 0.95, with 95.65 % sensitivity, 79.37 % specificity, 77.19 % PPV, 96.15 % NPV and 86.24 % diagnostic accuracy. An increasing trend was showed in diagnostic probability of GLMs among four groups based on the score (P <  0.001). CONCLUSIONS: The newly designed scoring system is reliable and easy-to-use for GLMs diagnosis by distinguishing from GISTs, including EGJ involvement, absence of ulceration and necrosis, mild enhancement and high LD/SD ratio. The overall score of model ranged from 1 to 17 points, which was divided into 4 groups: 1-7 points, 7-10 points, 10-13 points and 13-17 points, with a diagnostic probability of GLMs 0%, 45 %, 83 % and 100 %, respectively.