(1) Objective: To evaluate the performance of ultrasound-based radiomics in the preoperative prediction of human epidermal growth factor receptor 2-positive (HER2+) and HER2− breast carcinoma. (2) Methods: Ultrasound images from 309 patients (86 HER2+ cases and 223 HER2− cases) were retrospectively analyzed, of which 216 patients belonged to the training set and 93 patients assigned to the time-independent validation set. The region of interest of the tumors was delineated, and the radiomics features were extracted. Radiomics features underwent dimensionality reduction analyses using the intra-class correlation coefficient (ICC), Mann–Whitney U test, and the least absolute shrinkage and selection operator (LASSO) algorithm. The radiomics score (Rad-score) for each patient was calculated through a linear combination of the nonzero coefficient features. The support vector machine (SVM), K nearest neighbors (KNN), logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB) and XGBoost (XGB) machine learning classifiers were trained to establish prediction models based on the Rad-score. A clinical model based on significant clinical features was also established. In addition, the logistic regression method was used to integrate Rad-score and clinical features to generate the nomogram model. The leave-one-out cross validation (LOOCV) method was used to validate the reliability and stability of the model. (3) Results: Among the seven classifier models, the LR achieved the best performance in the validation set, with an area under the receiver operating characteristic curve (AUC) of 0.786, and was obtained as the Rad-score model, while the RF performed the worst. Tumor size showed a statistical difference between the HER2+ and HER2− groups (p = 0.028). The nomogram model had a slightly higher AUC than the Rad-score model (AUC, 0.788 vs. 0.786), but no statistical difference (Delong test, p = 0.919). The LOOCV method yielded a high median AUC of 0.790 in the validation set. (4) Conclusion: The Rad-score model performs best among the seven classifiers. The nomogram model based on Rad-score and tumor size has slightly better predictive performance than the Rad-score model, and it has the potential to be utilized as a routine modality for preoperatively determining HER2 status in BC patients non-invasively.

We read the recent published paper in this journal of J Gastrointest Oncol by Zhang and colleagues entitled "Secondary colon cancer in patients with ulcerative colitis: a systematic review and meta-analysis" (1). They performed a systematic review and meta-analysis to assess the correlation between ulcerative colitis (UC) and colon cancer. We appreciate Zhang et al. (1) for the valuable study, however, after a careful learning of the literature, several limitations should be noticed.First, in the results section of the abstract, Zhang et al.(1) performed the meta-analysis by random-effect model because of statistical heterogeneity (Chi 2 =103.10; I 2 =90%; P<0.00001) and found that there were no significant differences between colon cancer in patients with UC and patients without colon carcinoma (Z =12.44; P<0.00001). However, we believe the interpretation of the results was false. There should be significant difference due to P<0.00001.Second, in the statistical methods section of this article, Zhang et al. (1) stated that the odds ratio (OR) was used as an effect size for dichotomous variables. Whereas, in this meta-analysis, the effect size actually was relative risk (RR) showed in figures 5,6 and the OR was not reported in the study. Therefore, we believe the irrelevant effect size depicted would lead to misunderstanding.