Prediction models for postoperative recurrence of non-lactating mastitis based on machine learning.

OBJECTIVES: This study aims to build a machine learning (ML) model to predict the recurrence probability for postoperative non-lactating mastitis (NLM) by Random Forest (RF) and XGBoost algorithms. It can provide the ability to identify the risk of NLM recurrence and guidance in clinical treatment plan. METHODS: This study was conducted on inpatients who were admitted to the Mammary Department of Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine between July 2019 to December 2021. Inpatient data follow-up has been completed until December 2022. Ten features were selected in this study to build the ML model: age, body mass index (BMI), number of abortions, presence of inverted nipples, extent of breast mass, white blood cell count (WBC), neutrophil to lymphocyte ratio (NLR), albumin-globulin ratio (AGR) and triglyceride (TG) and presence of intraoperative discharge. We used two ML approaches (RF and XGBoost) to build models and predict the NLM recurrence risk of female patients. Totally 258 patients were randomly divided into a training set and a test set according to a 75%-25% proportion. The model performance was evaluated based on Accuracy, Precision, Recall, F1-score and AUC. The Shapley Additive Explanations (SHAP) method was used to interpret the model. RESULTS: There were 48 (18.6%) NLM patients who experienced recurrence during the follow-up period. Ten features were selected in this study to build the ML model. For the RF model, BMI is the most important influence factor and for the XGBoost model is intraoperative discharge. The results of tenfold cross-validation suggest that both the RF model and the XGBoost model have good predictive performance, but the XGBoost model has a better performance than the RF model in our study. The trends of SHAP values of all features in our models are consistent with the trends of these features' clinical presentation. The inclusion of these ten features in the model is necessary to build practical prediction models for recurrence. CONCLUSIONS: The results of tenfold cross-validation and SHAP values suggest that the models have predictive ability. The trend of SHAP value provides auxiliary validation in our models and makes it have more clinical significance.

Minimally invasive comprehensive treatment for granulomatous lobular mastitis.

OBJECTIVE: To describe a minimally invasive comprehensive treatment for granulomatous lobular mastitis (GLM) and compare its effect with the existing methods, particularly in terms of its recurrence rate and esthetic outcomes. METHODS: This retrospective study reviewed 69 GLM patients receiving the minimally invasive comprehensive treatment. Patients' information, including age, clinical features, image characteristics, histopathological findings, mastitis history, treatment process, operative technique, recurrence, and esthetic effect, was evaluated. RESULTS: All patients were female with a median age of 32 (range 17-55) years. Hospital stays ranged from 2 to 34 days, with a median of 6 days. The shortest time for complete rehabilitation was 2 days and the longest time was 365 days, with a median of 30 days. After a median follow-up of 391 days (range 162-690), 7 patients (10.14%) relapsed. The average cosmetic score was 2.62 ± 0.57 points and was mainly related to the past treatment, especially the surgical history. CONCLUSION: Minimally invasive comprehensive treatment is a new method for the treatment of GLM, ensuring a therapeutic effect while maintaining breast beauty.

A rare case of streptococcus mitis infective endocarditis complicated by heart failure in a lactating mother with recurrent breast engorgement

@#Infective endocarditis during breastfeeding is rare. To the best of the authors’ knowledge, this is the second recorded case of infective endocarditis in a lactating mother. It is known that women of child-bearing age are susceptible to infective endocarditis during pregnancy when the immune system is compromised.1 Nevertheless, past cases were also exposed to a systemic infection via milk infected by their infant’s oral commensal. Streptococcus mitis (S.Mitis) endocarditis in pregnancy has also been reported, whereby a lady delivered via caesarean section and underwent mitral valve reconstruction and annuloplasty.1 S. mitis is considered a pioneer streptococci commensal in human oral mucosa, appearing as early as 1-3 days after delivery.2 As a child grows, their oral mucosa will be colonized by more viridans streptococci, including the teeth, oropharynx and nasopharynx. In a mother who breastfeeds, a crack in the nipple and breast engorgement can be predisposing factors for systemic infection stemming from an infant’s oral commensal. Both cases of breastfeeding-related infective endocarditis caused by pioneer streptococcus viridans, S.mitis in our report and S.salivarius3 in the previous report, affected the left-sided valves