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.

Adolescent Non-Puerperal Mastitis: Risk Factors, Clinical Characteristics, and Prognosis Analysis.

Purpose: To determine the risk factors, clinical characteristics, and prognosis of adolescent non-puerperal mastitis patients. Patients and methods: A retrospective analysis was conducted on 10 cases of NPM in adolescents who underwent surgical treatment at Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine from August 2021 to August 2023. We analyze the patient's general information, clinical characteristics, related medical history, laboratory indicators, breast magnetic resonance imaging examination, postoperative pathology, prognosis, etc. Results: The clinical manifestations of NPM in adolescents mainly included redness, swelling and pain in the breasts, congenital nipple retraction, and extensive lesion range. Inflammatory markers and prolactin were elevated. Magnetic resonance imaging showed circular enhancement with abscess formation as the main type. All patients underwent surgical treatment with a fast recovery time after surgery. No recurrence was observed during follow-up and the postoperative breast appearance was satisfactory. Multivariate Logistic regression analysis indicated that congenital nipple retraction, elevated prolactin levels and trauma were independent risk factors for adolescents non-puerperal mastitis. Conclusion: Adolescent non-puerperal mastitis is a rare and unique type. Summarizing its main risk factors, clinical characteristics, and prognosis provides a basis for further research.

LC/MS-based untargeted lipidomics reveals lipid signatures of nonpuerperal mastitis.

BACKGROUND: Nonpuerperal mastitis (NPM) is a disease that presents with redness, swelling, heat, and pain during nonlactation and can often be confused with breast cancer. The etiology of NPM remains elusive; however, emerging clinical evidence suggests a potential involvement of lipid metabolism. METHOD: Liquid chromatography‒mass spectrometry (LC/MS)-based untargeted lipidomics analysis combined with multivariate statistics was performed to investigate the NPM lipid change in breast tissue. Twenty patients with NPM and 10 controls were enrolled in this study. RESULTS: The results revealed significant differences in lipidomics profiles, and a total of 16 subclasses with 14,012 different lipids were identified in positive and negative ion modes. Among these lipids, triglycerides (TGs), phosphatidylethanolamines (PEs) and cardiolipins (CLs) were the top three lipid components between the NPM and control groups. Subsequently, a total of 35 lipids were subjected to screening as potential biomarkers, and the chosen lipid biomarkers exhibited enhanced discriminatory capability between the two groups. Furthermore, pathway analysis elucidated that the aforementioned alterations in lipids were primarily associated with the arachidonic acid metabolic pathway. The correlation between distinct lipid populations and clinical phenotypes was assessed through weighted gene coexpression network analysis (WGCNA). CONCLUSIONS: This study demonstrates that untargeted lipidomics assays conducted on breast tissue samples from patients with NPM exhibit noteworthy alterations in lipidomes. The findings of this study highlight the substantial involvement of arachidonic acid metabolism in lipid metabolism within the context of NPM. Consequently, this study offers valuable insights that can contribute to a more comprehensive comprehension of NPM in subsequent investigations. TRIAL REGISTRATION: Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine (Number: 2019-702-57; Date: July 2019).