Mammography is considered the gold standard for breast cancer screening. Multiple risk factors that affect breast cancer development have been identified; however, there is an ongoing debate regarding the significance of these factors. Machine learning (ML) models and Shapley Additive Explanation (SHAP) methodology can rank risk factors and provide explanatory model results. This study used ML algorithms with SHAP to analyze the risk factors between two different age groups and evaluate the impact of each factor in predicting positive mammography. The ML model was built using data from the risk factor questionnaires of women participating in a breast cancer screening program from 2017 to 2021. Three ML models, least absolute shrinkage and selection operator (lasso) logistic regression, extreme gradient boosting (XGBoost), and random forest (RF), were applied. RF generated the best performance. The SHAP values were then applied to the RF model for further analysis. The model identified age at menarche, education level, parity, breast self-examination, and BMI as the top five significant risk factors affecting mammography outcomes. The differences between age groups ranked by reproductive lifespan and BMI were higher in the younger and older age groups, respectively. The use of SHAP frameworks allows us to understand the relationships between risk factors and generate individualized risk factor rankings. This study provides avenues for further research and individualized medicine.

Although gastric polyp is usually an incidental endoscopic finding, large-sized polyps can cause symptoms ranging from epigastralgia to bleeding from ulcerated polyps and gastric outlet obstruction. Although the gold standard of treatment is removal of the polyp either through endoscopic polypectomy or surgical excision, complications associated with these procedures cannot be ignored. The risk becomes a major concern for patients at high risk for surgery when complications arise. We describe a debilitated 74-year-old woman who presented with early satiety, intermittent postprandial nausea and vomiting for three months. Upper endoscopy revealed a 2.5 cm pedunculated polyp over the gastric antrum causing intermittent obstruction. Considering her high risk for polypectomy, detachable snaring was performed without polypectomy in an outpatient setting. The patient was complication-free with complete relief of obstructive symptoms one week after the procedure. Subsequent follow-ups showed satisfactory healing without signs of mucosal disruption or recurrence. The results suggest that detachable snaring without polypectomy may be a therapeutic option for high-risk patients with benign symptomatic gastric polyps.

This study aimed to investigate the important predictors related to predicting positive mammographic findings based on questionnaire-based demographic and obstetric/gynecological parameters using the proposed integrated machine learning (ML) scheme. The scheme combines the benefits of two well-known ML algorithms, namely, least absolute shrinkage and selection operator (Lasso) logistic regression and extreme gradient boosting (XGB), to provide adequate prediction for mammographic anomalies in high-risk individuals and the identification of significant risk factors. We collected questionnaire data on 18 breast-cancer-related risk factors from women who participated in a national mammographic screening program between January 2017 and December 2020 at a single tertiary referral hospital to correlate with their mammographic findings. The acquired data were retrospectively analyzed using the proposed integrated ML scheme. Based on the data from 21,107 valid questionnaires, the results showed that the Lasso logistic regression models with variable combinations generated by XGB could provide more effective prediction results. The top five significant predictors for positive mammography results were younger age, breast self-examination, older age at first childbirth, nulliparity, and history of mammography within 2 years, suggesting a need for timely mammographic screening for women with these risk factors.

Gastric hemangiomas (GHs) are extremely rare vascular lesions of mesodermal origin that may occur in isolation or in conjunction with underlying congenital pathology. Due to the scarcity of these tumors, there is no standardized diagnostic method; however, many have found the combination of endoscopic investigation and radiographic imaging to be most effective, with the presence of phleboliths on computerized tomography as being pathognomonic for GHs. Surgical treatment for symptomatic lesions is curative with no reports of recurrence. We describe a 21-year-old woman who presented with epigastric pain and one episode of 250 mL hematemesis earlier that morning. Under the impression of an upper gastrointestinal bleed due to peptic ulcer disease, esophagogastroduodenoscopy was performed which revealed a 5-cm blood clot-like mass similar in appearance to that of a II-b peptic ulcer, but the presence of a bridging fold led to the suspicion of a possible submucosal tumor. Dynamic computerized tomography scan showed similar findings, and the patient was referred for surgical intervention. Laparoscopic distal gastrectomy was performed with the final diagnosis of cavernous GH made via histological evaluation. The patient was discharged 9 days later with no complications. This case puts emphasis on the importance of considering cavernous GH as a potential cause of severe upper GI bleeding especially in those with atypical demographic profile and history.

Portal vein aneurysms are rare vascular malformations with unclear etiologies and optimal treatment guidelines. Although Doppler ultrasonography is the most commonly used diagnostic tool, there is no gold standard imaging modality. Despite recommendations of surgical treatment for symptomatic aneurysms, there are limited options in the management of portal vein aneurysm-related complications in patients unfit for surgical intervention. We describe an 85-year-old man who presented with abdominal pain and low-grade fever with clinical signs consistent with cholangitis. Endoscopic retrograde cholangiopancreatography revealed a common hepatic duct stricture and concomitant intraductal ultrasonography identified adjacent aneurysmal portal vein dilatation. The final diagnosis of portal vein aneurysm was made using contrast computerized tomography scan. The patient was considered unsuitable for surgery due to his advanced age and multiple comorbidities. Instead, an endoscopic biliary plastic stent was inserted as a therapeutic alternative, which successfully achieved complete resolution of symptoms 3 days after the procedure. The patient was regularly followed at the outpatient clinic with repeated stent replacements every 3 to 4 months. After a follow-up of over 3.5 years, the patient remained symptom-free without signs of portal vein aneurysm compression. The result suggests that repeated stent replacements may be a therapeutic option for biliary compression by portal vein aneurysm in patients contraindicated for surgical intervention.