Background and Objectives: Hospital length of stay (LOS) after breast cancer surgery is a key indicator of postoperative recovery, healthcare quality, and hospital resource utilization. Traditional statistical approaches have identified general correlates of LOS but remain limited in predictive accuracy, particularly in heterogeneous real-world surgical populations. Machine learning (ML) models may offer improved performance by capturing nonlinear interactions among clinical, pathological, and operative factors. This study aimed to evaluate ML algorithms for LOS prediction and to identify determinants of prolonged hospitalization in a contemporary breast cancer cohort. Materials and Methods: We conducted a retrospective cross-sectional study of 198 consecutive breast cancer patients who underwent surgery between January 2022 and December 2023 at a single tertiary care center. Clinical, pathological, and surgical data were extracted from electronic medical records. Three regression models—multiple linear regression, Random Forest, and Gradient Boosting—were trained to predict continuous LOS, and three classification models were applied to prolonged LOS (≥10 days). Model performance was assessed using mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R²), and area under the curve (AUC). Feature importance was analyzed for the best-performing model. Results: The median LOS was 7 days (IQR 5–10), ranging from 1 to 26 days. Breast-conserving surgery showed the shortest LOS (median 3 days), while mastectomy with immediate reconstruction resulted in the longest stays (median 8 days). Random Forest regression achieved the lowest prediction error (MAE 2.31 days; RMSE 2.82; R² = 0.37), outperforming Gradient Boosting and substantially surpassing linear regression (MAE 8.63 days; R² = –8.17). Key predictors included age, surgical complexity, reconstruction modality, BMI, implant capacity, and tumor burden. Classification models yielded modest AUCs (0.545–0.589) with low sensitivity, indicating limited discriminative performance for dichotomized LOS outcomes. Conclusions: Machine-learning models, particularly Random Forest, substantially improve LOS prediction compared with classical regression and provide clinically meaningful insights into the drivers of hospitalization after breast cancer surgery. Continuous LOS modeling is more informative than binary thresholds. These findings support integrating ML-based tools into perioperative planning, resource allocation, and patient counseling in breast surgical care.

Objectives. Up to 20% of patients with biliary lithiasis have bile duct stones, which are asymptomatic in 50% of cases. The aim of the study was to evaluate the role of choledoscopy in extracting stones from the main bile ducts. Materials and Methods. This is a retrospective study (January 2014–December 2024) on 2309 patients who underwent a laparoscopic cholecystectomy. Laparoscopic choledoscopy was performed in 32 cases. Of the 32 patients with complete clearance, none had residual common bile duct stones (CBDS) at 1 year postoperatively. Results. The ideal approach in our study was the transcystic approach, with the shortest hospital stays (mean 3 days) transcholedochal approach; it was only feasible in 7 patients. All patients had transcystic drainage that was removed after 10 days (mean operative time 105 min). The transcholedochal approach was demanding from a technical point of view. Primary ductal closure was performed in 5 patients. Ductal closure with transcystic drain was in 9 patients. A total of 14 patients had a T-tube and a longer operative time (on average 170 min). Conversion to open surgery was performed in 4 cases, due to difficult dissection at the level of the hepatic porta. Conclusions. LCBDE for previously documented or discovered CBDS during LC is a safe and feasible procedure. The technique is technically demanding, and requires advanced laparoscopic skills. Patient selection is very important, but the transcystic approach for LCBDE when possible is optimal.

Background: Multinodular goiter (MNG) is a common thyroid condition characterized by multiple nodules within the thyroid gland. This study aims to evaluate the incidence and clinical features of occult thyroid carcinoma in patients with multinodular goiter, based on the experience from a medium-volume cancer center. Methods: A retrospective analysis was conducted on patients diagnosed with multinodular goiter who underwent thyroidectomy. Clinical, radiological, and histopathological data were reviewed to identify cases of occult thyroid carcinoma. Factors such as age, sex, and histopathological characteristics were analyzed to determine potential risk factors for malignancy in this cohort. Results: A total of 332 patients with MNG were included in the study, with 61 (17.5%) diagnosed with occult thyroid carcinoma. The incidence of occult carcinoma was more frequent in females, with a notable predilection for papillary carcinoma. Regarding age, occult tumors were more frequently encountered in the 20–40 age group, irrespective of gender. Conclusions: In conclusion, we observed that in our center over a 6-year period, the incidence of thyroid cancer after total thyroidectomy for multinodular goiter sits at 17.5%. Thyroid diseases are more frequent in women, which in turn leads to an increased rate of occult carcinomas. Up to 70% of the cancers were papillary. The clinical risk factors associated with a higher probability of cancer were lower age and female gender.