Machine learning for predicting elective fertility preservation outcomes.

This retrospective study applied machine-learning models to predict treatment outcomes of women undergoing elective fertility preservation. Two-hundred-fifty women who underwent elective fertility preservation at a tertiary center, 2019-2022 were included. Primary outcome was the number of metaphase II oocytes retrieved. Outcome class was based on oocyte count (OC): Low (≤ 8), Medium (9-15) or High (≥ 16). Machine-learning models and statistical regression were used to predict outcome class, first based on pre-treatment parameters, and then using post-treatment data from ovulation-triggering day. OC was 136 Low, 80 Medium, and 34 High. Random Forest Classifier (RFC) was the most accurate model (pre-treatment receiver operating characteristic (ROC) area under the curve (AUC) was 77%, and post-treatment ROC AUC was 87%), followed by XGBoost Classifier (pre-treatment ROC AUC 74%, post-treatment ROC AUC 86%). The most important pre-treatment parameters for RFC were basal FSH (22.6%), basal LH (19.1%), AFC (18.2%), and basal estradiol (15.6%). Post-treatment parameters were estradiol levels on trigger-day (17.7%), basal FSH (11%), basal LH (9%), and AFC (8%). Machine-learning models trained with clinical data appear to predict fertility preservation treatment outcomes with relatively high accuracy.

Long-Term Matched Comparison of Primary and Revisional Laparoscopic Sleeve Gastrectomy.

BACKGROUND: Reports of long-term (> 5-15-year) outcomes assessing the safety and efficacy of primary revisional laparoscopic sleeve gastrectomy (LSG) are few. METHODS: Retrospective long-term comparisons of primary (pLSG) and revisional (rLSG) procedures were matched for gender, age ± 5 years, and body mass index (BMI) ± 5 kg/m2. Weight loss, associated medical condition status, and patient satisfaction were evaluated. RESULTS: Between May 1, 2006, and December 31, 2016, 194 matched patients with severe obesity (mean BMI 44.1 ± 6.7 kg/m2; age 44.2 ± 10.0 years, 67.0% female) underwent pLSG (n = 97) or rLSG (n = 97) and were followed for a mean 12.1 ± 1.5 vs 7.6 ± 2.1 years. Respective mean weight regain from nadir was 15.0 ± 14.4 kg vs 11.9 ± 12.2 kg. Respective percent mean total weight loss and excess weight loss were 20.9 ± 12.7% and 51.8 ± 33.1%, and 18.3 ± 12.8% and 43.4 ± 31.6% at last follow-up, with no significant difference between groups. Resolution of type 2 diabetes (HbA1C < 6.5%, off medications) was 23.1% vs 11.1%; hypertension 36.0% vs 16.0%; and hyperlipidemia 37.1% vs 35.3%. Patients in the pLSG group were significantly more satisfied with LSG (59.8% vs 43.3%, p < 0.05) and more likely to choose the procedure again. CONCLUSIONS: There were no significant differences in long-term weight loss or associated medical condition outcomes in matched pLSG and rLSG patients.

Long-term Reported Outcomes Following Primary Laparoscopic Sleeve Gastrectomy.

BACKGROUND: Long-term laparoscopic sleeve gastrectomy (LSG) outcomes in patients with obesity are scarce. We aimed to examine the outcomes and subjective experience of patients who underwent primary LSG with long-term follow-up. METHODS: The study is a retrospective observational analysis of patients who underwent primary LSG in a single center with 5-15 years of follow-up. Patients' hospital chart data supplemented by a detailed follow-up online questionnaire and telephone interview were evaluated. RESULTS: The study sample included 578 patients (67.0% female) with 8.8 ± 2.5 years of mean follow-up, with a response rate to the survey of 82.8%. Mean baseline age and body mass index (BMI) were 41.9 ± 10.6 years and 42.5 ± 5.5 kg/m2, respectively. BMI at nadir was 27.5 ± 4.9 kg/m2, corresponding to a mean excess weight loss (EWL) of 86.9 ± 22.8%. Proportion of patients with weight regain, defined as nadir ≥ 50.0% EWL, but at follow-up < 50.0% EWL, was 34.6% (n = 200) and the mean weight regain from nadir was 13.3 ± 11.1 kg. BMI and EWL at follow-up were 32.6 ± 6.4 kg/m2 and 58.9 ± 30.1%, respectively. The main reasons for weight regain given by patients included "not following guidelines," "lack of exercise," "subjective impression of being able to ingest larger quantities of food in a meal," and "not meeting with the dietitian." Resolution of obesity-related conditions at follow-up was reported for hypertension (51.7%), dyslipidemia (58.1%) and type 2 diabetes (72.2%). The majority of patients (62.3%) reported satisfaction with LSG. CONCLUSIONS: In the long term, primary LSG was associated with satisfactory weight and health outcomes. However, weight regain was notable.