Publication:

Artificial intelligence-enhanced in-vitro fertilization outcome prediction for the Indian subpopulation: integrating pre-treatment parameters and Bayesian-optimized ensemble techniques

Background In-vitro fertilization (IVF) outcomes, particularly their socioeconomic impact, are a major concern for Indian couples. Predicting success using pre-treatment parameters can improve clinical decision-making. This study develops and validates Bayesian-optimized voting-ensemble (BoVe), a novel machine learning (ML) algorithm, to enhance predictive accuracy for live birth outcomes.

Methods Clinical records from 2,908 IVF patients, encompassing 79 parameters-including maternal age, body mass index (BMI), Anti-Mullerian hormone (AMH) levels, number of IVF cycles, infertility type, and sperm parameters were analyzed following rigorous data preprocessing. The dataset was cleaned, transformed, and split 80:20 for training and validation. BoVe was evaluated against traditional ML models based on key performance metrics.

Results BoVe identified AMH levels >3.5 ng/mL, BMI <23, and maternal age <35 as strong predictors of live birth in female patients. Male sperm parameters significantly influenced success rates. Compared to conventional ML models, BoVe achieved superior predictive performance with an ROC-AUC score of 0.93 and accuracy of 0.87, demonstrating robust effectiveness. Additionally, an AI-powered web application was developed for cloud-based fertility guidance, providing personalized recommendations based on patient parameters.

Conclusions The BoVe model offers a highly accurate, population-specific approach to IVF prediction, surpassing previously published algorithms. Its integration into clinical workflows can enhance pre-treatment counseling, empower couples with data-driven reproductive insights, and improve success rates through personalized interventions.