Scholarlink

In recent years, advancements in deep learning have significantly improved medical predictions, including in the field of assisted reproductive technology (ART). This study explores the application of the ALEXNET deep learning model for predicting in vitro fertilization (IVF) success rates. By utilizing a dataset comprising patient medical histories, embryonic development parameters, and clinical factors, the model learns complex patterns associated with successful implantation and pregnancy outcomes. The ALEXNET architecture, originally designed for image classification, is adapted to analyze embryo images and relevant clinical data, enhancing predictive accuracy. Experimental results demonstrate that the proposed approach outperforms traditional statistical and machine learning models, offering a robust tool for personalized IVF outcome predictions. This research contributes to improving fertility treatment success rates by assisting clinicians in making data-driven decisions, ultimately increasing the likelihood of positive patient outcomes.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

IVF Success Rate Prediction Using Deep Learning Model LSTM and ALEXNET

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Vishva Pragneshbhai Padariya,
  • Vipul Vekariya,
  • Chintan Thacker

摘要

In recent years, advancements in deep learning have significantly improved medical predictions, including in the field of assisted reproductive technology (ART). This study explores the application of the ALEXNET deep learning model for predicting in vitro fertilization (IVF) success rates. By utilizing a dataset comprising patient medical histories, embryonic development parameters, and clinical factors, the model learns complex patterns associated with successful implantation and pregnancy outcomes. The ALEXNET architecture, originally designed for image classification, is adapted to analyze embryo images and relevant clinical data, enhancing predictive accuracy. Experimental results demonstrate that the proposed approach outperforms traditional statistical and machine learning models, offering a robust tool for personalized IVF outcome predictions. This research contributes to improving fertility treatment success rates by assisting clinicians in making data-driven decisions, ultimately increasing the likelihood of positive patient outcomes.