Scholarlink

Importance <p>Assisted Reproductive Technologies have been developed to address infertility by improving embryo selection. Artificial intelligence (AI), using Time-Lapse Imaging, enhances predictions from fertilization to the blastocyst stage.</p> Objective <p>Studies show that AI can identify suitable embryos more effectively than specialists. It improves IVF success rates by enhancing embryo transfer success and reducing miscarriage risks. With IVF success rates below 40%, it is essential to explore AI methods to boost outcomes.</p> Findings <p>A systematic review in October 2024 searched databases like PubMed and Scopus using terms related to IVF and AI, excluding non-English and qualitative studies. Twenty-seven studies were reviewed; 17 predicted treatment responses with deep learning. Two studies used neural networks for successful treatment prediction, and eight employed ML methods such as NB, SVM, and RF, with an average AUC of 0.91. Models showed 90–96% accuracy, sensitivity, and precision.</p> Conclusion <p>AI technologies, particularly NB and Reinforcement Learning, show promise in improving IVF outcomes by enhancing classification and diagnosis while saving time. Interdisciplinary approaches using micro and Nano-biotechnology can help overcome clinical challenges.</p> Relevance <p>Examining the quality of sperm and egg separately using AI could further improve fertility testing and success in ART, optimizing clinical results.</p>

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

Investigating artificial intelligence in predicting and evaluating sperm and embryo quality in the in vitro fertilization (IVF): a systematic review

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月29日

查看全文
  • Shahrzad kaveh,
  • Aida Ghaffari,
  • Solmaz Sohrabei

摘要

Importance

Assisted Reproductive Technologies have been developed to address infertility by improving embryo selection. Artificial intelligence (AI), using Time-Lapse Imaging, enhances predictions from fertilization to the blastocyst stage.

Objective

Studies show that AI can identify suitable embryos more effectively than specialists. It improves IVF success rates by enhancing embryo transfer success and reducing miscarriage risks. With IVF success rates below 40%, it is essential to explore AI methods to boost outcomes.

Findings

A systematic review in October 2024 searched databases like PubMed and Scopus using terms related to IVF and AI, excluding non-English and qualitative studies. Twenty-seven studies were reviewed; 17 predicted treatment responses with deep learning. Two studies used neural networks for successful treatment prediction, and eight employed ML methods such as NB, SVM, and RF, with an average AUC of 0.91. Models showed 90–96% accuracy, sensitivity, and precision.

Conclusion

AI technologies, particularly NB and Reinforcement Learning, show promise in improving IVF outcomes by enhancing classification and diagnosis while saving time. Interdisciplinary approaches using micro and Nano-biotechnology can help overcome clinical challenges.

Relevance

Examining the quality of sperm and egg separately using AI could further improve fertility testing and success in ART, optimizing clinical results.