Lantzi Myrto A, Papakonstantinou Eleni, Vlachakis Dimitrios
Laboratory of Genetics, Department of Biotechnology, School of Applied Biology and Biotechnology, Agricultural University of Athens, 11855 Athens, Greece.
University Research Institute of Maternal and Child Health and Precision Medicine, School of Medicine, National and Kapodistrian University of Athens, 11527 Athens, Greece.
Biology (Basel). 2025 May 16;14(5):556. doi: 10.3390/biology14050556.
Since its inception in 1987, in vitro fertilization (IVF) has constituted a significant medical achievement in the field of fertility treatment, offering a viable solution to the challenge of infertility. The continuous evolution of assisted reproductive technology (ART) has brought its relationship with the rapidly developing field of artificial intelligence (AI), in particular with techniques such as machine learning (ML), a rapidly evolving area of specialization. In fact, it is responsible for significant developments in the field of precision medicine, as well as in preventive and predictive medicine. The analysis focuses on a large volume of clinical data and patient characteristics of those who underwent assisted reproduction treatments. Concurrently, the utilization of machine learning algorithms has facilitated the development and implementation of predictive models. The objective is to predict the success of treatments for external fertilization based on processed clinical data. This study encompasses statistical analysis techniques and artificial intelligence algorithms for the correlation of variables, such as patient characteristics, the history of pregnancies, and the clinical and embryological parameters. The analysis and creation of prognostic models were compared with the objective of identifying factors that influence the outcome of IVF treatments. The potential for implementing a predictive model in routine clinical practice was also investigated. The findings revealed trends and factors that warrant attention. Such findings may prompt questions regarding the impact of the patient's age on treatment efficacy. Moreover, the value of developing a predictive model based entirely on patient data prior to the commencement of treatment was also investigated. This approach to the processing and utilization of clinical data demonstrates the potential for optimization and documentation of therapeutic procedures. The objective is to reduce costs and the emotional burden while increasing the success rate of IVF treatments.
自1987年体外受精（IVF）诞生以来，它已成为生育治疗领域一项重大的医学成就，为不孕不育这一难题提供了可行的解决方案。辅助生殖技术（ART）的不断发展使其与迅速发展的人工智能（AI）领域建立了联系，特别是与机器学习（ML）等技术，这是一个快速发展的专业领域。事实上，它推动了精准医学领域以及预防和预测医学的重大发展。该分析聚焦于大量接受辅助生殖治疗者的临床数据和患者特征。同时，机器学习算法的应用促进了预测模型的开发与实施。目的是基于处理后的临床数据预测体外受精治疗的成功率。本研究涵盖了用于变量相关性分析的统计分析技术和人工智能算法，这些变量包括患者特征、妊娠史以及临床和胚胎学参数。对预后模型的分析和创建进行了比较，目的是确定影响IVF治疗结果的因素。还研究了在常规临床实践中实施预测模型的潜力。研究结果揭示了值得关注的趋势和因素。这些发现可能会引发关于患者年龄对治疗效果影响的问题。此外，还研究了在治疗开始前完全基于患者数据开发预测模型的价值。这种处理和利用临床数据的方法展示了优化治疗程序和记录的潜力。目的是降低成本和减轻情感负担，同时提高IVF治疗的成功率。
