ABSTRACT
BACKGROUND: In the realm of in vitro fertilization (IVF), artificial intelligence (AI) models serve as invaluable tools for clinicians, offering predictive insights into ovarian stimulation outcomes. Predicting and understanding a patient's response to ovarian stimulation can help in personalizing doses of drugs, preventing adverse outcomes (eg, hyperstimulation), and improving the likelihood of successful fertilization and pregnancy. Given the pivotal role of accurate predictions in IVF procedures, it becomes important to investigate the landscape of AI models that are being used to predict the outcomes of ovarian stimulation. OBJECTIVE: The objective of this review is to comprehensively examine the literature to explore the characteristics of AI models used for predicting ovarian stimulation outcomes in the context of IVF. METHODS: A total of 6 electronic databases were searched for peer-reviewed literature published before August 2023, using the concepts of IVF and AI, along with their related terms. Records were independently screened by 2 reviewers against the eligibility criteria. The extracted data were then consolidated and presented through narrative synthesis. RESULTS: Upon reviewing 1348 articles, 30 met the predetermined inclusion criteria. The literature primarily focused on the number of oocytes retrieved as the main predicted outcome. Microscopy images stood out as the primary ground truth reference. The reviewed studies also highlighted that the most frequently adopted stimulation protocol was the gonadotropin-releasing hormone (GnRH) antagonist. In terms of using trigger medication, human chorionic gonadotropin (hCG) was the most commonly selected option. Among the machine learning techniques, the favored choice was the support vector machine. As for the validation of AI algorithms, the hold-out cross-validation method was the most prevalent. The area under the curve was highlighted as the primary evaluation metric. The literature exhibited a wide variation in the number of features used for AI algorithm development, ranging from 2 to 28,054 features. Data were mostly sourced from patient demographics, followed by laboratory data, specifically hormonal levels. Notably, the vast majority of studies were restricted to a single infertility clinic and exclusively relied on nonpublic data sets. CONCLUSIONS: These insights highlight an urgent need to diversify data sources and explore varied AI techniques for improved prediction accuracy and generalizability of AI models for the prediction of ovarian stimulation outcomes. Future research should prioritize multiclinic collaborations and consider leveraging public data sets, aiming for more precise AI-driven predictions that ultimately boost patient care and IVF success rates.
Subject(s)
Artificial Intelligence , Fertilization in Vitro , Ovulation Induction , Humans , Ovulation Induction/methods , Fertilization in Vitro/methods , Female , PregnancyABSTRACT
PURPOSE: This study assessed the visibility of embryologists on fertility clinic websites among Society for Assisted Reproductive Technology (SART) and the Human Fertilisation and Embryology Authority (HFEA) member clinics. METHODS: During a 1-month interval (March 2022), all Society for Assisted Reproductive Technology (SART) and the Human Fertilisation and Embryology Authority (HFEA) member fertility clinic websites were evaluated. The professional representation of the primary care team was examined including specialties, the presence of headshots, and biographies. RESULTS: A total of 446 fertility clinic websites were scanned in the search. The embryology team has the least common professional identification by their names (53.58%) compared to gynecology clinicians (96.21%, p < 0.001) and nurses (55.58%, p < 0.001). This trend also applies to other types of professional identifiers, such as headshots and biographies. Professional headshots of embryologists (50.34%) were less prominent than those of gynecology clinicians (93.51%, p < 0.001). A similar trend was observed in the biographies of the embryology team (47.20%) compared to gynecology clinicians (95.08%, p < 0.001). CONCLUSION: The present study revealed that embryologists have low professional visibility on fertility clinic websites. Fertility clinics may prioritize enhancing the online visibility of their embryology laboratory team. This approach could potentially enhance the recognition of their team, foster transparency, and provide accessible information about the skills and expertise of healthcare professionals involved in the treatment process.
Subject(s)
Fertility Clinics , Gynecology , Humans , Cross-Sectional Studies , Reproductive Techniques, Assisted , InternetABSTRACT
BACKGROUND: The potential of COVID-19 severe pandemic necessitates the development of an organized and well-reasoned plan for the management of embryology/andrology laboratories while safeguarding the wellbeing of patients and IVF staff. MAIN BODY: A COVID-19 pandemic response plan was proposed for embryology and andrology laboratories for pre-pandemic preparedness and pandemic management in anticipation of a possible second coronavirus wave. Preparation involves many plans and logistics before a pandemic risk rises. Many operational changes can be considered during the pandemic. This plan includes logistical arrangements, reducing labor needs, conserving supplies, and protective measures for embryologists and gametes/embryos. CONCLUSION: The unpredictable emergence of the COVID-19 pandemic dictates the need for a preparedness plan for embryology/andrology laboratories, which includes an action-oriented plan to secure the safety of all stakeholders.