Reporting on the Value of Artificial Intelligence in Predicting the Optimal Embryo for Transfer: A Systematic Review including Data Synthesis

Abstract

Artificial intelligence (AI) has been gaining support in the field of in vitro fertilization (IVF). Despite the promising existing data, AI cannot yet claim gold-standard status, which serves as the rationale for this study. This systematic review and data synthesis aims to evaluate and report on the predictive capabilities of AI-based prediction models regarding IVF outcome. The study has been registered in PROSPERO (CRD42021242097). Following a systematic search of the literature in Pubmed/Medline, Embase, and Cochrane Central Library, 18 studies were identified as eligible for inclusion. Regarding live-birth, the Area Under the Curve (AUC) of the Summary Receiver Operating Characteristics (SROC) was 0.905, while the partial AUC (pAUC) was 0.755. The Observed: Expected ratio was 1.12 (95%CI: 0.26–2.37; 95%PI: 0.02–6.54). Regarding clinical pregnancy with fetal heartbeat, the AUC of the SROC was 0.722, while the pAUC was 0.774. The O:E ratio was 0.77 (95%CI: 0.54–1.05; 95%PI: 0.21–1.62). According to this data synthesis, the majority of the AI-based prediction models are successful in accurately predicting the IVF outcome regarding live birth, clinical pregnancy, clinical pregnancy with fetal heartbeat, and ploidy status. This review attempted to compare between AI and human prediction capabilities, and although studies do not allow for a meta-analysis, this systematic review indicates that the AI-based prediction models perform rather similarly to the embryologists’ evaluations. While AI models appear marginally more effective, they still have some way to go before they can claim to significantly surpass the clinical embryologists’ predictive competence.

Which sperm parameter limits could really guide the clinical decision in assisted reproduction?

“…In this setting, using a large dataset of real‐world data collected in clinical practice, we confirm the predictive role of sperm parameters for ART success 27 . Many works have been published so far to determine potential predictors of ART outcomes, even applying artificial intelligence 35,36 . However, also the innovative and complex artificial intelligence‐based prediction model performs rather similarly to clinicians’ evaluations, 35 not providing in fact additional useful predictive tools.…”

“…Many works have been published so far to determine potential predictors of ART outcomes, even applying artificial intelligence 35,36 . However, also the innovative and complex artificial intelligence‐based prediction model performs rather similarly to clinicians’ evaluations, 35 not providing in fact additional useful predictive tools. Here, combining fresh and frozen cycles, we confirm once again that the male partner must be considered in couple infertility management 10,18,37,38 .…”

Criteria for implementing artificial intelligence systems in reproductive medicine

“…Different authors have expressed their thoughts on whether or not to implement predictive AI models into the daily practice [59][60][61]. From my point of view, it is worth considering implementing an algorithm if its result is robust enough to answer the initial question of the requirement.…”

Exploring the Role of Explainability in AI-Assisted Embryo Selection

“…[20]. The most ambitious tasks, those of predicting clinical pregnancy or fetal heartbeat from five days old fertilized embryo images, are reviewed in [23], together with the ploidy status (number of chromosomes) prediction task. [26] includes the annotation of data (e.g., development phase, cell counting) in its review, while the particularities of the time-lapse imaging are the focus of [28].…”