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.

Congenital Herpes simplex virus (HSV) infection is considered a common pregnancy pathology that is not always easy to diagnose. This study aimed to present the spectrum of placental histopathological lesions in pregnancies complicated by HSV infection. MEDLINE and Google Scholar databases were searched using the keywords "HSV" and "placental histopathology" up to June 20, 2022. Study inclusion required presenting placental histopathological anomalies in pregnant women diagnosed with HSV infection antenatally, during labor, or postnatally. Herein, we briefly present placental pathogenesis conditions, which have been correlated with congenital HSV infection, providing clinicians with a short review describing herpetic placental pathology.

Study question Could microRNA dysregulation be an underlying molecular mechanism leading to the observed increased prevalence of cancer in patients with Sertoli-cell only syndrome (SCOS)? Summary answer Patients with SCOS are characterized by altered microRNA profiles and dysregulated gene pathways involved in SCOS pathophysiology and in cell-cycle control and therefore in carcinogenesis. What is known already Sertoli cell-only syndrome constitutes a histopathological subtype of non-obstructive azoospermia, affecting 26.3–57.8% of azoospermia patients. It is characterized by partial or complete absence of active spermatogenesis due to germ cell aplasia. Except from infertility, SCOS is associated with increased risk of testicular nodules and cancer, rendering research on the topic essential. Despite advances, the underlying molecular mechanisms connecting SCOS with cancer remain unknown. Data demonstrates that microRNAs could play crucial roles in both SCOS pathophysiology and carcinogenesis. Identifying relevant microRNAs and conducting in-silico analysis on affected pathways may lead to mapping the way forward. Study design, size, duration A systematic review was performed in PubMed/Medline and Embase up to April 2022. Only full-length original studies in humans were included. Strict inclusion-exclusion criteria were applied aiming to select studies comparing microRNA profiling between SCOS cases versus men with normal spermatogenesis or men with proven fertility. Following study selection, data on altered microRNA expression patterns were analyzed to underline differences between the abovementioned groups. Subsequently, in-silico functional analysis was performed to compare affected gene pathways. Participants/materials, setting, methods The studied population consisted of SCOS cases. Men with normal spermatogenesis or proven fertility served as the control group. Predicted microRNA–target pairs were retrieved from microT-CDS, while a 0.8 cutoff threshold was applied. The GTEx repository was used to identify microRNA-targeted genes in the testis. Annotations derived from Ensembl and miRbase. Gene-set enrichment analysis was performed employing the KEGG-database. Fisher’s exact test was performed in R package limma, setting a 0.01 p-value threshold. Main results and the role of chance Four studies reported altered microRNA expression profiles in SCOS (n = 45) versus normal spermatogenesis cases or men of proven fertility (n = 16). Functional analysis revealed that six microRNAs, which were downregulated in the SCOS cases, namely hsa-miR-34b-5p, hsa-miR-202-3p, hsa-miR-34c-5p, hsa-miR-449a, hsa-miR-141-3p, and hsa-miR-34b-3p, affected 66 statistically significant gene-targets in the testis. Two pathways were reported to be statistically significantly dysregulated from these microRNAs, namely the ‘’microRNAs in cancer’’ pathway (40 affected genes, p-value  =  0.004), and the ‘’TGF-beta signaling’’ pathway (26 affected genes, p-value  =  0.01). Furthermore, four microRNAs, namely hsa-miR-10b-5p, hsa-miR-4270, hsa-miR-181c-5p, and hsa-miR-605-3p, reported to be upregulated in the SCOS group. These microRNAs had 108 statistically significant gene-targets in the testis. Three pathways were statistically significantly dysregulated from these microRNAs, namely the ‘’Herpes simplex virus 1 infection’’ pathway (61 affected genes, p-value  =  0.01), the ‘’microRNAs in cancer’’ pathway (28 affected genes, p-value  =  0.01), and the ‘’longevity regulating’’ pathway (19 affected genes, p-value  =  0.01). The molecular role of the affected gene pathways in proper cell-cycle regulation and germ cell differentiation is herein underlined as critical. In the disrupted testicular microenvironment of the SCOS cases these disrupted genes may act as inducers of carcinogenic mechanisms. Limitations, reasons for caution The main limitation is the small number of the included studies and the small number of participants investigated per study, especially with regards to the control group. Moreover, the observed heterogeneity among the studies regarding the molecular tools employed for the microRNA profiling is another reason for caution. Wider implications of the findings Our data suggest that the dysregulation of microRNAs affecting several gene pathways that control cell-cycle and differentiation may lead to increased cancer risk in SCOS cases. Further studies employing our findings as a starting point will indicate whether microRNA profiling can serve as an effective evaluation tool for cancer predisposition. Trial registration number Not applicable

Study question To investigate the effect of oocyte vitrification on embryo developmental arrest rate accounting for both open and closed systems. Summary answer Open and closed vitrification systems are equally associated with a statistically significant higher embryo developmental arrest rate per MII oocyte vitrified compared to fresh oocytes. What is known already Oocyte cryopreservation has increased in popularity as it enhances women’s reproductive autonomy. Numerous studies have been published evaluating its effectiveness. However, the majority of published evidence commonly include comparisons with the now considered as “outdated” method of slow freezing. Additionally, data principally report on fertilization rates and clinical outcomes. It may be timely and essential to focus strictly on the effect of oocyte vitrification on the developmental potential of the embryo. Further to this, data are lacking on whether employing an open or closed vitrification system may affect the outcome of vitrification. Study design, size, duration A systematic search of the literature was performed in the databases Pubmed/Medline, Embase, and Cochrane Central Library limited to articles published in English up to October 2021. Only studies employing vitrification were included in this meta-analysis. A total of 17 published prospective studies were eligible. The population consists of oocytes that were either vitrified or fresh and subjected to ICSI. A network meta-analysis was performed comparing the type of vitrification system employed and fresh oocytes. Participants/materials, setting, methods The primary outcome measure was developmental arrest rate per MII oocyte vitrified prior to reaching cleavage or blastocyst stage. The secondary outcome measures were fertilization rate per MII oocyte vitrified and developmental arrest rate per 2PN zygote. Further to this, a subgroup analysis was performed according to the stage of developmental arrest. To rank the efficiency between the fresh oocytes and the oocytes vitrified employing the open and closed system, the P-Score was employed. Main results and the role of chance The seventeen studies reporting on the effect of oocyte vitrification on embryo developmental arrest per MII oocyte vitrified, presented with high heterogeneity I2=81%. Vitrified oocytes employing either the open or closed vitrification system presented with a statistically higher embryo developmental arrest rate when compared to fresh oocytes (open-systems:RR:1.16; 95%CI:1.07-1.26; closed-systems:RR:1.19 95%CI:1.06-1.34). No statistically significant difference was observed between the two vitrification systems (open vs closed:RR:0.99;95%CI:0.89-1.10). Subgroup analysis was performed according to the developmental stage of embryo arrest. Similarly to the pooled results, when subgrouping for embryos arresting prior to the cleavage stage, a statistically significant difference on developmental arrest was identified when vitrifying (open-systems:RR:1.44; 95%CI:1.18-1.77; closed-systems:RR:1.51 95%CI:1.12-2.04; 8 studies). However, when subgrouping for embryos arresting prior to the blastocyst stage, no statistically significant difference on developmental arrest was observed when vitrifying (open-systems:RR:1.06; 95%CI:0.98-1.15; closed systems:RR:1.10 95%CI:0.98-1.24; 9 studies). Fertilization rate was significantly lower for vitrified oocytes compared to fresh (open-systems:RR:0.86; 95%CI:0.79-0.93; closed-systems:RR:0.81 95%CI:0.72-0.92), while no statistically significant difference was observed between the two vitrification systems (open vs closed:RR:1.04; 95%CI:0.93-1.16). When comparing developmental arrest rate per 2PN zygote no statistically significant difference was detected between vitrification versus fresh (open-systems:RR:1.01; 95%CI:0.87-1.17; closed-systems:RR:0.98 95%CI:0.78-1.22), or between the two vitrification systems (open vs closed:RR:1.03;95%CI:0.82-1.30). Limitations, reasons for caution The limited number of studies included along with the heterogeneity identified present as limitations of this study. Further studies and especially Randomized Controlled Trials should be conducted in order to evaluate possible effects of oocyte vitrification on embryo development. Wider implications of the findings Oocyte vitrification results to higher developmental arrest rates per oocyte vitrified but not per 2PN zygote. Both vitrification systems perform equally in affecting developmental arrest. The differential expression of miRNAs and cytokinesis-related genes are identified by this systematic review as potential pathways influencing developmental potential following oocyte vitrification. Trial registration number Not applicable

Study question Are Artificial Intelligence (AI) based models effective in robustly predicting in vitro fertilization (IVF) outcome by assessing embryo quality? Summary answer The majority of the AI-based models could provide an accurate prediction regarding live birth, clinical pregnancy, clinical pregnancy with fetal heartbeat and embryo ploidy status. What is known already Precision and consistency in embryo quality evaluation are of paramount importance regarding the outcome of an IVF cycle. Numerous embryo grading and evaluation systems, employing morphological and morphokinetical assessment, have been proposed but without reaching a consensus yet. The main limitation of the aforementioned assessment systems is that they depend on human evaluation, which may be subject to subjectivity and interobserver variation. Thus, automated prediction models may be essential to optimize objectivity and reliability of embryo grading. Artificial neural network models may process microscopy images or time-lapse videos as input to predict the embryos’ potential competency. Study design, size, duration A systematic review and meta-analysis including 18 published studies. The population consists of preimplantation embryos suitable for embryo transfer in IVF/ICSI cycles following employment of an AI-based prediction model. The outcome measures are prediction of live birth, clinical pregnancy, clinical pregnancy with heartbeat and ploidy status. Participants/materials, setting, methods A systematic search of the literature was performed in the databases of Pubmed/Medline, Embase, and Cochrane Central Library limited to articles published in English up to August 2021. The initial search yielded a total of 694 studies with 97 of them being duplicates and other 579 being excluded on the grounds of not fulfilling inclusion criteria. Following full-text screening and citation mining a total of 18 studies were identified to be eligible for inclusion. Main results and the role of chance Four studies reported on prediction of live birth. The sensitivity was 70.6% (95%C.I.: 38.1-90.4%) and specificity was 90.6% (95%C.I.:79.3-96.1%).  The Area Under the Curve (AUC) of the Summary Receiver Operating Characteristics (SROC) curve was 0.905, while the partial AUC (pAUC) was 0.755. Employing the Bayesian approach, the total Observed:Expected ratio (O:E) was 1.12 (95%CI: 0.26–2.37; 95%PI:0.02-6.54). Ten studies reported on prediction of clinical pregnancy. The sensitivity and the specificity were 71% (95%C.I.: 58.1-81.2%) and 62.5% (95%C.I.: 47.4-75.5%) respectively. The AUC was 0.716, while pAUC was 0.693. Moreover, the total O:E ratio was 0.92 (95%CI: 0.61–1.28; 95%PI:0.13-2.43). Eight studies reported on prediction of clinical pregnancy with fetal heartbeat the sensitivity was 75.2% (95%C.I.: 66.8-82%) and the specificity was 55.3% (95%C.I.: 41.2-68.7%). The AUC 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). Four studies reported on the ploidy status of the embryo. The sensitivity and specificity were 59.4% (95%C.I.: 45.0-73.1%) and 79.2% (95%C.I.: 70.1-86.1%) respectively. The AUC was 0.751 and the pAUC was 0.585. The total O:E ratio was 0.86 (95%CI: 0.42 – 1.27; 95%PI: 0.03-1.83). Limitations, reasons for caution The limited number of studies fulfilling inclusion criteria, along with the different designs applied when developing AI models which may lead to increased heterogeneity, stand as limitations. Inclusion of women regardless of their age presents as another limitation, as advanced maternal age has been associated with diminished IVF outcomes. Wider implications of the findings Albeit, our findings support that AI is a highly promising tool in the era of personalized medicine providing precise predictions it does not appear to considerably surpass human prediction capabilities. More studies and more collaborations between the developers are of paramount importance prior to AI becoming the gold standard. Trial registration number Not applicable