P-177 Is AI the future of ART? Key barriers and drivers to AI adoption in clinical practice from the views of 144 fertility professionals

Abstract

Participants/materials, setting, methods: The questionnaire consisted of 28 questions, split into 4 sections: (i) the demographics of the participant, (ii) their knowledge of AI, (iii) current use and (iv) unmet needs towards AI in clinical practice. Perceptions were graded (1:Strongly Against, 2:Against, 3:Neutral, 4:For, 5:Strongly For). Main results and the role of chance: Respondents expressed positive views towards AI in clinical practice as highlighted by fertility professionals having felt more positive towards using 'AI' (average score ¼ 3.9) compared to using 'decision support tools' (3.7,p ¼ 0.002). Most participants had positive/neutral views regarding 'patient confidence towards them when implementing AI decision tools in treatment plans' (77%,n ¼ 125). 78% of participants were intrigued in finding out more about the possible implementation of AI in clinical practice. Contrastingly, only 53% believed that AI could help reduce their clinical burden in decision making (1:7%,2:13%,3:37%,4:40%,5:13%). Age, source of funding and occupation did not affect perceptions. Furthermore, inexperience and lack of knowledge of AI tools were major barriers experienced: 14/29 participants that disagreed with whether utilising AI could reduce clinical burden, had never even used AI tools in the first place. Similarly, 11% indicated discomfort in using AI tools in clinical practice, of whom 79% self-described as having poor knowledge of AI. Evidence and data with improved live birth rate was identified by most respondents (120/144) as the most critical/important unmet need by fertility professionals. The preferred manner of implementation was directly to the equipment used in clinical practice (50%). Limitations, reasons for caution: Despite attempts to have invitees' global distribution matching global cycle numbers, the actual respondents did not reflect the proportion of IVF cycles in each country due to an increased response rate from UK, France and Europe and a reduced response rate from China and Asia. Wider implications of the findings: This is the first study to assess perceptions of fertility professionals towards the use of AI in fertility care, highlighting the need to increase education of fertility professionals and validation standards to support fertility professionals in the responsible use of this new type of technology. Trial registration number: N/A Abstract citation ID: dead093.538 P-178 The interaction between spermatozoa and cumulus cells: a more physiological approach to the selection of good quality spermatozoa for assisted reproduction Study question: Does selection by cumulus cells (CCs) improve sperm quality in terms of acrosome integrity and mitochondrial functionality compared to standard techniques? Summary answer: The sperm-CCs interaction method appears to be effective in selecting sperm with an intact acrosome and functioning mitochondria What is known already: In nature, the selection of the best quality sperm is very demanding and involves high morphological qualities and dynamic features. Semen preparation in ART has long been carried out using either the swim-up or density gradient method; although both methods provide motile sperm, they cannot really replicate the physiological selection processes. As a result, several methods have been proposed to mimic the natural selection that occurs in the female reproductive tract, allowing the most competent sperm to provide the paternal contribution to the zygote. However, the literature on these techniques is limited and does not provide consistent conclusions Study design, size, duration: Proof-of-principle study conducted at the New Fertility Group (NFG) in Rome and the Department of Molecular and Developmental Medicine at the University of Siena (Italy) from July 2022 to December 2022, including 9 semen samples. Comparison of the CCs selection model with the standard swim-up by assessing mitochondrial and ac-rosome integrity. In addition, mitochondrial activity was assessed by oxy-graphic analysis in spermatozoa exposed to immortalised human granulosa cells (hGL5) compared to standard swim-up sorted spermatozoa Participants/materials, setting, methods: The CCs-model was prepared by running two channels of medium, one with CCs (study group) and one with medium alone (control). Spermatozoa were added to each channel and incubated at 37 C for 1 hour. Moreover, spermatozoa were also added on hGL5 and incubated for 1.5h. The collected spermatozoa were compared with controls for acrosomal integrity, assessed by FITC-labelled PSA, and mi-tochondrial membrane potential, assessed by Mitotracker. Finally, sperm oxygen uptake was measured by oxygraphic analysis Main results and the role of chance: Assessment of sperm acrosome integrity showed a higher percentage of responding acrosomes in the CCs model compared to swim-up and controls (61% § 0.3; 39% § 0.4; 19% § 0.4 p < 0.05). The CCs model also showed 83% § 0.3 of spermato-zoa with active mitochondria compared to 65% § 0.3 in the control group (p < 0.005). A similar pattern was observed in the swim-up group. Quantitative analysis of mitochondrial membrane potential (MMP) confirmed that CCs and swim-up groups had higher MMP compared to the control group (p < 0.005). Evaluation of mitochondria in the hGL5 treated group showed active mitochondria in 78% § 0.49 of the sperm compared to 59% § 0.65 in the control group (p ¼ 0.1). The same profile was detected by fluorescence quantification of MMP in the hGL5 group compared to the control group (p < 0.01). Oxygraphic analysis, as an index of oxidative phos-phorylation and consequently of ATP production, was performed on hGL5 exposed spermatozoa, swim-up selected spermatozoa and controls. hGL5 exposed and swim-up selected spermatozoa showed a similar O2 consumption, about 4 times higher than unselected spermatozoa (p < 0.05) Limitations, reasons for caution: The limited sample size and the hetero-geneity of the samples were the main limitations of this study. Although CC and hGL5 sperm selection models appear to be more physiological, further studies on other parameters such as sperm DNA integrity are needed. Wider implications of the findings: Both the CCs model and the hGL5 model appear to be effective in selecting good quality sperm. As these models avoid sperm centrifugation, further research is needed to understand their efficacy and reliability and whether they are a valid alternative to conventional sperm selection methods in terms of IVF outcomes. Trial registration number: none Abstract citation ID: dead093.539 P-179 Euploid blastocysts rate in pre-implantation genetic testing (PGT) cycles with high levels of sperm DNA fragmentation does not improve after Magnetic Activated Cell Sorting (MACS)