Patient Data Research Articles

Validation of Artificial Intelligence in the Classification of Adolescent Idiopathic Scoliosis and the Compairment to Clinical Manual Handling.

The accurate measurement of Cobb angles is crucial for the effective clinical management of patients with adolescent idiopathic scoliosis (AIS). The Lenke classification system plays a pivotal role in determining the appropriate fusion levels for treatment planning. However, the presence of interobserver variability and time-intensive procedures presents challenges for clinicians. The purpose of this study is to compare the measurement accuracy of our developed artificial intelligence measurement system for Cobb angles and Lenke classification in AIS patients with manual measurements to validate its feasibility. An artificial intelligence (AI) system measured the Cobb angle of AIS patients using convolutional neural networks, which identified the vertebral boundaries and sequences, recognized the upper and lower end vertebras, and estimated the Cobb angles of the proximal thoracic, main thoracic, and thoracolumbar/lumbar curves sequentially. Accordingly, the Lenke classifications of scoliosis were divided by oscillogram and defined by the AI system. Furthermore, a man-machine comparison (n = 300) was conducted for senior spine surgeons (n = 2), junior spine surgeons (n = 2), and the AI system for the image measurements of proximal thoracic (PT), main thoracic (MT), thoracolumbar/lumbar (TL/L), thoracic sagittal profile T5-T12, bending views PT, bending views MT, bending views TL/L, the Lenke classification system, the lumbar modifier, and sagittal thoracic alignment. In the AI system, the calculation time for each patient's data was 0.2 s, while the measurement time for each surgeon was 23.6 min. The AI system showed high accuracy in the recognition of the Lenke classification and had high reliability compared to senior doctors(ICC 0.962). The AI system has high reliability for the Lenke classification and is a potential auxiliary tool for spinal surgeons.

292 Predictive Factors for Post-Operative Hypotension Following Carotid Endarterectomy

Abstract Background Post-operative hypotension is a recognised complication following carotid endarterectomy (CEA). This study aimed to examine the incidence of post-operative hypotension requiring vasopressors and to identify variables associated with this phenomenon following CEA. Method A retrospective cohort study of 73 consecutive patients undergoing CEA between June 2022 and June 2023 was conducted. Patient data, including degree of carotid stenosis, and comorbidities such as myocardial infarction, diabetes, hypertension, and chronic kidney disease (CKD), were extracted from medical records. Fisher’s exact test was used to evaluate the difference in prevalence of co-morbidities between groups, and Mann-Whitney U test to assess for difference in degree of carotid stenosis. Results 71 symptomatic and 2 asymptomatic CEAs were performed, with 12.3% (n=9) experiencing post-operative hypotension requiring vasopressors. In the post-CEA hypotension group, 33.3% (n=3) had a history of myocardial infarction, 77.8% (n=7) had hypertension, and none had diabetes or CKD. In comparison, the non-hypotensive group had a prevalence of 17.2% (n=11) for myocardial infarction, 18.8% (n=12) for diabetes, 71.9% (n=46) for hypertension, and 6.3% (n=4) for CKD. There was no significant difference in prevalence of these co-morbidities between the two groups. The degree of carotid stenosis was similar in the post-CEA hypotension and the non-hypotension group, 75% (IQR 60% – 90%), and 70% (IQR 65% - 90%), respectively. Conclusions Approximately 1 in 8 CEA patients require vasopressor support for post-operative hypotension. However, no specific variable emerged as a significant predictor for vasopressor requirement. Consequently, emphasis should be placed on post-operative monitoring to facilitate timely and appropriate intervention.

Relation of Total Antioxidant Capacity to Clinical Severity of COVID-19 Infection in Paediatric Patients

Abstract Objectives The pathogenesis of COVID-19 infection is still not well clarified. In this regard oxidative stress and its relation to disease severity is one of the topics that need to be investigated. Aim This study was carried out to investigate the relationship between the oxidant stress and antioxidant system represented by total antioxidant capacity and clinical severity of COVID19 infection in pediatric age group. Methods The current cross-sectional study included 45 patients with COVID 19 PCR-proven infection admitted at the Children’s Hospital, Faculty of Medicine, Ain Shams University compared to 45 healthy age and sex matched control group. Detailed medical history, thorough examination and recording of all infection related laboratory parameters were done for each enrolled case. Measurement of total antioxidant capacity (TAC) in the serum of all studied patients and controls was done by ELISA. Results TAC levels were considerably lower in pediatric patients (median 24u/l, IQR 9-37u/l) compared to healthy individuals (median 90u/l, IQR 77-100u/l, p < 0.001) and the levels were statistically lower in severe cases compared to those with mild disease (p = 0.008). In this regard, 100% of controls showed normal TAC while only 31.1% from cases exhibited normal TAC levels and 68.9% of cases had low TAC levels. There was strong statistical significance between PICU admission and low TAC levels (p = 0.035). Additionally, the TAC showed negative correlation with the initial CRP of patients (r= -0.433, p = 0.003). There was also a significant inverse correlation between TAC and time needed for viral clearance (r=- 0.418, p = 0.004) as well as a significant positive correlation between body mass index z-score and TAC levels (r = 0.423, p value 0.004). Conclusion Total antioxidant capacity could serve as a novel prognostic marker of COVID -19 infection severity in pediatric patients.

ChatGPT in Urology: Bridging Knowledge and Practice for Tomorrow's Healthcare, a Comprehensive Review.

Background: Among emerging AI technologies, Chat-Generative Pre-Trained Transformer (ChatGPT) emerges as a notable language model, uniquely developed through artificial intelligence research. Its proven versatility across various domains, from language translation to healthcare data processing, underscores its promise within medical documentation, diagnostics, research, and education. The current comprehensive review aimed to investigate the utility of ChatGPT in urology education and practice and to highlight its potential limitations. Methods: The authors conducted a comprehensive literature review of the use of ChatGPT and its applications in urology education, research, and practice. Through a systematic review of the literature, with a search strategy using databases, such as PubMed and Embase, we analyzed the advantages and limitations of using ChatGPT in urology and evaluated its potential impact. Results: A total of 78 records were eligible for inclusion. The benefits of ChatGPT were frequently cited across various contexts. In educational/academic benefits mentioned in 21 records (87.5%), ChatGPT showed the ability to assist urologists by offering precise information and responding to inquiries derived from patient data analysis, thereby supporting decision making; in 18 records (75%), advantages comprised personalized medicine, predictive capabilities for disease risks and outcomes, streamlining clinical workflows and improved diagnostics. Nevertheless, apprehensions were expressed regarding potential misinformation, underscoring the necessity for human supervision to guarantee patient safety and address ethical concerns. Conclusion: The potential applications of ChatGPT hold the capacity to bring about transformative changes in urology education, research, and practice. AI technology can serve as a useful tool to augment human intelligence; however, it is essential to use it in a responsible and ethical manner.

O-288 Pro

Abstract Currently and globally, the majority of ART treatments are performed either fully in the private medical sector or are partially subsidized in the public sector but with common treatments spill-over to the private sector; countries where there is sufficient public coverage of ART are in fact rare. While private clinics and hospital have been the norm in ART for decades, in recent years the field has undergone significant consolidation, and this has resulted in an influx of large financial players such as private equity (PE) firms. The results are a series of mergers and acquisitions that are shaping the geography of ART provision. In this debate, I will take on the “pro” side and I will highlight the scholarship around the changes in care brought about by PE ownership of medical practices, bringing examples from branches of medicine such as dermatology, dentistry, long term care or Ob&Gyn that have experienced market consolidation in the last decades. I will show that available evidence indicate that the change in ownership to PE of private medical practices is associated with an increase in the number of patients treated and a net increase in payments to clinicians. Moreover, PE ownership has been repeatedly associated with a perception of higher quality care by patients, while clinical KPIs have not gotten worse and, if anything, have improved. This is usually due to greater intentional focus on standardization and quality control, streamline and protocolization of treatments, and centralization of certain administrative areas. I will further argue that, in large PE owned networks, best practices tend to be enhanced by peer to peer sharing and central medical boards, while centralization and digitalization of patient data collection favors research and development in a field that sorely lacks public funding for reproductive research.

O-251 Generative artificial intelligence substantially enhances the accuracy of embryo selection models

Abstract Study question Can generative artificial intelligence (AI) produce high-fidelity human embryo images to improve AI-based embryo selection models? Summary answer Generative AI models exhibit the capability to generate high-fidelity human embryo images and can substantially improve the performance of AI models through extensive training data. What is known already The integration of AI into in vitro fertilization (IVF) procedures holds the potential to enhance objectivity and automate embryo selection for transfer. However, the effectiveness of AI is limited by data scarcity and ethical concerns related to patient data privacy. Generative Adversarial Networks (GAN) have emerged as a promising approach to alleviate data limitations by generating synthetic data that closely approximate real images. However, the advantage of applying GAN in IVF embryo images is yet to be determined. Study design, size, duration Embryo images were retrieved as training data from time-lapse microscopy (TLM) videos (n = 328). Embryo key morphokinetic variables including blastomere division from 1-cell stage to 9 (and more) cells-stage, compaction of morula, and blastocyst formation were manually annotated by six embryologists. A style-based GAN was fine-tuned as the generative model and a residual network as the morphokinetic classification model. Participants/materials, setting, methods We configured generative models with data augmentation (AUG) and pretrained weights (Pretrained-T/R) to test their refinement to synthetic image quality. We analyzed quantitative metrics including Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) to assess the quality and fidelity of the generated images. Subsequently, we evaluated qualitative performance through a visual Turing test. Then, we compared the performance of a classifier by training real images alone and by integrating real images with generated data. Main results and the role of chance During the training process, we observed consistent improvement in image quality that was measured by FID and KID scores. The AUG+Pretrained-R model showed the highest performance of the evaluated five configurations with FID and KID scores of 15.2 and 0.004 following 5,000 training iterations. Subsequently, we carried out a visual Turing test, such that a total of 60 individuals including IVF embryologists (Group I, n = 25), IVF laboratory technicians (Group II, n = 15), and non-experts (Group III, n = 20) evaluated the synthetic blastocyst-stage embryo images. Group I displayed accuracy of 55.7% (±6.2), sensitivity of 65.9% (±14.1), and specificity of 45.1% (±17.8). Group II showed accuracy of 54.2% (±4.7), sensitivity of 65.9% (±17.6), and specificity of 42.0% (±19.6). Group III had the accuracy of 50.1% (±3.8), sensitivity of 49.3% (±6.3), and specificity was 50.9% (±10.4). Statistical analysis indicated significant differences in accuracy (Kruskal-Wallis test, P=1.2x10-3) and sensitivity (Kruskal-Wallis test, P=1.6x10-4) among the three groups. In the embryonic stage classification model, integrated with generated data outperformed the model using real data solely, with an increase of validation accuracy from 72.6% to 90.6%. The classifier was tested on external TLM video data (n = 100) where the area under the curve was 0.92. Limitations, reasons for caution Further research is needed to involve a more extensive and diverse dataset, e.g. video generation, and more detailed annotations including polar body appearance, pronuclei appearance and disappearance, and blastocyst expansion and hatching. Wider implications of the findings Generative AI offers potential in generating high-fidelity human embryo images. This approach ensures sufficient training datasets while addressing class imbalances for robust AI-based methods, ultimately transforming embryo selection and enhancing IVF outcomes. A set of 5,000 generated images (1024x1024-pixel) at each embryonic developmental stage was open-source for future AI studies. Trial registration number not applicable

P-576 Pharmacokinetic and pharmacodynamic modelling to explore dosing regimens of corifollitropin alfa for ovarian stimulation without the need for additional daily recFSH injections

Abstract Study question Can ovarian stimulation in IVF patients be realized with one or two corifollitropin alfa (CFA) injections only? Summary answer For 94% of IVF patients, ovarian stimulation can be safely completed with a maximum of two CFA injections What is known already A single dose CFA replaces the first week of stimulation with daily recFSH, providing ovarian stimulation similar to daily 300 IU recFSH. Pharmacokinetic and pharmacodynamic (PK/PD) modelling has shown that a threshold serum FSH concentration of 1.1 ng/ml (∼ 6.72 IU/L) is required to maintain multiple follicular development, and that such FSH concentrations are maintained for 7 days following single injection. From day 8 onwards, most patients require daily recFSH injections to maintain serum FSH above threshold to complete the follicular growth. Patients requiring profound stimulation, e.g. prior to ‘freeze-all’, would benefit most from CFA only treatment, requiring less injections. Study design, size, duration This was a retrospective analysis using individual patient data from 4 large CFA trials, including totally 2397 IVF patients receiving a single injection of CFA followed by daily follitropin beta injections from day 8 of stimulation until triggering. Participants/materials, setting, methods A PK model developed for CFA was used to predict serum concentrations following different dosing regimens of CFA only. Clinical trial data from 2397 patients was used to estimate the distribution of the required length of stimulation and to evaluate the impact of different dosing regimens on the serum FSH concentrations up to the day of triggering. Main results and the role of chance At stimulation day 8, 21% of patients did not require additional FSH, whereas 25%, 27%, 14%, and 7% needed 1, 2, 3 or 4 days additional stimulation days to complete the cycle. Only 6% required more than 4 days additional stimulation. Patients below 60 kg remained longer above the threshold and additional dosing could have been delayed to stimulation day 9-11 depending on the initial dose (100 or 150 mg). In a 70 kg woman, daily doses of 7 mg CFA would be sufficient to maintain trough concentrations of FSH above the threshold, and a single dose of 15 and 30 mg on day 8 would sustain stimulation for another 2 and 4 days, respectively. A single dose of 30 mg on day 8 would increase FSH concentrations from 7 IU/L to a maximal level of approximately 12 IU/L, a fluctuation that is unlikely to recruit new small follicles during the late follicular phase. It is therefore suggested that patients can be safely treated with a second dose of 30 mg CFA on day 8 of stimulation, without risk of overdosing when receiving GnRH agonist triggering, and that 94% of patients will not need more than two doses. Limitations, reasons for caution The theoretical dosing regimens build upon this retrospective analysis and modelling needs to be validated in a clinical study to confirm that one additional dose of CFA is able to complete ovarian stimulation efficiently. Wider implications of the findings IVF patients planned to have ‘freeze-all’ following GnRH agonist triggering may be treated conveniently with one or max two injections of CFA for ovarian stimulation. Trial registration number not applicable

983 A comparison of the Post-operative Complications Rates in the Removal of Benign Parotid Tumours: Extracapsular Dissection Versus Superficial Parotidectomy and Partial Superficial Parotidectomy

Abstract Aim The objective of this systematic review was to assess the effectiveness of different surgical techniques in the removal of benign parotid tumours. The analysis focused on three specific postoperative complications including: recurrence rate, temporary and permanent facial nerve palsy (FNP) and Frey's syndrome. In this systematic review, patients who underwent extracapsular dissection (ECD) were compared to those who underwent superficial parotidectomy (SP) or partial superficial parotidectomy (PSP). Method OVID, Cochrane Library, PubMed, and Scopus databases were searched. Inclusion and exclusion criteria were applied resulting in seven papers; all of which were retrospective cohort studies. Results A total of 2282 patient data was pooled (1174 ECD-treated and 1108 SP and PSP-treated patients). Statistical analysis showed there was no significant difference in the rate of recurrence (log odds ratio (LOR) = -0.15, 95% confidence interval (CI): -1.11, 0.80). There were lower rates of both temporary facial nerve injury (LOR = -1.76, 95% CI: -2.75,-0.76) and Frey’s syndrome (LOR = -1.63, 95% CI: -2.90,-0.37) in the ECD treated patients. There is reasonable statistical significance suggesting that ECD has lower rates of Permanent FNP (LOR=-1.00, 95% CI: -2.35, 0.35). Conclusions Despite the results showing ECD favourability in terms of FNP and Frey’s syndrome, it is important to understand the limitations of this study. Confounding factors such as, tumour size and placement, patient age and gender and surgical cosmetic outcomes were not analysed in this systematic review (SR). Future research should focus on a prospective cohort study, directly comparing the different surgical techniques.

O-014 Cumulative live birth associated with number of oocytes in ovarian stimulation with follitropin delta: an individual patient data meta-analysis

Abstract Study question What is the optimum number of oocytes retrieved to maximise cumulative live birth rates in the fresh and subsequent frozen cycles following follitropin delta stimulation? Summary answer The cumulative live birth rate increased steadily with number of oocytes retrieved up to a plateau starting at ∼21 oocytes retrieved. What is known already Live birth rate (LBR) per fresh ovarian stimulation cycle is the conventionally reported outcome of in vitro fertilisation (IVF). In recent years, there has been a marked increase in number and successful outcomes of cryopreserved cycles, suggesting that the cumulative live birth rate (CLBR) has emerged as a more clinically relevant outcome. In the fresh cycle, the number of oocytes retrieved is regarded as a prognostic factor for LBR. A similar association has been shown for CLBR implying that CLBR increases with the number of oocytes and continues to increase beyond the plateau observed for fresh cycle LBR. Study design, size, duration Individual patient data meta-analysis of 1746 patients from 4 randomised controlled trials using follitropin delta for ovarian stimulation. The analysis included patients with ≥1 oocyte retrieved following stimulation. The CLBR in the fresh and subsequent frozen cycles was evaluated. Predicted CLBR was obtained using a logistic regression analysis with fractional polynomials to assess the association between number of oocytes retrieved and CLBR. Subgroup analyses were performed based on age, AMH and number of oocytes retrieved. Participants/materials, setting, methods Participants were women, 18–42 years, undergoing their first or second in vitro fertilisation/intracytoplasmic sperm injection (IVF/ICSI) cycle in a GnRH antagonist/long agonist protocol with human chorionic gonadotrophin or GnRH agonist triggering and IVF/ICSI insemination. Single or double blastocyst transfer was performed on Day 5 and all viable surplus blastocysts were cryopreserved. All pregnancies from the fresh cycle and frozen cycles initiated within 1 year after start of stimulation were followed until birth. Main results and the role of chance The study included 1746 patients who underwent a total of 2948 cycles; 1746 fresh and 1202 frozen. In total, 740 patients (42.4%) initiated frozen cycles (maximum of 6). The study population had a mean age of 33.8 years and a median AMH level of 17.0 pmol/l. The mean number of oocytes retrieved was 12.4, the fresh cycle LBR was 29.1% and the CLBR was 51.4%. The CLBR steadily increased with number of oocytes retrieved, reaching above 60% at > 15 oocytes and above 70% at > 20 oocytes. The CLBR started to plateau at ∼21 oocytes. Subgroup analyses by number of oocytes retrieved, age group or AMH group demonstrated that the CLBR decreased with increasing age (57.1%, 51.6% and 35.8% at < 35, 35-37 and ≥38 years). In comparison it was similar for AMH <15 and ≥15 pmol/l (52.0% and 50.9%, respectively). A continued increase in CLBR from 15 oocytes retrieved was observed in older patients (≥38 years); from 41.3% to 53.4% to 58.7% at 15-19, 20-24 and ≥25 oocytes. No equivalent benefit was observed in younger patients, where corresponding rates were 72.5%, 68.0% and 78.8% in patients <35 years, and 70.3%, 73.1% and 71.5% in patients 35-37 years. Limitations, reasons for caution A limitation of this study is the small number of patients with >20 oocytes retrieved. The individual pooled studies were heterogenous regarding number of blastocysts transferred and hCG/agonist trigger. Wider implications of the findings The current individual patient data meta-analysis suggests an increase in CLBR with number of oocytes retrieved up to a plateau starting at ∼21 oocytes following ovarian stimulation cycles with follitropin delta and subsequent frozen cycles. An increase in CLBR from 20 oocytes was evident in older but not younger patients. Trial registration number NCT01956110, NCT03564509, NCT03740737, NCT03738618

P-655 Live birth rate in the fresh cycle associated with number of oocytes in ovarian stimulation with individualised follitropin delta: an individual patient data meta-analysis

Abstract Study question What is the optimum number of oocytes retrieved to achieve a live birth for women undergoing ovarian stimulation with individualised follitropin delta? Summary answer The live birth rate (LBR) in the fresh cycle was highest in the range of 8-14 oocytes retrieved, peaking at 11 oocytes. What is known already The number of oocytes retrieved following ovarian stimulation for assisted reproductive technologies is regarded a prognostic marker of pregnancy outcome, where high numbers increase chances of live birth but also the risk of complications, especially ovarian hyperstimulation syndrome (OHSS). Thus, an optimum range of oocytes retrieved is essential. Still, there is no consensus regarding this range in fresh cycles. Optimum numbers between 6 and 15 oocytes have been suggested, taking the risk of OHSS into consideration. The individualised dosing algorithm for the recombinant follicle-stimulating hormone follitropin delta has a target range of 8–14 oocytes. Study design, size, duration Individual patient data meta-analysis of 1772 patients from 5 randomised controlled trials using individualised dosing of follitropin delta for ovarian stimulation, with fixed daily dosing based on serum anti-Müllerian hormone (AMH) and body weight. The analysis included patients with ≥1 oocyte retrieved. Outcomes of LBR and OHSS in the fresh stimulation cycle were evaluated in relation to number of oocytes retrieved. Subgroup analyses were performed based on age, AMH and number of oocytes retrieved. Participants/materials, setting, methods Participants were women, 18–42 years, undergoing first or second in vitro fertilisation/intracytoplasmic sperm injection (IVF/ICSI) cycle in a GnRH antagonist/long agonist protocol with human chorionic gonadotrophin or GnRH agonist triggering and IVF/ICSI. Single or double embryo/blastocyst transfer was performed on Day 3/5. All pregnancies were followed until birth. Predicted live birth was obtained using a logistic regression analysis with fractional polynomials to assess the association between number of oocytes retrieved and live birth. Main results and the role of chance The studied population (n = 1772) had a mean age of 32.6 years and median AMH of 17.7 pmol/l. Mean number of oocytes retrieved was 10.4, the LBR was 32.1% and the OHSS rate (any grade and onset) was 6.6%. The LBR steadily increased with the number of oocytes retrieved up to a plateau starting at 8 oocytes, with a LBR above 34% in the range of 8-14 oocytes retrieved, peaking at 34.9% for 11 oocytes. Beyond 14 oocytes, LBR gradually declined. By number of oocytes (grouped), the LBR was 27.8%, 33.6% and 30.9% at 1-7, 8-14 and ≥15 oocytes. In patients with embryo transfer, corresponding rates were 32.8%, 37.2% and 38.7%. In the subgroup analyses, LBR decreased with increasing age (32.7%, 30.7% and 23.4% at < 35, 35-37 and 38-42 years) while it was similar for AMH <15 and ≥15 pmol/l (30.4% and 31.3%, respectively). LBR was highest at 8-14 oocytes in patients <35 years (28.0%, 36.2% and 32.4% at 1-7, 8-14 and ≥15 oocytes), while it was consistently low (<26%) in patients 38-42 years, irrespective of number of oocytes retrieved. The OHSS rate (any grade) increased from 2.1% with 1-7 oocytes, to 5.2% with 8-14 oocytes and 17.0% with ≥15 oocytes. Limitations, reasons for caution A limitation of this study is the small number of patients with >20 oocytes retrieved in the studied population. Wider implications of the findings The current individual patient data meta-analysis suggests an optimum range of 8-14 oocytes retrieved to achieve a live birth in fresh cycles with follitropin delta. Furthermore, the analysis demonstrates a marked increase in OHSS rate from 15 oocytes retrieved. The results support the appropriateness of individualised follitropin delta dosing regimen. Trial registration number NCT01956110, NCT03228680, NCT03296527, NCT03564509, NCT03809429

358 Driving Endovascular Solutions for Abdominal Aortic Aneurysms: A 9-Year International Experience with the Fenestrated Anaconda Endograft

Abstract Aim Endovascular aortic repair (EVAR) has become the mainstay treatment for abdominal aortic aneurysms and is associated with optimal outcomes. However, there remains a risk of complications requiring reintervention. Several EVAR devices exist commercially, yet, the Fenestrated Anaconda™ (FA) has demonstrated outstanding results. This study aims to presents a 9-year cross-sectional international analysis of custom-made FA outcomes. Method Patient data was collected prospectively in 27 countries over 9 years and stored in an international registry. This was later retrieved and analysed retrospectively. Results A total of 5058 patients received the FA endograft. This was indicated either due to complex anatomy for competitor devices (n = 3891, 76.9%) or based on surgeon preference (n = 1167, 23.1%). Overall, the FA was utilised to rescue 2987 (59%) failed previous EVARs. The predominant device category and proximal ring stent configuration were bifurcate (83.6%) and standard (64.5%). Most devices were delivered within 6-8 weeks (55.4%) of diagnosis and 95% came with a prototype. As for clinical outcomes, both survival and TVP were 100% during the first 6 postoperative years but dropped to 77.1% and 81% thereafter. A sac regression of 0-30% was observed in 4772 (94.3%) patients over the first 4 years, whilst all patients had 20-45% sac regression in years 5-9 of follow-up. No cases of endograft migration or reintervention were recorded. All clinical outcomes were further stratified by indication group. Conclusions The custom-made FA endograft features a highly unique and innovative design which enables it to treat highly complex aortic anatomy while achieving favourable results.

Integrating Omics Data and AI for Cancer Diagnosis and Prognosis.

Cancer is one of the leading causes of death, making timely diagnosis and prognosis very important. Utilization of AI (artificial intelligence) enables providers to organize and process patient data in a way that can lead to better overall outcomes. This review paper aims to look at the varying uses of AI for diagnosis and prognosis and clinical utility. PubMed and EBSCO databases were utilized for finding publications from 1 January 2020 to 22 December 2023. Articles were collected using key search terms such as "artificial intelligence" and "machine learning." Included in the collection were studies of the application of AI in determining cancer diagnosis and prognosis using multi-omics data, radiomics, pathomics, and clinical and laboratory data. The resulting 89 studies were categorized into eight sections based on the type of data utilized and then further subdivided into two subsections focusing on cancer diagnosis and prognosis, respectively. Eight studies integrated more than one form of omics, namely genomics, transcriptomics, epigenomics, and proteomics. Incorporating AI into cancer diagnosis and prognosis alongside omics and clinical data represents a significant advancement. Given the considerable potential of AI in this domain, ongoing prospective studies are essential to enhance algorithm interpretability and to ensure safe clinical integration.

O-286 Weight loss interventions prior to infertility treatment does it make sense?

Abstract Obesity in women is negatively associated with reproductive outcomes such as decreased natural conception and pregnancy rate in assisted reproductive technique (ART), as well as increased risks of miscarriage and maternal and foetal complications, including risks of perinatal and neonatal death. The reproductive consequences of obesity stem from a combination of ovarian, uterine and systemic pathophysiological changes, although not all fully elucidated. These alterations contribute to reduced oocyte and embryo quality, reduced uterine receptivity and systemic inflammatory responses. Various guidelines recommend lifestyle interventions based on dietary and/or physical activity targeting at a 5 to 10% reduction in body weight as an initial step prior to fertility treatment for women with infertility and overweight or obesity. However, evidence from well powered randomised controlled trials (RCTs) assessing the effectiveness of lifestyle interventions aiming at weight loss prior to fertility treatments is scarce and not unequivocally positive with respect to reproductive outcomes. First, this presentation will focus on the effectiveness of pre-conception lifestyle intervention targeting weight loss, on reproductive outcomes documented in the latest systematic review (SR) and meta-analysis and preliminary results of an individual participant data meta-analysis (IPDMA). The latest SR in 2021 (Obesity reviews DOI: 10.1111/obr.13325) including 15 RCTs until March 2020 (N = 1852 women) suggests more weight loss in the intervention group. An increase in live birth rates (LBR) in nine RCTs (N = 1203 women) and a higher natural conception rate following lifestyle intervention compared to no intervention were reported. However, no effect of lifestyle intervention preceding ART in six RCTs (N = 1040 women). With respect to potential harm of lifestyle intervention there is no significant increased risk of early pregnancy loss. Complications during pregnancy, such as early pregnancy loss and maternal, fetal and neonatal outcomes are underreported in most included studies. The VENUS IPDMA (BMJ Open 2022;12:e065206) analyzed individual patient data of 11 RCTs of 14 eligible RCTs (N = 1903 participants; 1010 in the intervention group and 893 in the control group). Preliminary data (abstract ESHRE 2023) showed that physical activity and/or dietary interventions prior to fertility treatment resulted in more weight reduction compared to those in the control group in 11 RCTs. The intervention group, however, did not have a significantly higher rate of LBR in nine RCTs (N = 1702 participants). Compared to the control group, the intervention group had smaller waist and hip circumference, lower systolic and diastolic blood pressure, and lower triglycerides, total cholesterol, glucose, and insulin levels at the time of study follow up. Do we have a definitive answer to the question: “weight loss interventions prior to fertility treatment; does it make sense” using data of IPDMA? Shortcomings of the available evidence regarding the effectiveness and safety of dietary and/or physical activity interventions in women with overweight or obesity prior to fertility treatments will be presented. Limitations of the studies and future perspectives and challenges in this field of research will be highlighted. Finally, the question “does it make sense” is broader than the effectivity of the intervention. Do we as clinicians adopt our role as health advocates to advice and guide future parents to adopt a healthy lifestyle, with weight reduction as a result? Could this lead to a healthier lifestyle for the future of parents and children? To conclude: “does it make sense” is not an easy question to answer.

P-490 ‘Your Fertility @ Home’, a clinical pilot study on a new diagnostic smartphone app for treatment naive fertility patients

Abstract Study question What are patients’ experiences with a newly developed diagnostic smartphone app? Summary answer The first patients’ experiences with the content of the app are positive. Also, participants made positive changes in their lifestyle after advice from the app. What is known already Previous studies on digital healthcare for fertility patients are promising. However, many e-Health initiatives are not thoroughly evaluated, which hampers implementation. During a fertility trajectory patients often feel a lack of control, we therefore developed a new smartphone app with a dual purpose. First, to give new fertility patients more control and empowerment over their situation by providing reliable information and personalized advice. Second, to support healthcare professionals in choosing the right diagnostic tests and interpretation of the results. This app was first validated on a historical cohort of patient data, before testing the app in a prospective patient group. Study design, size, duration This is an ongoing, prospective pilot study of 70 heterosexual patient couples. Patients were followed up from the start of the fertility workup until the work-up finished. This abstract covers the preliminary results of the first 19 participants. Follow up is expected to be complete at time of the ESHRE annual meeting. Participants/materials, setting, methods The study population consists of treatment naïve infertile couples, who were referred to a fertility-clinic. Before the first appointment, patients used the smartphone app, which consisted of a medical anamnesis questionnaire for both women and partners. Based on the anamnesis the app provided recommendations about lifestyle and diagnostic tests, which were in line with current Dutch guidelines. Patients were given advice on the results of the tests and filled in a questionnaire about their experiences. Main results and the role of chance The experience questionnaire for patients included three parts. The questions in the first part were based on the validated Patient-Centered Questionnaire Infertility. This covered questions about the use of the app, for example the ease of installation and if they felt involved with use of the app. Sixteen out of nineteen patients (84%) felt taken seriously, eleven patients (58%) experienced enough attention to their emotions and fourteen patients (74%) would advise their friends to use the app. The second part included questions about the results of the diagnostic tests. Ten patients (52%) found the explanation of the results clear, three patients (15%) wanted additional information. Eleven patients (58%) thought the results and information matched their personal situation. The third part of the questionnaire asked about the lifestyle advice patients received in the app. Twelve patients (63%) found this advice useful. The other patients found the advice not matching their situation. After using the app, ten patients (52%) said they made a change in their lifestyle to optimize their fertility situation. On a ten point Likert scale, 16 patients (84%) scored the app an eight or higher. Limitations, reasons for caution These are results of a pilot study and thus must be interpreted with caution. Secondly, this is the first version of the app that has been tested with patients, so next the app needs further optimization before it can be fully implemented. Wider implications of the findings Considering the positive reception, this app holds potential for a beneficial change in fertility care. It may increase the accessibility to reliable personal information and advice for new fertility patients in a safe and private environment. This might lead to patient empowerment and positive lifestyle changes enhancing their fertility potential. Trial registration number 2022.09.05.01

P-719 The fertility clinic landscape in England 2012-2017: a study of the impact of clinic size and environment on success rates

Abstract Study question How are fertility clinics in England distributed and has this changed over time? Does clinic size, geography and local deprivation level influence live birth rates? Summary answer A clinic’s size, urban/rural environment and local deprivation level shows no statistically significant impact on a clinic’s live birth rates. What is known already It has been established that children born through assisted reproduction are more likely to have parents from higher socioeconomic groups compared to those conceived through natural conception. However, studies examining the relationship between socioeconomic status and fertility treatment success rates have varied outcomes and occasionally conflicting results. There has so far been little research internationally as to whether geographical, environmental and socioeconomic markers influence fertility treatment outcomes on a national scale. Study design, size, duration Publicly available HFEA data from 2012 to 2017 for all registered clinics in England was accessed. The total number of IVF/ICSI cycles for all age groups and live birth rate per embryo transferred were recorded. 56 clinics (32,091 treatment cycles) were recorded in 2012, rising to 69 clinics (36,638 treatment cycles) in 2017. Clinic postcode was used to determine Rural-Urban Classification and postcode-level and local authority-level deprivation according to the Index of Multiple Deprivation (IMD). Participants/materials, setting, methods Statistical analysis was performed using R Statistical Software and Datawrapper was used to generate map infographics. Clinic size was categorised by the number of IVF/ICSI cycles conducted per year – small (0-499), medium (500-999) and large (>1000). Clinic environment was classified as urban or rural and IMD was used to categorise clinics into deprivation quintiles. Weighted live birth rates were analysed to determine any difference in clinic success based on its size and environment. Main results and the role of chance The majority of clinics conducted between 0-499 IVF/ICSI cycles per year. There was no statistically significant difference in the live birth rate per embryo transferred based on clinic size with an average success rate of 31.8% in small clinics, 33.9% in medium clinics and 32.2% in large clinics (p-value 0.885). A large proportion of clinics were located in London (28-29% of clinics and 34-40% treatment cycles) between 2012 and 2017 despite only ∼16% of the population of England living in London. There were significantly fewer clinics (p-value 0.047) and treatment cycles (p-value <0.001) conducted in rural, compared to urban locations. There was a small, but not statistically significant, increase in success rate in clinics located in the least, compared to most deprived quintile. The difference in average live births/embryo transferred between the most and least deprived quintile across all years studied was 3.8% (31.1% in most deprived vs 34.9% in least deprived, p-value 0.227). There was also no statistical difference between the live birth rates per embryo transferred across the local-authority deprivation quintiles, although there was a trend for slightly higher success rates in the least deprived quintile compared to most deprived quintile. (30.3% compared to 33.9% (p-value 0.211)). Limitations, reasons for caution Clinic postcode only was used, therefore deprivation may not be representative of the whole population it treats. All IVF/ICSI treatments for all age groups were included, but some clinics may treat an older population of patients. Many IVF laboratories have satellite clinics in surrounding areas, whose postcodes were not included. Wider implications of the findings It is reassuring that local environment and deprivation do not significantly impact on clinic success rates. More detailed analysis of individual patient data on a nationwide level is required to understand this further either through access to primary care records or collaboration between clinics. Trial registration number not applicable

Artificial intelligence innovations in neurosurgical oncology: a narrative review.

Artificial Intelligence (AI) has become increasingly integrated clinically within neurosurgical oncology. This report reviews the cutting-edge technologies impacting tumor treatment and outcomes. A rigorous literature search was performed with the aid of a research librarian to identify key articles referencing AI and related topics (machine learning (ML), computer vision (CV), augmented reality (AR), virtual reality (VR), etc.) for neurosurgical care of brain or spinal tumors. Treatment of central nervous system (CNS) tumors is being improved through advances across AI-such as AL, CV, and AR/VR. AI aided diagnostic and prognostication tools can influence pre-operative patient experience, while automated tumor segmentation and total resection predictions aid surgical planning. Novel intra-operative tools can rapidly provide histopathologic tumor classification to streamline treatment strategies. Post-operative video analysis, paired with rich surgical simulations, can enhance training feedback and regimens. While limited generalizability, bias, and patient data security are current concerns, the advent of federated learning, along with growing data consortiums, provides an avenue for increasingly safe, powerful, and effective AI platforms in the future.

P-386 The effect of intravenous immunoglobulin versus placebo in patients with recurrent pregnancy loss: a systematic review and meta-analysis of randomized trials

Abstract Study question In women with recurrent pregnancy loss (RPL), how does intravenous immunoglobulin (IVIg) compared with placebo affect live birth rate (LBR) in the first subsequent pregnancy? Summary answer IVIg significantly improved LBR in the per protocol (PP), but not the intention to treat (ITT) analysis. LBR increased significantly with number of pregnancy losses. What is known already RPL is defined as two or more pregnancy losses before 24 weeks of gestation, impacting 1-2% of fertile couples. It results from diverse causes, and immunological factors are increasingly implicated in unexplained RPL cases. IVIg has been studied as a treatment with various proposed mechanisms. Existing research on IVIg in RPL has shown conflicting results, but a recent Japanese randomized controlled trial (RCT) reported a significantly increased LBR when IVIg was administered early and in high-dose. Study design, size, duration We conducted a systematic review and meta-analysis of relevant (RCTs, incorporating individual patient data (IPD) to evaluate IVIg’s impact on LBR in RPL patients. Participants/materials, setting, methods This study adhered to PRISMA guidelines and was registered in PROSPERO (ID CRD42023375788). We searched PubMed, Embase, and Cochrane libraries for relevant RCTs up to March 20, 2023. We conducted a meta-analysis with predefined primary (live birth and clinical pregnancy rates) and secondary outcomes. Risk ratios with 95% confidence intervals were calculated for dichotomous outcomes, and mean and standard deviation for continuous variables. We contacted the original authors to perform subgroup analyses based on IPD. Main results and the role of chance A total of 10 RCTs comprising 594 women were included in the meta-analysis, and IPD were retrieved from six RCTs including 354 women. No statistically significant results in LBR between IVIg and placebo treated women were found in the ITT analysis (RR: 1.02 [95% CI 0.86-1.22] p = 0.78). In the PP analysis, LBR was increased in the IVIg group compared with placebo (RR: 1.23 [1.00-1-50]). A statistically significant increase in clinical pregnancy rate was found in the IVIg group compared with placebo among women receiving high dose (median ³ 77.5 g) IVIg (RR: 1.79, [95% CI 1.21-2.65], p = 0.004). Furthermore, a statistically significant decrease in pregnancy loss rate was found in patients receiving high doses of IVIg (RR: 0.76 [95% CI 0.60-0.96], p = 0.02) compared to placebo. In the IPD analysis, RRs for live birth in the IVIg group compared with placebo increased steadily with the number of previous pregnancy losses. RRs for live birth in patients receiving IVIg compared with placebo were 5.26 (1.58-17.53) and 7.50 [1.20-47.05) in patients with ≥6 and ≥7 consecutive pregnancy losses, respectively. In analyses of IPD data adjusted for maternal age, the RRs for live birth were almost similar. Limitations, reasons for caution Limitations in the systematic review include potential bias due to financial support from pharmaceutical companies in half of the studies; potential confounding in subgroup analysis, missing individual patient data; and clinical and methodological heterogeneity among the included RCTs, which all may impact the overall reliability of results. Wider implications of the findings The findings highlight the importance of patient selection and personalized treatment. The PP analysis favored IVIg, emphasizing importance of protocol adherence. Secondly, the effectiveness of IVIg seems to increase with number of previous consecutive pregnancy losses. Thirdly, the dose of IVIg seem to impact its effectiveness. Trial registration number CRD42023375788

P-578 A combined analysis to establish the equipotency of corifollitropin alfa in comparison to daily recombinant FSH including individual data of 3292 IVF/ICSI patients

Abstract Study question What daily dose of follitropin beta provides a similar ovarian response as single dose of corifollitropin alfa (CFA) in women with different ovarian reserve? Summary answer Regardless of ovarian reserve, a single dose of CFA provides a similar ovarian response as 300 IU/day follitropin beta in IVF/ICSI patients. What is known already A single dose of CFA replaces the first week of stimulation with daily recFSH and provides robust ovarian stimulation due to its unique pharmacokinetic profile. Previous controlled trials in IVF/ICSI patients have demonstrated that CFA yields more oocytes than daily recFSH. In women up to 36 years, on average +2.5 oocytes were obtained in comparison to daily 150 IU recFSH and +1.2 oocytes in comparison to daily 200 IU recFSH, whereas this difference was only +0.5 oocytes in comparison to daily 300 IU recFSH in women aging 35 to 42 years. Study design, size, duration This was a retrospective analysis using individual patient data from 3 large, randomized trials, including 1715 IVF patients receiving a single injection of 100 or 150 mg CFA, followed by daily follitropin beta injections from day 8, and 1577 IVF patients treated with daily follitropin beta with a fixed starting dose of 150 IU, 200 IU or 300 IU for the first week of stimulation. Participants/materials, setting, methods The mean number of oocytes retrieved were estimated for each treatment and predicted response group (Low: AFC≤7 (n = 595), Normal: 8≥AFC≤14 (n = 1899), High: AFC≥15 (n = 808)). Pooling of the three trials was enabled by adjusting for AFC, age, body weight, and the interaction between AFC and age, all as continuous covariates. The dose of follitropin beta corresponding to CFA was estimated by including log(dose) as a covariate in the model. Main results and the role of chance There were similar positive associations between AFC and oocytes and negative associations between age and oocytes following CFA and daily recFSH treatment. There was no clear association between body weight and oocytes following either treatment. A clear increase in number of oocytes was observed with increasing daily doses of recFSH in predicted normal and predicted high responders, but not in predicted low responders. Accordingly, regardless the dose, CFA was providing an ovarian response higher than daily 150 IU or 200 IU recFSH in normal and high responders. The number of oocytes following 100 mg and 150 mg CFA was comparable in all three subsets of predicted responders and similar to the number of oocytes following daily treatment with 300 IU recFSH. The analysis estimated a single dose of 150 mg CFA to be equipotent to daily 300 IU recFSH (95% CI 251-359 IU) and a single dose of 100 mg CFA to be equipotent to 297 IU recFSH daily (95% CI 217-405 IU). Limitations, reasons for caution This retrospective analysis excludes patients with an irregular cycle, suffering from PCOS or having an AFC >20. Thus, the data cannot be extrapolated to these patients Wider implications of the findings Daily doses of recFSH provide dose-related increases of ovarian response in normal and high responders. With CFA treatment, the potential of a single IVF cycle is maximised with an ovarian response comparable to daily 300 IU recFSH, which can be safely managed by GnRH agonist triggering and a freeze-all strategy. Trial registration number NCT00696800, NCT00702845, NCT01144416

Assessment of the Admission and Follow-up Characteristics of Children Diagnosed with Secondary Osteoporosis.

Secondary osteoporosis is a condition when the underlying disease or its treatment causes the bone mass to decrease and the bone structure to deteriorate, increasing the risk of fracture. The importance of diagnosis and treatment during childhood and adolescence is due to its long-term negative effects. In this study, our objectives were to determine the diagnostic findings, treatment efficacy, and follow-up characteristics of childhood with secondary osteoporosis. 61 patients diagnosed with secondary osteoporosis between January 2000 and January 2021 were included in the study. The research is a cross-sectional and descriptive study. Study participants had to be under 18 years of age when the primary underlying disease was diagnosed and received treatment for secondary osteoporosis. Patient data were collected from patient files. Patient data were obtained from patient files in hospitals and were interpreted through the IBM SPSS Statistics for Windows version 20.0 (IBM Corp, Armonk, NY, USA). 61 patients (28 women/33 men) were evaluated. The most common underlying primary diseases in patients with secondary osteoporosis were inflammatory diseases (57.7%), neuromuscular diseases (26.2%), immunodeficiency (13.1%), acute lymphoblastic leukemia (8.2%), metabolic diseases (8.2%), and solid organ transplantation. (8.2%), bone marrow transplantation (6.6%) and epilepsy (6.6%). The average chronological age when secondary osteoporosis was diagnosed was 11.89±4.88 years. They were evaluated for osteoporosis 6.39±5.13 years after the onset of the underlying primary chronic diseases. 78.7% of the patients had one or more chronic drug use. Systemic steroid use was 59%, chemotherapeutics 23%, immunomodulatory drugs 19.7%, antiepileptic drugs 8.2%, inhaled steroids 4.9%, IVIG 1.6%, and antituberculosis drugs 1.6%. Additionally, 1.6% of the patients were using testosterone as replacement, 3.3% L-Thyroxine, 1.6% estrogen, and 1.6% growth hormone. Bone pain was detected in 49.2% of the patients. All patients had vertebral fractures before treatment. Bisphosphonate treatment was given to 45 patients with secondary osteoporosis. There was a statistically significant increase in mean bone mineral density (BMD) and bone mineral content values six months after treatment, (p<0.001). There was a significant increase in BMD Z-score values for chronological and height age (p<0.001). The patients' BMD values increased on average by 31.15% with treatment. Following bisphosphonate treatment, there was a significant reduction in both fracture number and bone pain in patients (p<0.01). When patients who received and did not receive steroid treatment were compared, both groups received similar benefits from bisphosphonate treatment. Secondary osteoporosis is a condition that is influenced by many factors, such as the primary disease causing osteoporosis, chronic medication use, especially steroids. If left untreated, osteoporosis leads to important diseases such as bone pain, bone fractures, immobilization, and reduced linear growth of bone. When used to treat childhood secondary osteoporosis, Bisphosphonates significantly improve BMD and reduce fracture risk.

Can chatbots enhance the management of pediatric sialadenitis in clinical practice?

The purpose of this study was to assess how well ChatGPT, an AI-powered chatbot, performed in helping to manage pediatric sialadenitis and identify when sialendoscopy was necessary. 49 clinical cases of pediatric sialadenitis were retrospectively reviewed. ChatGPT was given patient data, and it offered differential diagnoses, proposed further tests, and suggested treatments. The decisions made by the treating otolaryngologists were contrasted with the answers provided by ChatGPT. Analysis was done on ChatGPT response consistency and interrater reliability. ChatGPT showed 78.57% accuracy in primary diagnosis, and 17.35% of cases were considered likely. On the other hand, otolaryngologists recommended fewer further examinations than ChatGPT (111 vs. 60, p < 0.001). For additional exams, poor agreement was found between ChatGPT and otolaryngologists. Only 28.57% of cases received a pertinent and essential treatment plan via ChatGPT, indicating that the platform's treatment recommendations were frequently lacking. For treatment ratings, judges' interrater reliability was greatest (Kendall's tau = 0.824, p < 0.001). For the most part, ChatGPT's response constancy was high. Although ChatGPT has the potential to correctly diagnose pediatric sialadenitis, there are a number of noteworthy limitations with regard to its ability to suggest further testing and treatment regimens. Before widespread clinical use, more research and confirmation are required. To guarantee that chatbots are utilized properly and effectively to supplement human expertise rather than to replace it, a critical viewpoint is required.