Introduction

Pregnancy is common in women with inflammatory bowel disease (IBD), a population in whom optimal obstetric management is essential to ensure maternal and neonatal well-being. Vaginal delivery is generally recommended as the preferred mode of birth due to its lower risk of complications and faster recovery. Unnecessary caesarean section (C-section) delivery increases the risk of maternal complications, such as infection and thrombosis, and may negatively impact neonatal outcomes, including respiratory distress and delayed breastfeeding. Identifying the precise prevalence of C-sections and the factors driving that prevalence in women with IBD is essential to improve care and promote safe, evidence-based delivery planning.

Aims & Methods

To assess the frequency of C-section, and to identify factors associated with the mode of delivery in pregnant women with IBD included in the DUMBO registry.
Patients from DUMBO registry, a prospective multicentre cohort study of pregnant women with IBD in Spain, were included. The registry systematically collects demographic characteristics, obstetric history, IBD phenotype and activity, treatments received during pregnancy, and pregnancy-related complications. Mode of delivery is recorded for all participants. In cases of C-section, investigators document whether the indication was obstetric or IBD-related, as well as the specific reason for the procedure. Logistic regression analysis was performed to identify clinical and disease-related variables independently associated with the likelihood of C-section.

Results

A total of 1,012 women had given birth at the time of data analysis; mean age 34 years (standard deviation 4.8); median IBD duration 8.8 years (interquartile range 4.5–13); 626 (57%) had Crohn’s disease (CD) (21% had perianal disease, 19% active), 216 (19%) had previous surgery due to IBD, 464 (42%) were exposed to biologics, and 122 (11%) had active disease during pregnancy. A total of 293 deliveries (29%) were by C-section. Among C-sections, 237 (81%) were indicated for obstetric reasons, and 56 (19%) for IBD. In univariate analysis, older maternal age, longer IBD duration, to have CD (vs. ulcerative colitis), prior IBD surgery, active perianal disease, and exposure to biologic therapy during pregnancy were significantly more frequent among patients undergoing C-section compared to those with vaginal delivery (table 1). In the multivariate analysis, older maternal age [Odds ratio (OR) = 1.05, 95% confidence interval (CI) = 1.02–1.08], biologic treatment during pregnancy (OR = 1.46, 95%CI 1.08–1.95), prior IBD surgery (OR = 1.47, 95%CI 1.47–2.95), and active perianal disease (OR = 4.89, 95% CI 1.86–12.8) were independently associated with a higher risk of C-section.

Conclusion

One-third of deliveries in women with IBD are by C-section (a figure higher than that in general population¹). In 20% of cases, the indication for C-section was directly related to IBD-specific conditions. Several factors associated with an increased risk of C-section were identified, which are also recognized as predictors of more severe disease. Further efforts are needed to assess the appropriateness of C-section indications and to reduce unnecessary procedures in women with IBD.

References

¹ Ministerio de Sanidad. Annual report on the National Health System of Spain 2023 [Internet]. Madrid: Ministerio de Sanidad; 2023 [accessed 2025 April 14]. p. 86. Available from: https://www.sanidad.gob.es/estadEstudios/estadisticas/sisInfSanSNS/tablasEstadisticas/InfAnualSNS2023/INFORME_ANUAL_2023.pdf

Disclosure

María José Casanova María José Casanova, has received education or research funding from Pfizer, Takeda, Janssen, MSD, Dr. Falk, Shire, Ferring, Galápagos, Abbvie and Lilly.
María Chaparro has served as speaker, consultant or research or education funding from MSD, Abbvie, Hospira, Pfizer, Takeda, Janssen, Ferring, Shire Pharmaceuticals, Dr. Falk Pharma, Tillotts Pharma, Biogen, Gilead and Lilly.
Javier P. Gisbert has served as speaker, consultant, and advisory member for or has received research funding from MSD, Abbvie, Pfizer, Kern Pharma, Biogen, Mylan, Takeda, Janssen, Roche, Sandoz, Celgene/Bristol Myers, Gilead/Galapagos, Lilly, Ferring, Faes Farma, Shire Pharmaceuticals, Dr. Falk Pharma, Tillotts Pharma, Chiesi, Casen Fleet, Gebro Pharma, Otsuka Pharmaceutical, Norgine and Vifor Pharma.
Cristina Calvino-Suarez, has served as a speaker for or has received research funding from MSD, AbbVie, Janssen, Takeda and Adacyte.
Pilar López Serrano has received grants from MSD, Abbvie, Takeda, Janssen, Faes, Ferring and Dr Falk Pharma.
Noemí Manceñido Marcos has served as a speaker and consultant for or received financial support for educational activities from Janssen, Abbvie, Pfizer, Takeda, Ferring, Faes Farma, Dr. Falk Pharma, and Tillots Pharma.
Marta Maia Boscá Watts Conflictos de interés: MSD, Ferring, Abbvie, Janssen, Biogen, Pfizer, Galápagos, Otsuka, Kern pharma y Takeda.
Agnès Fernández-Clotet has served as a speaker, or has recieves education funding from Dr. Falk, Janssen, Takeda, Chiesi and Pfizer.
Lara Arias García has served as speaker or has received research or education funding from MSD; Abbvie; Kern Pharma; Ferring; Faes Farma; Shire Pharmaceuticals; Pfizer; Takeda; Janssen; Tillots Pharma and OtsuKa Pharmaceutical.
Lucía Marquez-Mosquera has been served as speaker and / or has received research or education funds from Abbvie, Pfizer, Takeda, Janssen.
Marta Calvo Moya has served as a speaker, consultant and advisory member for or has received research funding from MSD, Abbvie, Takeda, Jannsen, Pfizer, Lilly, Mylan, Kern Pharma, Ferring, Shire Pharmaceuticals, Tillots, Dr. Falk Pharma, Chiesi, and Gebro Pharma.
Miriam Mañosa has served as a speaker, consultant and advisory member for or has received research funding from AbbVie, Janssen, MSD, Pfizer, Faes, Takeda, Tillots, Ferring.
Vicent Hernández has served as consultant, has served as speaker, has received travel support or research funding from MSD, AbbVie, Ferring, Dr. Falk Pharma, Tillotts Pharma, Pfizer, Takeda, Janssen, KernPharma Biologics, Adacyte, Sandoz, Biogen, Fresenius-Kabi, FAES Farma and Galapagos.
Raquel Camargo-Camero, He recibido financiación para diferentes tipos de actividades formativas de Janssen, Ferring, Abbvie, Falk, Pfizer, Galápagos y Takeda.
Iván Guerra has served as speaker or has received education funding from Takeda and Tillots.
David Busquets declares educational activities, research projects and scientific meetings sponsored by Abbvie, Janssen, Ferring, Pfizer, Tillots Pharma and Takeda.
Montserrat Rivero has served as a speaker or advisory member from TaKeda, Janssen, Galapagos, Ferring and Pfizer.
Iago Rodríguez-Lago has received financial support for traveling and educational activities from or has served as an advisory board member for Abbvie, Adacyte, Celltrion, Chiesi, Danone, Ferring, Faes Farma, Janssen, Galapagos, MSD, Pfizer, Roche, Takeda, and Tillotts Pharma. Financial support for research: Tillotts Pharma.
Rest of authors have nothing to declare.

Introduction

In Early Gastric Cancer(EGC), if the risk of lymph node metastasis(LNM) is negligible, endoscopic curative resection is performed preferentially. If LNM is suspicious, additional gastrectomy with lymphadenectomy should be performed.
Recently, as artificial intelligence has revolutionized medical field, several studies have been conducted to predict LNM applying machine learning in stomach.
The risk of LNM is determined by primary tumor. It is necessary to pick up on fine and diverse morphologic patterns within H&E stained tissue slide.
Therefore, the aim of this study is to develop machine learning algorithm for predicting LNM status in patients with EGC using H&E stained WSI.

Aims & Methods

This multicenter study involved five cohorts, including Hanyang University Guri Hospital (HGH), Kangbuk Samsung Medical Center (KBSMC), Seoul St. Mary’s Hospital (SS), International St. Mary’s Hospital (ISH), and Korea University Medical Center (KUMC). The cohorts were randomly divided into training, validation, and test sets.
Whole slide pathology images were annotated and divided into 512 * 512-pixel patches using ASAP software. Expert pathologists used spline on the rectangle region of interest (ROI) to annotate areas of tumor tissue.
In the first step, Deep Lab V and SE-ResNext101 were trained on 7029 patches from three early gastric cancer (EGC) datasets to segment differentiated and undifferentiated gastric cancer.
In the second step, morphological features inferred by the trained segmentation network from whole slide images (WSI) of primary EGC were used to predict lymph node metastasis (LNM) status.

Results

The data consisted of 243 cases from 5 cohorts. The number of cases in each cohort was 61, 84, 59, 14, and 25, respectively.
The classification results of differentiated/undifferentiated tumor and normal tissue are described.
We represented differentiated tumors as orange, undifferentiated as brown, and normal cells as light orange(apricot color). When visualizing patch images, ground truth, and predictions from both internal and external datasets, we observed significant similarity.
And the performance of the classifier at the patch and slide level, as well as internal and external cohorts.
A mean AUROC of 0.7487 and a mean accuracy of 0.7 were achieved in predicting LNM status in the test set using XGBoost.

Conclusion

Our study is the first proof of concept that machine learning trained with deep learning of whole slide images may be able to predict LNM in early gastric cancer.
The clinical feasibility of this machine learning algorithm could empower clinicians to make informed decisions regarding the appropriate treatment for early gastric cancer patients immediately following biopsy.

Disclosure

No confict