Introduction

In the United Kingdom (UK), the Royal College of Obstetricians and Gynaecology (RCOG) recommend that women who have sustained an obstetric anal sphincter injury (OASI) should undergo anorectal physiology testing (ARPT) to inform mode of delivery (MOD), where services are available [1]. ARPT is comprised of endoanal ultrasound (EAUS) which is considered the gold standard for assessing anal sphincter integrity [2,3], and high-resolution anorectal manometry (HR-ARM) for assessing motor and sensory function. However access to such services in the UK are limited, with 12.5% and 3.8% of women offered EAUS and ARM studies, respectively [2,4].

Aims & Methods

The prospective service evaluation assessed the impact of OASIs on anal sphincter anatomy and function, and reviewed the value of ARPT in MOD decision making.
Patients referred for MOD decision making underwent EAUS with the BK medical 3000 system with a 3D anorectal transducer (20R3' 6–16 MHz 360°) and HR-ARM with the Laborie water-perfused system. HR-ARM was performed in accordance with a limited version of the international anorectal physiology working group standardized testing protocol [5], and subsequently analysed in accordance with the London Classification of Anorectal Disorders [5]. Following discussion at a multi-disciplinary team meeting, patients were counselled with the ARPT results by their obstetrician in line with published guidance [6]. Postal feedback surveys were sent post-partum to assess patient experience and the impact of ARPT results on their delivery.

Results

24 pregnant patients with a previous OASI attended for ARPT during a 15 month period. Abnormalities which would encourage counselling for a C-section were identified in 12 patients. 7/12 patients had an external anal sphincter (EAS) defect >30°, 4 of which also had disruption to the internal anal sphincter (IAS). All 7 patients had normal anal contractility on HR-ARM. 1/7 patients had a hypotensive anal canal, disrupted IAS and reported faecal incontinence despite a normal stool consistency. 5/12 patients had anal hypocontractility on HR-ARM; 4 of whom had faecal urgency.
13 patients reported bowel symptoms, with the majority reporting faecal urgency (n=10) and 1 patient reporting Irritable Bowel Syndrome. Of the 13 symptomatic patients, EAUS identified significant defects in 15%, and HR-ARM identified abnormal tone or contractility in 31%. No symptomatic patients were identified to have a major or minor disorder of rectal sensation. 2 urgency patients reported loose stool.
6/18 (33%) patients completed feedback surveys after their delivery. All patients reported that counselling with ARPT results influenced their MOD decision, with 20% changing their intended MOD following ARPT. All patients were satisfied with their MOD choice.

Conclusion

HR-ARM identified 5 patients for C-section counselling, in addition to 7 patients identified by EAUS. There appeared to be poor agreement between EAUS defects and impaired manometric function. EAUS and HR-ARM identified significant anal sphincter impairment in 15% and 31% of symptomatic patients, respectively. This suggests that EAUS may lack sensitivity for identifying symptomatic cohorts, and that HR-ARM abnormality may be a more sensitive indicator of symptomology. This highlights the need to increase HR-ARM provision in perineal services.
Whilst the RCOG recommends counselling with the option of a C-section in all of the patients in this cohort [1], these findings suggest HR-ARM in addition to EAUS may offer a more individualised and collaborative approach to MOD delivery decision making.

References

1. The Management of Third-and Fourth-Degree Perineal Tears Green-top Guideline No. 29. 2015. Available from: https://www.rcog.org.uk/media/5jeb5hzu/gtg-29.pdf. Accessed 24/04/2025.
2. Badri H, et al. The role of anal manometry in the follow-up of women with obstetric anal sphincter injuries (OASI) . Int Urogynecol J. 2023;34:399–404.
3. Santoro GA, et al. State of the art: an integrated approach to pelvic floor ultrasonography. Ultrasound Obstet Gynecol. 2011;37(4):381–96.
4. Ismail SIMF. The management of obstetric anal sphincter injuries (OASIS): A national postal questionnaire survey in hospitals in the UK. J Obstet Gynaecol. 2015;35(3):229–34.
5. Carrington EV, et al. The international anorectal physiology working group (IAPWG) recommendations: Standardized testing protocol and the London classification for disorders of anorectal function. Neurogastroenterology and motility. 2020;32(1): e13679.
6. Jordan PA, et al. Effect of subsequent vaginal delivery on bowel symptoms and anorectal function in women who sustained a previous obstetric anal sphincter injury. International Urogynaecology Journal. 2018;29(11):579-1588.

Introduction

Esophageal motility disorders are common in the clinical practice, with impact in patient’s quality of life. High-resolution esophageal manometry (HREM) is the gold standard for evaluation of patients with functional esophageal disorders. The Chicago Classification offers a standardized approach HREM, reducing bias and enabling a precise diagnosis of these disorders. Despite these, HREM remains a complex exam, both in data analysis and in accessibility. This proof-of-concept study aims to develop and validate an artificial intelligence model for identification of motility disorders in HREM according to the Chicago Classification.

Aims & Methods

618 HREM exams from two different devices and three centers from Spain and the United States of America were used for model development. Several machine learning models were trained and evaluated for detection of motility disorders. The exams were classified according to the Chicago Classification 4.0, based on a consensus reached by two independent HREM experts. The training and testing dataset were divided in a 80%/20% patient split design based on label frequency. Models’ performance was evaluated through their accuracy and area under the receiver-operating characteristic curve (AUC-ROC).

Results

The GradientBoostingClassifier model outperformed the remaining machine learning models with an accuracy of 94.2% and an AUCROC of 0.921 for identifying disorders of esophagogastric junction outflow. The xGBClassifier model detected disorders of peristalsis with an accuracy of 80.9% and an AUC-ROC of 0.871.

Conclusion

In this pilot study with integration of exams from different devices and demographic contexts, several machine learning models accurately identified disorders of the esophagogastric junction outflow and peristalsis in HREM according to Chicago Classification.
The integration of AI into the study of esophageal motility disorders through HREM-driven diagnosis is expected to revolutionize the way these conditions are managed, optimizing both exam accuracy and accessibility, transforming patient management.

Introduction

Timed barium esophagogram (TBE) is widely used to evaluate esophageal clearance (EC) after peroral endoscopic myotomy (POEM) in achalasia. However, high-resolution impedance manometry (HRiM) offers a dynamic, radiation-free alternative, potentially more accurate and reflective of true esophageal function.

Aims & Methods

To compare EC assessed by HRiM (EC_HRiM) and TBE (EC_TBE) after POEM for achalasia, and to evaluate their diagnostic performance, reproducibility, and predictive value for long-term clinical success, with external validation.
We conducted a monocentric prospective study between October 2020 and September 2023. Patients undergoing POEM were assessed pre- and post-procedure using Eckardt score, HRiM, and TBE. Treatment failure was defined by an Eckardt score >3 at 12 months. EC impairment was defined as a residual column height >5 cm at 5 minutes. In parallel, we validated our findings in an independent cohort. Statistical correlations and diagnostic performance were analyzed using Spearman, Pearson, ICC, and ROC curve analyses.

Results

In the primary cohort (n=104; 65% male; median age 62; 75% with type II achalasia; 30% had prior treatment, mainly dilation), 97 patients completed the 12-month follow-up, with a POEM success rate of 90%. EC significantly improved post-POEM on both modalities (HRiM: −8.9 cm; TBE: −4.9 cm; p<0.001). Interobserver reproducibility of EC measurement was higher for HRiM (ICC =0.98) than for TBE (ICC=0.93) (p<0.001). EC_HRiM correlated more strongly with clinical outcomes (Spearman r = 0.68) than EC_TBE (r = 0.37). In univariate analysis, significant predictors of failure were EC_HRiM (p<0.001), 3-month Eckardt score (p<0.001), and EC_TBE (p<0.001). The most discriminative thresholds were EC_HRiM < 0 cm and EC_TBE < 9 cm. Diagnostic performance of HRiM at this threshold was: Se = 66%, Sp = 82%, PPV = 30%, NPV = 95%. For TBE, the same values were: Se = 100%, Sp = 59%, PPV = 19%, NPV = 100%.
In the external validation cohort (median age: 66.5 years; 55.7% male; 50.8% with type II achalasia), the 12-month failure rate was 14.8%. Diagnostic performance of HRiM for predicting clinical FAILURE in this cohort showed: sensitivity 55.6%, specificity 82.7%, PPV 35.7%, and NPV 91.5%, confirming its utility in real-world settings.

Conclusion

HRiM is a reliable, reproducible tool for assessment of esophageal clearance post-POEM and shows stronger correlation with clinical outcomes than TBE. Its predictive value was confirmed in an external validation cohort, supporting its potential as a new standard in achalasia management.

Disclosure

None