Artificial Intelligence and FLIP Panometry—Automated Classification of Esophageal Motility Patterns
Authors:
- Miguel MascarenhasMiguel Mascarenhas
- Francisco MendesFMFrancisco Mendes
- João Rala CordeiroJCJoão Rala Cordeiro
- Joana MotaJMJoana Mota
- Miguel MartinsMMMiguel Martins
- Maria João AlmeidaMAMaria João Almeida
- Catarina AraujoCACatarina Araujo
- Joana FriasJFJoana Frias
- Pedro CardosoPCPedro Cardoso
- Ismael El HajraIHIsmael El Hajra
- António Pinto da CostaACAntónio Pinto da Costa
- Virginia MatallanaVMVirginia Matallana
Open Access
- 5 January 2026
- journal article
- research article
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (1) , 401
Abstract
Background/Objectives: Functional lumen imaging probe (FLIP) panometry allows real-time assessment of the esophagogastric junction opening and esophageal body contractile activity during an endoscopic procedure. Despite the development of the Dallas Consensus, FLIP panometry analysis remains complex. Artificial intelligence (AI) models have proven their benefit in high-resolution esophageal manometry; however, data on their role in FLIP panometry are scarce. This study aims to develop an AI model for automatic classification of motility patterns during a FLIP panometry exam. Methods: A total of 105 exams from five centers from both the European and American continents were included. Several machine learning models were trained and evaluated for detection of FLIP panometry patterns. Each exam was classified with an expert consensus-based decision according to the Dallas Consensus, with division into a training and testing dataset in a patient-split design. Models’ performance was evaluated through their accuracy and area under the receiver-operating characteristic curve (AUC-ROC). Results: Pathological planimetry patterns were identified by an AdaBoost Classifier with 84.9% accuracy and a mean AUC-ROC of 0.92. Random Forest identified disorders of the esophagogastric junction opening with 86.7% accuracy and an AUC-ROC of 0.973. The Gradient Boosting Classifier identified disorders of the contractile response with 86.0% accuracy and an AUC-ROC of 0.933. Conclusions: In this study, integrating exams with different probe sizes and demographic contexts, a machine learning model accurately classified FLIP panometry exams according to the Dallas Consensus. AI-driven FLIP panometry could revolutionize the approach to this exam during an endoscopic procedure, optimizing exam accuracy, standardization, and accessibility, and transforming patient management.Keywords
This publication has 32 references indexed in Scilit:
- Endoscopic Sedation Type During FLIP Panometry Does Not Significantly Impact FLIP Motility Classification Relative to ManometryClinical Gastroenterology and Hepatology, 2024
- Esophageal impedance planimetry during per-oral endoscopic myotomy guides myotomy extentSurgical Endoscopy, 2024
- Artificial Intelligence Tools for Improving Manometric Diagnosis of Esophageal DysmotilityCurrent Gastroenterology Reports, 2024
- The Severity of Reduced Esophageal Distensibility Parallels Eosinophilic Esophagitis Disease DurationClinical Gastroenterology and Hepatology, 2023
- Advances in the Diagnosis and Management of Achalasia and Achalasia-Like Syndromes: Insights From HRM and FLIPGastro Hep Advances, 2023
- POEM and GERD: Prevalence, Mechanisms, Potential Strategies for Prevention, and ManagementClinical Gastroenterology and Hepatology, 2022
- Validation of Clinically Relevant Thresholds of Esophagogastric Junction Obstruction Using FLIP PanometryClinical Gastroenterology and Hepatology, 2022
- A multi-stage machine learning model for diagnosis of esophageal manometryArtificial Intelligence in Medicine, 2021
- Normal Functional Luminal Imaging Probe Panometry Findings Associate With Lack of Major Esophageal Motility Disorder on High-Resolution ManometryClinical Gastroenterology and Hepatology, 2021
- The practical implementation of artificial intelligence technologies in medicineNature Medicine, 2019