BACKGROUND: This study aimed to build and evaluate a deep learning, artificial intelligence (AI) model to automatically classify swallow types based on raw data from esophageal high-resolution manometry (HRM). METHODS: HRM studies on patients with no history of esophageal surgery were collected including 1,741 studies with 26,115 swallows labeled by swallow type (normal, hypercontractile, weak-fragmented, failed, and premature) by an expert interpreter per the Chicago Classification. The dataset was stratified and split into train/validation/test datasets for model development. Long short-term memory (LSTM), a type of deep-learning AI model, was trained and evaluated. The overall performance and detailed per-swallow type performance were analyzed. The interpretations of the supine swallows in a single study were further used to generate an overall classification of peristalsis. KEY RESULTS: The LSTM model for swallow type yielded accuracies from the train/validation/test datasets of 0.86/0.81/0.83. The model's interpretation for study-level classification of peristalsis yielded accuracy of 0.88 in the test dataset. Among model misclassification, 535/698 (77%) swallows and 25/35 (71%) studies were to adjacent categories, for example, normal to weak or normal to ineffective, respectively. CONCLUSIONS AND INFERENCES: A deep-learning AI model can automatically and accurately identify the Chicago Classification swallow types and peristalsis classification from raw HRM data. While future work to refine this model and incorporate overall manometric diagnoses are needed, this study demonstrates the role that AI will serve in the interpretation and classification of esophageal HRM studies.
BACKGROUND: This study aimed to build and evaluate a deep learning, artificial intelligence (AI) model to automatically classify swallow types based on raw data from esophageal high-resolution manometry (HRM). METHODS: HRM studies on patients with no history of esophageal surgery were collected including 1,741 studies with 26,115 swallows labeled by swallow type (normal, hypercontractile, weak-fragmented, failed, and premature) by an expert interpreter per the Chicago Classification. The dataset was stratified and split into train/validation/test datasets for model development. Long short-term memory (LSTM), a type of deep-learning AI model, was trained and evaluated. The overall performance and detailed per-swallow type performance were analyzed. The interpretations of the supine swallows in a single study were further used to generate an overall classification of peristalsis. KEY RESULTS: The LSTM model for swallow type yielded accuracies from the train/validation/test datasets of 0.86/0.81/0.83. The model's interpretation for study-level classification of peristalsis yielded accuracy of 0.88 in the test dataset. Among model misclassification, 535/698 (77%) swallows and 25/35 (71%) studies were to adjacent categories, for example, normal to weak or normal to ineffective, respectively. CONCLUSIONS AND INFERENCES: A deep-learning AI model can automatically and accurately identify the Chicago Classification swallow types and peristalsis classification from raw HRM data. While future work to refine this model and incorporate overall manometric diagnoses are needed, this study demonstrates the role that AI will serve in the interpretation and classification of esophageal HRM studies.
Authors: Omer F Ahmad; Antonio S Soares; Evangelos Mazomenos; Patrick Brandao; Roser Vega; Edward Seward; Danail Stoyanov; Manish Chand; Laurence B Lovat Journal: Lancet Gastroenterol Hepatol Date: 2018-12-06
Authors: Dustin A Carlson; Karthik Ravi; Peter J Kahrilas; C Prakash Gyawali; Arjan J Bredenoord; Donald O Castell; Stuart J Spechler; Magnus Halland; Navya Kanuri; David A Katzka; Cadman L Leggett; Sabine Roman; Jose B Saenz; Gregory S Sayuk; Alan C Wong; Rena Yadlapati; Jody D Ciolino; Mark R Fox; John E Pandolfino Journal: Am J Gastroenterol Date: 2015-06-02 Impact factor: 10.864
Authors: John E Pandolfino; Sudip K Ghosh; John Rice; John O Clarke; Monika A Kwiatek; Peter J Kahrilas Journal: Am J Gastroenterol Date: 2007-09-26 Impact factor: 10.864