Achalasia subtypes can be identified with functional luminal imaging probe (FLIP) panometry using a supervised machine learning process. Issue 3 (1st July 2020)

• Record Type: Journal Article
• Authors: Carlson, Dustin A.; Kou, Wenjun; Rooney, Katharine P.; Baumann, Alexandra J.; Donnan, Erica; Triggs, Joseph R.; Teitelbaum, Ezra N.; Holmstrom, Amy; Hungness, Eric; Sethi, Sajiv; Kahrilas, Peter J.; Pandolfino, John E.
• Is Part Of: Neurogastroenterology & motility. Volume 33:Issue 3(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-07-01
• Subjects: dysphagia -- endoscopy -- impedance -- manometry -- peristalsis; Gastrointestinal system -- Motility -- Periodicals; Gastrointestinal system -- Innervation -- Periodicals; 616.33
• DOI: 10.1111/nmo.13932
• Languages: English
• ISSNs: 1350-1925

Abstract

Abstract: Background: Achalasia subtypes on high‐resolution manometry (HRM) prognosticate treatment response and help direct management plan. We aimed to utilize parameters of distension‐induced contractility and pressurization on functional luminal imaging probe (FLIP) panometry and machine learning to predict HRM achalasia subtypes. Methods: One hundred eighty adult patients with treatment‐naïve achalasia defined by HRM per Chicago Classification (40 type I, 99 type II, 41 type III achalasia) who underwent FLIP panometry were included: 140 patients were used as the training cohort and 40 patients as the test cohort. FLIP panometry studies performed with 16‐cm FLIP assemblies were retrospectively analyzed to assess distensive pressure and distension‐induced esophageal contractility. Correlation analysis, single tree, and random forest were adopted to develop classification trees to identify achalasia subtypes. Key Results: Intra‐balloon pressure at 60 mL fill volume, and proportions of patients with absent contractile response, repetitive retrograde contractile pattern, occluding contractions, sustained occluding contractions (SOC), contraction‐associated pressure changes >10 mm Hg all differed between HRM achalasia subtypes and were used to build the decision tree‐based classification model. The model identified spastic (type III) vs non‐spastic (types I and II) achalasia with 90% and 78% accuracy in the train and test cohorts, respectively. Achalasia subtypes I, II, and III were identified with 71% and 55% accuracy in the train and test cohorts, respectively. Conclusions and Inferences: Using a supervised machine learning process, a preliminary model was developed that distinguished type III achalasia from non‐spastic achalasia with FLIP panometry. Further refinement of the measurements and more experience (data) may improve its ability for clinically relevant application. Abstract : A supervised machine learning model was developed that utilized FLIP panometry parameters to distinguish type III achalasia from non‐spastic achalasia. These approaches can be applied to detect achalasia subtypes using FLIP panometry and may also complement HRM to identify specific clinical phenotypes of achalasia.