Endoflip vs high‐definition manometry in the assessment of fecal incontinence: A data‐driven unsupervised comparison

• Published in: Neurogastroenterology and motility Vol. 30; no. 12; pp. e13462 - n/a
• Main Authors: Zifan, Ali, Sun, Catherine, Gourcerol, Guillaume, Leroi, Anne M., Mittal, Ravinder K.
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.12.2018; Wiley
• Subjects: Adult; Anorectal; cluster analysis; Fecal incontinence; Fecal Incontinence - diagnosis; Female; functional luminal imaging probe; high‐definition anorectal monetary; Human health and pathology; Humans; Imaging, Three-Dimensional - methods; Learning algorithms; Life Sciences; Machine Learning; Manometry - instrumentation; Manometry - methods; Middle Aged; Pressure; Sensitivity and Specificity; Sphincter; Tissues and Organs; unsupervised learning; Young Adult; cluster analysis; functional luminal imaging probe; high-definition anorectal monetary; unsupervised learning
• ISSN: 1350-1925; 1365-2982; 1365-2982
• DOI: 10.1111/nmo.13462

Background How much anal sphincter dysfunction contributes to fecal incontinence (FI) is not clear. High‐definition anorectal manometry (HDAM) and functional luminal imaging probe (Endoflip) are two new techniques to study anal sphincter function. Aims The goal was to compare the diagnostic utility of HDAM and Endoflip using optimal feature(s) in each modality for FI diagnosis. Methods: Blinded classification was carried out on 70 female subjects (32 FI & 38 controls), using 3 prominent machine‐learning clustering techniques, with 3 distance metrics. For HDAM, descriptive statistics, shape, and textural features characterizing the spatial relationship of pixels in the HDAM high‐pressure zone, and for Endoflip, permutations of pressure and CSA combinations (ie, multiplication, division, or individually) at rest and squeeze were tested. Results Intramodality: (a) Endoflip: Best clustering was obtained using the combination of the ratio of CSA over pressure at 40 and 50 mL at rest, which had significantly better specificity (P < 0.001) than using only pressure at 50 mL, no difference in sensitivity (P = 0.68). (b) HDAM: clustering using textural information at rest had significantly higher specificity compared to using only the maximal pressure at rest (P < 0.001). Intermodality: Clustering results using optimal features were not significantly different with respect to sensitivity or specificity (P > 0.05). Optimal Endoflip feature set differed significantly in specificity compared to HDAM maximal pressure at both rest (P < 0.001) and squeeze (P < 0.001). Conclusion Defective anal closure function is fairly sensitive and highly specific in diagnosing FI. Using optimal feature sets, HDAM and Endoflip perform in a similar fashion in diagnosing FI, but are not complementary. High‐definition anal manometry and functional luminal imaging probe (Endoflip) are two novel techniques to assess the anal closure function; however, their sensitivity and specificity in diagnosing fecal incontinence (FI) are not clear. We used machine‐learning tools to determine the ideal parameters provided by HDAM and Endoflip and performed blinded analysis on a group of FI patients and normal subjects to determine the sensitivity and specificity of two techniques in diagnosing FI. Our data show that both of these techniques are moderately sensitive but highly specific in the FI diagnosing, but they are not complimentary.