Chey, W. D. | bioRxiv Science

bioRxiv2021

Video-Based Deep Learning to Detect Dyssynergic Defecation with 3D High-Definition Anorectal Manometry

BACKGROUND AND AIMSEvaluation for dyssynergia is the most common reason that gastroenterologists refer patients for anorectal manometry, because dyssynergia is amenable to biofeedback by physical therapists. High-definition anorectal manometry (3D-HDAM) is a promising technology to evaluate anorectal physiology, but adoption remains limited by its sheer complexity. We developed a 3D-HDAM deep learning algorithm to evaluate for dyssynergia. METHODSSpatial-temporal data were extracted from consecutive 3D-HDAM studies performed between 2018-2020 at a tertiary institution. The technical procedure and gold standard definition of dyssynergia were based on the London consensus, adapted to the needs of 3D-HDAM technology. Three machine learning models were generated: (1) traditional machine learning informed by conventional anorectal function metrics, (2) deep learning, and (3) a hybrid approach. Diagnostic accuracy was evaluated using bootstrap sampling to calculate area-under-the-curve (AUC). To evaluate overfitting, models were validated by adding 502 simulated defecation maneuvers with diagnostic ambiguity. RESULTS302 3D-HDAM studies representing 1,208 simulated defecation maneuvers were included (average age 55.2 years; 80.5% women). The deep learning model had comparable diagnostic accuracy (AUC=0.91 [95% confidence interval 0.89-0.93]) to traditional (AUC=0.93[0.92-0.95]) and hybrid (AUC=0.96[0.94-0.97]) predictive models in training cohorts. However, the deep learning model handled ambiguous tests more cautiously than other models; the deep learning model was more likely to designate an ambiguous test as inconclusive (odds ratio=4.21[2.78-6.38]) versus traditional/hybrid approaches. CONCLUSIONSBy considering complex spatial-temporal information beyond conventional anorectal function metrics, deep learning on 3D-HDAM technology may enable gastroenterologists to reliably identify and manage dyssynergia in broader practice.

bioinformatics↗

bioRxiv2020

Comparison of Anorectal Function Measured using Wearable Digital Manometry and a High Resolution Manometry System.

There is a need for a lower cost manometry system for assessing anorectal function in primary and secondary care settings. We developed an index finger-based system (termed "digital manometry") and tested it in healthy volunteers, patients with chronic constipation, and fecal incontinence. Anorectal pressures were measured in 16 participants with the digital manometry system and a 23-channel high-resolution anorectal manometry system. The results were compared using a Bland-Altman analysis at rest as well as during maximum squeeze and simulated defecation maneuvers. Myoelectric activity of the puborectalis muscle was also quantified simultaneously using the digital manometry system. The limits of agreement between the two methods were -7.1 {+/-} 25.7 mmHg for anal sphincter resting pressure, 0.4 {+/-} 23.0 mmHg for the anal sphincter pressure change during simulated defecation, -37.6 {+/-} 50.9 mmHg for rectal pressure changes during simulated defecation, and -20.6 {+/-} 172.6 mmHg for anal sphincter pressure during the maximum squeeze maneuver. The change in the puborectalis myoelectric activity was proportional to the anal sphincter pressure increment during a maximum squeeze maneuver (slope = 0.6, R2 = 0.4). Digital manometry provided a similar evaluation of anorectal pressures and puborectalis myoelectric activity at an order of magnitude less cost than high-resolution manometry, and with a similar level of patient comfort. Digital Manometry provides a simple, inexpensive, point of service means of assessing anorectal function in patients with chronic constipation and fecal incontinence.

bioengineering↗