Assessment of colonoscopy skill using machine learning to measure quality: Proof-of-concept and initial validation.

Background and study aims Low-quality colonoscopy increases cancer risk but measuring quality remains challenging. We developed an automated, interactive assessment of colonoscopy quality (AI-CQ) using machine learning (ML). Methods Based on quality guidelines, metrics selected for AI development included insertion time (IT), withdrawal time (WT), polyp detection rate (PDR), and polyps per colonoscopy (PPC). Two novel metrics were also developed: HQ-WT (time during withdrawal with clear image) and WT-PT (withdrawal time subtracting polypectomy time). The model was pre-trained using a self-supervised vision transformer on unlabeled colonoscopy images and then finetuned for multi-label classification on another mutually exclusive colonoscopy image dataset. A timeline of video predictions and metric calculations were presented to clinicians in addition to the raw video using a web-based application. The model was externally validated using 50 colonoscopies at a second hospital. Results The AI-CQ accuracy to identify cecal intubation was 88%. IT ( P = 0.99) and WT ( P = 0.99) were highly correlated between manual and AI-CQ measurements with a median difference of 1.5 seconds and 4.5 seconds, respectively. AI-CQ PDR did not significantly differ from manual PDR (47.6% versus 45.5%, P = 0.66). Retroflexion was correctly identified in 95.2% and number of right colon evaluations in 100% of colonoscopies. HQ-WT was 45.9% of, and significantly correlated with ( P = 0.85) WT time. Conclusions An interactive AI assessment of colonoscopy skill can automatically assess quality. We propose that this tool can be utilized to rapidly identify and train providers in need of remediation.

The Role of High-Resolution Manometry Prior to and Following Antireflux Surgery: The Padova Consensus.

BACKGROUND: In the last two decades the development of high-resolution manometry (HRM) has changed and revolutionized the diagnostic assessment of patients complain foregut symptoms. The role of HRM before and after antireflux procedure remains unclear, especially in surgical practice, where a clear understanding of esophageal physiology and hiatus anatomy is essential for optimal outcome of antireflux surgery (ARS). Surgeons and gastroenterologists (GIs) agree that assessing patients following antireflux procedures can be challenging. Although endoscopy and barium-swallow can reveal anatomic abnormalities, physiologic information on HRM allowing insight into the cause of eventually recurrent symptoms could be key to clinical decision making. METHOD: A multi-disciplinary international working group (14 surgeons and 15 GIs) collaborated to develop consensus on the role of HRM pre- and post- ARS, and to develop a postoperative classification to interpret HRM findings. The method utilized was detailed literature review to develop statements, and the RAND/University of California, Los Angeles Appropriateness Methodology (RAM) to assess agreement with the statements. Only statements with an approval rate >80% or a final ranking with a median score of 7 were accepted in the consensus. The working groups evaluated the role of HRM prior to ARS and the role of HRM following ARS. CONCLUSION: This international initiative developed by surgeons and GIs together, summarizes the state of our knowledge of the use of HRM pre- and post-ARS. The Padova Classification was developed to facilitate the interpretation of HRM studies of patients underwent ARS.

Dysphagia associated with esophageal wall thickening in patients with nonspecific high-resolution manometry findings: Understanding motility beyond the Chicago classification version 4.0.

BACKGROUND: Previous studies have demonstrated that 50% of patients with normal high-resolution manometry (HRM) findings or ineffective esophageal motility (IEM) may have abnormal functional luminal imaging probe (FLIP) results. However, the specific HRM findings associated with abnormal FLIP results are unknown. Herein, we investigated the relationship between nonspecific manometry findings and abnormal FLIP results. METHODS: We retrospectively analyzed 684 patients who underwent HRM at a tertiary care center in Seoul, Korea, based on the Chicago Classification version 4.0 protocol. KEY RESULTS: Among the 684 patients, 398 had normal HRM findings or IEM. Of these 398 patients, eight showed esophageal wall thickening on endoscopic ultrasonography or computed tomography; however, no abnormalities were seen during esophagogastroduodenoscopy. Among these eight patients, seven showed repetitive simultaneous contractions (RSCs) in at least one of the two positions: 61% (±29%) in 10 swallows in the supine position and 51% (±30%) in five swallows in the upright position. Four patients who underwent FLIP had a significantly decreased esophagogastric junction distensibility index (1.0 ± 0.5 m m 2 mmHg - 1 at 60 mL). Two of these patients underwent per-oral endoscopic myotomy (POEM) due to a lack of response to medication. Esophageal muscle biopsy revealed hypertrophic muscle with marginal eosinophil infiltration. CONCLUSIONS & INFERENCES: A subset of patients (2%) with normal HRM findings or IEM and RSCs experienced dysphagia associated with poor distensibility of the thickened esophageal wall. FLIP assessment or combined HRM and impedance protocols may help better define these patients who may respond well to POEM.

Secondary peristalsis and esophagogastric junction distensibility in symptomatic post-fundoplication patients.

BACKGROUND: The impact of esophageal dysmotility among patients with post-fundoplication esophageal symptoms is not fully understood. This study aimed to investigate secondary peristalsis and esophagogastric junction (EGJ) opening biomechanics using functional lumen imaging probe (FLIP) panometry in symptomatic post-fundoplication patients. METHODS: Eighty-seven adult patients post-fundoplication who completed FLIP for symptomatic esophageal evaluation were included. Secondary peristaltic contractile response (CR) patterns and EGJ opening metrics (EGJ distensibility index (EGJ-DI) and maximum EGJ diameter) were evaluated on FLIP panometry and analyzed against high-resolution manometry (HRM), patient-reported outcomes, and fundoplication condition seen on esophagram and/or endoscopy. KEY RESULTS: FLIP CR patterns included 14 (16%) normal CR, 30 (34%) borderline CR, 28 (32%) impaired/disordered CR, 13 (15%) absent CR, and 2 (2%) spastic reactive CR. Compared with normal and borderline CRs (i.e., CR patterns with distinct, antegrade peristalsis), patients with impaired/disordered and absent CRs demonstrated significantly greater time since fundoplication (2.4 (0.6-6.8) vs. 8.9 (2.6-14.5) years; p = 0.002), greater esophageal body width on esophagram (n = 50; 2.3 (2.0-2.8) vs. 2.9 (2.4-3.6) cm; p = 0.013), and lower EGJ-DI (4.3 (2.7-5.4) vs. 2.6 (1.7-3.7) mm2/mmHg; p = 0.001). Intact fundoplications had significantly higher rates of normal CRs compared to anatomically abnormal (i.e., tight, disrupted, slipped, herniated) fundoplications (9 (28%) vs. 5 (9%); p = 0.032), but there were no differences in EGJ-DI or EGJ maximum diameter. CONCLUSIONS & INFERENCES: Symptomatic post-fundoplication patients were characterized by frequent abnormal secondary peristalsis after fundoplication, potentially worsening with time after fundoplication or related to EGJ outflow resistance.

The Severity of Reduced Esophageal Distensibility Parallels Eosinophilic Esophagitis Disease Duration.

BACKGROUND & AIMS: Chronic inflammation of eosinophilic esophagitis (EoE) results in progressive, fibrostenotic remodeling of the esophageal wall. This study aimed to demonstrate objective changes in esophageal distensibility relative to duration of EoE disease using a functional lumen imaging probe (FLIP). METHODS: Adult patients with EoE who completed a 16-cm FLIP protocol during endoscopy were evaluated in a cross-sectional study. FLIP analysis focused on distensibility plateau (DP) of the esophageal body. The time from onset of symptoms to time of endoscopy with FLIP was assessed, as was time from symptom onset to EoE diagnosis (ie, diagnostic delay). RESULTS: A total of 171 patients (mean age 38 ± 12 years; 31% female) were included; the median symptom duration was 8 (interquartile range, 3-15) years and diagnostic delay was 4 (interquartile range, 1-12) years. At the time of endoscopy with FLIP, there were 54 patients (39%) in histologic remission (<15 eosinophils per high-power field [eos/hpf]). Symptom duration and diagnostic delay were negatively correlated with DP (rho = -0.326 and -0.309; P values < .001). Abnormal esophageal distensibility (DP ≤17 mm) was more prevalent with increased duration of symptoms (P < .004): 23% at <5 years to 64% at ≥25 years. When stratifying the cohort based on mucosal eosinophil density, patients with ≥15 eos/hpf had significantly lower DP with greater symptom duration (P = .004), while there was not a significant difference among patients with <15 eos/hpf (P = .060). CONCLUSIONS: Esophageal distensibility objectively measured with FLIP was reduced in EoE patients with greater symptom duration and diagnostic delay. This supports that EoE is a progressive, fibrostenotic disease and that FLIP may be a useful tool to monitor disease progression in EoE.

Temporal correlation between postreperfusion complement deposition and severe primary graft dysfunction in lung allografts.

Growing evidence implicates complement in the pathogenesis of primary graft dysfunction (PGD). We hypothesized that early complement activation postreperfusion could predispose to severe PGD grade 3 (PGD-3) at 72 hours, which is associated with worst posttransplant outcomes. Consecutive lung transplant patients (n = 253) from January 2018 through June 2023 underwent timed open allograft biopsies at the end of cold ischemia (internal control) and 30 minutes postreperfusion. PGD-3 at 72 hours occurred in 14% (35/253) of patients; 17% (44/253) revealed positive C4d staining on postreperfusion allograft biopsy, and no biopsy-related complications were encountered. Significantly more patients with PGD-3 at 72 hours had positive C4d staining at 30 minutes postreperfusion compared with those without (51% vs 12%, P < .001). Conversely, patients with positive C4d staining were significantly more likely to develop PGD-3 at 72 hours (41% vs 8%, P < .001) and experienced worse long-term outcomes. In multivariate logistic regression, positive C4d staining remained highly predictive of PGD-3 (odds ratio 7.92, 95% confidence interval 2.97-21.1, P < .001). Hence, early complement deposition in allografts is highly predictive of PGD-3 at 72 hours. Our data support future studies to evaluate the role of complement inhibition in patients with early postreperfusion complement activation to mitigate PGD and improve transplant outcomes.

Composite score of physiomechanical esophageal function using functional lumen imaging probe panometry in eosinophilic esophagitis.

BACKGROUND AND AIMS: The evaluation provided by functional lumen imaging probe (FLIP) panometry includes esophageal distensibility/compliance (mechanics) of the esophageal body and esophagogastric junction (EGJ) and esophageal motility (secondary peristalsis). We developed a composite score using these parameters to characterize physiomechanical function in patients with eosinophilic esophagitis (EoE). METHODS: Two hundred fifteen adult patients with EoE who completed FLIP panometry during sedated endoscopy with esophageal biopsy sampling were included. FLIP metrics of esophageal body Compliance, Contractile response, Distensibility plateau, and maximum EGJ Diameter (C2D2) were scored as 0 for normal versus 1 or 2 for increasing degree of abnormality. Scores were summed to calculate the composite C2D2 score. RESULTS: The C2D2 score had a significant positive correlation with mucosal eosinophil count (ρ = .241) and total Endoscopic EoE Reference Score (ρ = .467). Among 46 patients off treatment at the baseline evaluation, future proton pump inhibitor (PPI) responders (ie, achieved mucosal eosinophil count <15 per high-powered field after PPI treatment) had lower C2D2 scores than PPI nonresponders (median, 2 [interquartile range, 1-3] vs 4 [interquartile range, 2-6], respectively; P = .003). A regression model (that controlled for age, sex, and baseline eosinophil count) showed a C2D2 score ≤3 had an odds ratio of 14.5 (95% confidence interval, 2.6-85) to predict future PPI response. However, total Endoscopic EoE Reference Scores (P = .142) and baseline eosinophil count (P = .480) did not differ between PPI responders and PPI nonresponders. CONCLUSIONS: This composite score of FLIP panometry metrics, the C2D2 score, may facilitate characterizing physiomechanical function in EoE and serve as an objective outcome measure.

Suprabasal cells retain progenitor cell identity programs in eosinophilic esophagitis-driven basal cell hyperplasia.

Eosinophilic esophagitis (EoE) is an esophageal immune-mediated disease characterized by eosinophilic inflammation and epithelial remodeling, including basal cell hyperplasia (BCH). Although BCH is known to correlate with disease severity and with persistent symptoms in patients in histological remission, the molecular processes driving BCH remain poorly defined. Here, we demonstrate that BCH is predominantly characterized by an expansion of nonproliferative suprabasal cells that are still committed to early differentiation. Furthermore, we discovered that suprabasal and superficial esophageal epithelial cells retain progenitor identity programs in EoE, evidenced by increased quiescent cell identity scoring and the enrichment of signaling pathways regulating stem cell pluripotency. Enrichment and trajectory analyses identified SOX2 and KLF5 as potential drivers of the increased quiescent identity and epithelial remodeling observed in EoE. Notably, these alterations were not observed in gastroesophageal reflux disease. These findings provide additional insights into the differentiation process in EoE and highlight the distinct characteristics of suprabasal and superficial esophageal epithelial cells in the disease.

A PhysioMechanical Model of Esophageal Function in Eosinophilic Esophagitis.

BACKGROUND & AIMS: Eosinophilic esophagitis (EoE) is characterized by eosinophilic inflammation, but also heterogeneous presentations involving fibrostenotic esophageal remodeling and esophageal dysmotility. We aimed to define and evaluate phenotypes of EoE using functional lumen imaging probe (FLIP) panometry (ie, a PhysioMechanical classification of EoE). METHODS: Patients with EoE who completed FLIP during endoscopy were included in a cross-sectional study. FLIP studies were analyzed for distensibility plateau and compliance of the esophageal body, maximum esophagogastric junction diameter, and contractile response pattern. These FLIP features were then applied to define PhysioMechanical classifications. RESULTS: A total of 215 patients with EoE (mean [standard deviation] age 38 [12] years; 31% female) were included. Seven PhysioMechanical classifications were identified that differed by various clinical characteristics, including symptom duration (P < .001) and Endoscopic EoE Reference Scores (EREFS) (P < .001). In particular, patients with "nonreactive fibrostenosis" (n = 14), had greater symptom duration (median [interquartile range] 20 [10-30] years) and more frequently had EREFS grade 2 or 3 ring scores (14 of 14 patients) than patients with a "normal" PhysioMechanical classification (symptom duration: 3 [1-8] years; 4 of 50 [8%] had EREFS grade 2 or 3 rings). In addition, among patients off treatment at cross-sectional evaluation (n = 46), there was a difference between PhysioMechanical classifications in future proton pump inhibitor (PPI) response rates (ie, achieving peak mucosal eosinophil count <15 per high-powered field after PPI treatment); P = .009. PPI response ranged from 87% (13 of 15 patients) with "isolated esophagogastric junction outflow obstruction" to 11% (1 of 9 patients) with "spastic-reactive fibrostenosis." CONCLUSIONS: Classifying PhysioMechanical esophageal function in EoE based on FLIP panometry features may facilitate defining disease severity and directing management in EoE.

An artificial intelligence platform provides an accurate interpretation of esophageal motility from Functional Lumen Imaging Probe Panometry studies.

BACKGROUND: Functional lumen imaging probe (FLIP) Panometry is performed at the time of sedated endoscopy and evaluates esophageal motility in response to distension. This study aimed to develop and test an automated artificial intelligence (AI) platform that could interpret FLIP Panometry studies. METHODS: The study cohort included 678 consecutive patients and 35 asymptomatic controls that completed FLIP Panometry during endoscopy and high-resolution manometry (HRM). "True" study labels for model training and testing were assigned by experienced esophagologists per a hierarchical classification scheme. The supervised, deep learning, AI model generated FLIP Panometry heatmaps from raw FLIP data and based on convolutional neural networks assigned esophageal motility labels using a two-stage prediction model. Model performance was tested on a 15% held-out test set (n = 103); the remainder of the studies were utilized for model training (n = 610). KEY RESULTS: "True" FLIP labels across the entire cohort included 190 (27%) "normal," 265 (37%) "not normal/not achalasia," and 258 (36%) "achalasia." On the test set, both the Normal/Not normal and the achalasia/not achalasia models achieved an accuracy of 89% (with 89%/88% recall, 90%/89% precision, respectively). Of 28 patients with achalasia (per HRM) in the test set, 0 were predicted as "normal" and 93% as "achalasia" by the AI model. CONCLUSIONS: An AI platform provided accurate interpretation of FLIP Panometry esophageal motility studies from a single center compared with the impression of experienced FLIP Panometry interpreters. This platform may provide useful clinical decision support for esophageal motility diagnosis from FLIP Panometry studies performed at the time of endoscopy.

Measuring esophageal compliance using functional lumen imaging probe to assess remodeling in eosinophilic esophagitis.

BACKGROUND: Eosinophilic esophagitis (EoE) is associated with fibrostenotic remodeling that can be objectively assessed using the functional lumen imaging probe (FLIP). This is typically done using a metric called distensibility plateau (DP). We aimed to describe a novel measure of compliance of the esophageal body and evaluate the associated clinical characteristics in EoE. METHODS: One hundred seventy-one adult patients with EoE (mean (SD) age 38 (12) years), 31% female and 35 healthy, asymptomatic controls who completed 16-cm functional luminal imaging probe (FLIP) during endoscopy, were evaluated in a cross-sectional study. The esophageal body DP and compliance were measured using a customized analysis program, with compliance calculated as (Δ esophageal body volume)/(Δ pressure) between two FLIP-filled volumes. RESULTS: In controls, the median (5-95th percentile) DP was 19.8 mm (17.9-21) and esophageal body compliance was 0.37 ml/mmHg (0.18-1.1), which was greater than in EoE (DP 19 (11-21)), compliance 0.19 (0.02-0.71), p-values <0.001. Among EoE patients, 70 (41%) had normal compliance (>0.2 ml/mmHg) and normal DP (>17 mm); 11 (6%) had normal compliance and reduced DP; 34 (20%) had reduced compliance and normal DP; and 56 (33%) had reduced compliance and reduce DP. Patients with both reduced compliance and DP had the greatest proportion of severe rings (61% with EREFS score 2-3) and stricture (100%). CONCLUSION: FLIP provides an objective evaluation of biomechanical properties of the esophageal wall that appears enhanced by complementary application of metrics of DP and esophageal body compliance.

Novel histologic score predicts recurrent intestinal metaplasia after successful endoscopic eradication therapy.

Endoscopic eradication therapy (EET) is an effective treatment for Barrett's esophagus (BE); however, disease recurrence remains problematic requiring surveillance post-treatment. While data regarding predictors of recurrence are limited, uncontrolled reflux may play a significant role. Our aim was to develop a scoring system based on histopathologic reflux in surveillance biopsies following EET to identify patients at high risk for recurrence of BE. Patients were identified from two centers in the treatment with resection and endoscopic ablation techniques for BE consortium. Hematoxylin and eosin-stained slides of surveillance biopsies post-EET were assessed for histologic changes associated with reflux from a cohort of patients who also underwent pH-metry (derivation cohort). We developed a novel scoring system (Recurrent Epithelial Changes from Uncontrolled Reflux [RECUR]) composed of dilated intercellular spaces, epithelial ballooning, basal cell hyperplasia, and parakeratosis, to identify patients with abnormal esophageal acid exposure. This scoring system was then used to grade surveillance biopsies from patients with or without recurrence of BE following EET (validation cohort). Of 41 patients in the derivation cohort, 19.5% had abnormal acid exposure times (AET) while on proton pump inhibitor therapy. The mean (SD) RECUR score for patients with AET <4% was 4.0 (1.6), compared with 5.5 (0.9) for AET ≥4% (P = 0.015). In the validation cohort consisting of 72 patients without recurrence and 64 patients with recurrence following EET, the RECUR score was the only significant predictor of recurrence (odds ratio: 1.36, 95% confidence interval: 1.10-1.69, P = 0.005). Histologic grading of surveillance biopsies using the RECUR scoring system correlates with BE recurrence following EET.

Three Distinct Transcriptional Profiles of Monocytes Associate with Disease Activity in Scleroderma Patients.

OBJECTIVE: Patients with diffuse cutaneous systemic sclerosis (dcSSc) display a complex clinical phenotype. Transcriptional profiling of whole blood or tissue from patients are affected by changes in cellular composition that drive gene expression and an inability to detect minority cell populations. We undertook this study to focus on the 2 main subtypes of circulating monocytes, classical monocytes (CMs) and nonclassical monocytes (NCMs) as a biomarker of SSc disease severity. METHODS: SSc patients were recruited from the Prospective Registry for Early Systemic Sclerosis. Clinical data were collected, as well as peripheral blood for isolation of CMs and NCMs. Age-, sex-, and race-matched healthy volunteers were recruited as controls. Bulk macrophages were isolated from the skin in a separate cohort. All samples were assayed by RNA sequencing (RNA-seq). RESULTS: We used an unbiased approach to cluster patients into 3 groups (groups A-C) based on the transcriptional signatures of CMs relative to controls. Each group maintained their characteristic transcriptional signature in NCMs. Genes up-regulated in group C demonstrated the highest expression compared to the other groups in SSc skin macrophages, relative to controls. Patients from groups B and C exhibited worse lung function than group A, although there was no difference in SSc skin disease at baseline, relative to controls. We validated our approach by applying our group classifications to published bulk monocyte RNA-seq data from SSc patients, and we found that patients without skin disease were most likely to be classified as group A. CONCLUSION: We are the first to show that transcriptional signatures of CMs and NCMs can be used to unbiasedly stratify SSc patients and correlate with disease activity outcome measures.

Functional Lumen Imaging Probe Panometry Helps Identify Clinically Relevant Esophagogastric Junction Outflow Obstruction per Chicago Classification v4.0.

INTRODUCTION: Esophagogastric junction (EGJ) outflow obstruction (EGJOO) per Chicago Classification v4.0 (CCv4.0) represents a high-resolution manometry (HRM) diagnosis with uncertain clinical significance. This study aimed to evaluate functional lumen imaging probe (FLIP) panometry among patients with EGJOO on HRM/CCv4.0 to assess clinical/manometric associations and treatment outcomes. METHODS: An observational cohort study was performed on patients who completed FLIP during endoscopy and had an HRM/CCv4.0 diagnosis of EGJOO, i.e., HRM-EGJOO (inconclusive). Abnormal FLIP panometry motility classifications were applied to identify FLIP-confirmed conclusive EGJOO. Rapid drink challenge on HRM and timed barium esophagram were also assessed. Clinical management plan was determined by treating physicians and assessed through chart review. Clinical outcome was defined using the Eckardt score (ES) during follow-up evaluation: ES < 3 was considered a good outcome. RESULTS: Of 139 adult patients with manometric EGJOO (inconclusive per CCv4.0), a treatment outcome ES was obtained in 55 after achalasia-type treatment (i.e., pneumatic dilation, peroral endoscopic myotomy, laparoscopic Heller myotomy, or botulinum toxin injection) and 36 patients after other nonachalasia-type treatment. Among patients with conclusive EGJOO by HRM-FLIP complementary impression, 77% (33/43) had a good outcome after achalasia-type treatment, whereas 0% (0/12) of patients had a good outcome after nonachalasia-type treatment. Of patients with normal EGJ opening on FLIP, one-third of patients treated with achalasia-type treatment had a good outcome, while 9 of the 10 treated conservatively had a good outcome. DISCUSSION: FLIP panometry provides a useful complement to clarify the clinical significance of an HRM/CCv4.0 EGJOO diagnosis and help direct management decisions.

Identifying hiatal hernia with impedance planimetry during esophageal distension testing.

INTRODUCTION: Functional luminal imaging probe (FLIP) Panometry evaluates the esophageal response to distension involving biomechanics and motility. We have observed that hiatus hernia (HH) is evident during FLIP studies as a separation between the crural diaphragm (CD) and lower esophageal sphincter (LES) like what is seen with high-resolution manometry (HRM). The aim of this study was to compare FLIP findings to endoscopy and HRM in the detection of HH. METHODS: A total of 100 consecutive patients that completed FLIP during sedated endoscopy and HRM were included. LES-CD separation was assessed on FLIP and HRM with the presence of HH defined as LES-CD ≥1 cm. The agreement was evaluated using the kappa (κ) statistic. RESULTS: Hiatal hernia was detected in 32% of patients on HRM and 44% of patients on FLIP with a substantial agreement between studies (84% agreement; κ = 0.667). On FLIP, a 'new' HH (i.e. HH not observed on HRM) occurred in 14 patients and an "enlarged" HH (i.e., LES-CD ≥2 cm larger than on HRM) occurred in 11 patients. Among patients that also completed, timed barium esophagogram (TBE), delayed esophageal emptying on TBE was more common in patients with new or enlarged HH on FLIP than those without: 7/11 (64%) versus 2/12 (17%); p = 0.017. CONCLUSION: FLIP can detect HH with a substantial agreement with HRM, though esophageal distension with FLIP testing appeared to elicit and/or enlarge a HH in an additional 25% of patients. Although this unique response to esophageal distension may represent a mechanism of dysphagia or susceptibility to reflux, additional study is needed to clarify its significance.

Peroral endoscopic myotomy versus pneumatic dilation in treatment-naive patients with achalasia: 5-year follow-up of a randomised controlled trial.

BACKGROUND: 2-year follow-up data from our randomised controlled trial showed that peroral endoscopic myotomy is associated with a significantly higher efficacy than pneumatic dilation as initial treatment of therapy-naive patients with achalasia. Here we report therapeutic success rates in patients treated with peroral endoscopic myotomy compared with pneumatic dilation at the 5-year follow-up. METHODS: We did a multicentre, randomised controlled trial in six hospitals in the Netherlands, Germany, Italy, Hong Kong, and the USA. Adults aged 18-80 years with newly diagnosed symptomatic achalasia (based on an Eckardt score >3) were eligible for inclusion. Patients were randomly assigned (1:1) to peroral endoscopic myotomy or pneumatic dilation using web-based randomisation with a random block size of 8 and stratification according to site. Randomisation concealment for treatment type was double blind until official study enrolment. Treatment was unmasked because of the different technical approach of each procedure. Patients in the pneumatic dilation group were dilated with a single series of 30-35 mm balloons. The need for subsequent dilations in the pneumatic dilation group, and the need for dilation after initial treatment in the peroral endoscopic myotomy group, was considered treatment failure. The primary outcome was therapeutic success (Eckardt score ≤3 in the absence of severe treatment-related complications and no need for retreatment). Analysis of the primary outcome was by modified intention to treat, including all patients randomly assigned to a group, excluding those patients who did not receive treatment or were lost to follow-up. Safety was assessed in all included patients. This study is registered at the Dutch Trial Registry, NTR3593, and is completed. FINDINGS: Between Sept 21, 2012, and July 20, 2015, 182 patients were assessed for eligibility, 133 of whom were included in the study and randomly assigned to peroral endoscopic myotomy (n=67) or pneumatic dilation (n=66). 5-year follow-up data were available for 62 patients in the peroral endoscopic myotomy group and 63 patients in the pneumatic dilation group. 50 (81%) patients in the peroral endoscopic myotomy group had treatment success at 5 years, compared with 25 (40%) in the pneumatic dilation group, an adjusted absolute difference of 41% (95% CI 25-57; p<0·0001). Reasons for failure were no initial effect of treatment (one patient in the peroral endoscopic myotomy group vs 12 patients in the pneumatic dilation group) and recurrent symptoms causing treatment failure (11 patients in the peroral endoscopic myotomy group [seven patients between 2 and 5 years] vs 25 patients in the pneumatic dilation group [nine patients between 2 and 5 years]); one patient in the pneumatic dilation group had treatment failure due to an adverse event. Proton-pump inhibitor use (mostly daily) was significantly higher after peroral endoscopic myotomy than after pneumatic dilation among patients still in clinical remission (23 [46%] of 50 patients vs three [13%] of 24 patients; p=0·008). 5-year follow-up endoscopy of patients still in clinical remission showed reflux oesophagitis in 14 (33%) of 42 patients in the peroral endoscopic myotomy group (12 [29%] grade A or B, two [5%] grade C or D) and two (13%) of 16 patients in the pneumatic dilation group (two [13%] grade A or B, none grade C or D; p=0·19). No intervention-related serious adverse events occurred between 2 and 5 years after treatment. The following non-intervention-related serious adverse events occurred between 2 and 5 years: a stroke (one [2%]) in the peroral endoscopic myotomy group; and death due to a melanoma (one [2%]) and dementia (one [2%]) in the pneumatic dilation group. INTERPRETATION: Based on this study, peroral endoscopic myotomy should be proposed as an initial treatment option for patients with achalasia. Although our study has shown that peroral endoscopic myotomy has greater long-term efficacy with a low risk of major treatment-related complications, this should not lead to abandonment of pneumatic dilation from clinical practice. Ideally, all treatment options should be discussed with treatment-naive patients with achalasia and a shared decision should be made. FUNDING: Fonds NutsOhra and European Society of Gastrointestinal Endoscopy.

Normative values of intra-bolus pressure and esophageal compliance based on 4D high-resolution impedance manometry.

BACKGROUND: This study aimed to quantify normative values of phase-specific intra-bolus pressure (IBP) and esophageal distensibility using 4D analysis of high-resolution-impedance manometry (HRIM). METHODS: HRIM studies of supine swallows from 34 normal controls were analyzed with respect to the four phases of bolus transit: (1) accommodation, (2) compartmentalization, (3) peristalsis/esophageal emptying, and (4) ampullary emptying. Phase-specific IBP, bolus volume, and distensibility index (DI) in the esophageal body and esophagogastric junction (EGJ) during phases 1-3 were extracted. RESULTS: The median (5-95th/IQR) IBP values were as follows: phase 1: 4.0 (-2.0-10.4/1.9-5.8) mmHg, phase 2: 5.7 (0.2-14.1/3.6-8.9) mmHg, and phase 3: 11.2 (2.9-19.4/7.7-15.1) mmHg. The median bolus volume calculated by integrating impedance planimetry cross-sectional areas was 4.1 ml during the compartmentalization phase. The EGJ-DI at max EGJ diameter during phase 2 and 3 was 2.8 (1.1-9.5/1.8-3.7) mm2 /mmHg and 6.0 (3.2-20.3/5.1-7.8) mm2 /mmHg, respectively. The phase 3 EGJ-DI values (6.0 (3.2-20.3/5.1-7.8) mm2 /mmHg) were similar to those calculated using functional lumen imaging probe (FLIP) at the 60 ml volume on the same subjects (5.8 [3.5-7.2/5.0-6.4] mm2 /mmHg). CONCLUSIONS AND INFERENCES: 4D-HRIM provides a standardized methodology to track the nadir impedance and provide measurements of IBP during maximal distention across phases 1-3 of bolus transit. Median IBP and delta IBP were different across the phases, supporting the need to define IBP by phase. Additionally, the EGJ-DI calculated during phase 3 was similar to the 60-ml EGJ-DI from FLIP in the same subjects suggesting that 4D-HRIM can quantify EGJ opening during primary peristalsis.

AGA Clinical Practice Update on the Personalized Approach to the Evaluation and Management of GERD: Expert Review.

BACKGROUND & AIMS: As many as one-half of all patients with suspected gastroesophageal reflux disease (GERD) do not derive benefit from acid suppression. This review outlines a personalized diagnostic and therapeutic approach to GERD symptoms. METHODS: The Best Practice Advice statements presented here were developed from expert review of existing literature combined with extensive discussion and expert opinion to provide practical advice. Formal rating of the quality of evidence or strength of recommendations was not the intent of this clinical practice update. BEST PRACTICE ADVICE 1: Clinicians should develop a care plan for investigation of symptoms suggestive of GERD, selection of therapy (with explanation of potential risks and benefits), and long-term management, including possible de-escalation, in a shared-decision making model with the patient. BEST PRACTICE ADVICE 2: Clinicians should provide standardized educational material on GERD mechanisms, weight management, lifestyle and dietary behaviors, relaxation strategies, and awareness about the brain-gut axis relationship to patients with reflux symptoms. BEST PRACTICE ADVICE 3: Clinicians should emphasize safety of proton pump inhibitors (PPIs) for the treatment of GERD. BEST PRACTICE ADVICE 4: Clinicians should provide patients presenting with troublesome heartburn, regurgitation, and/or non-cardiac chest pain without alarm symptoms a 4- to 8-week trial of single-dose PPI therapy. With inadequate response, dosing can be increased to twice a day or switched to a more effective acid suppressive agent once a day. When there is adequate response, PPI should be tapered to the lowest effective dose. BEST PRACTICE ADVICE 5: If PPI therapy is continued in a patient with unproven GERD, clinicians should evaluate the appropriateness and dosing within 12 months after initiation, and offer endoscopy with prolonged wireless reflux monitoring off PPI therapy to establish appropriateness of long-term PPI therapy. BEST PRACTICE ADVICE 6: If troublesome heartburn, regurgitation, and/or non-cardiac chest pain do not respond adequately to a PPI trial or when alarm symptoms exist, clinicians should investigate with endoscopy and, in the absence of erosive reflux disease (Los Angeles B or greater) or long-segment (≥3 cm) Barrett's esophagus, perform prolonged wireless pH monitoring off medication (96-hour preferred if available) to confirm and phenotype GERD or to rule out GERD. BEST PRACTICE ADVICE 7: Complete endoscopic evaluation of GERD symptoms includes inspection for erosive esophagitis (graded according to the Los Angeles classification when present), diaphragmatic hiatus (Hill grade of flap valve), axial hiatus hernia length, and inspection for Barrett's esophagus (graded according to the Prague classification and biopsied when present). BEST PRACTICE ADVICE 8: Clinicians should perform upfront objective reflux testing off medication (rather than an empiric PPI trial) in patients with isolated extra-esophageal symptoms and suspicion for reflux etiology. BEST PRACTICE ADVICE 9: In symptomatic patients with proven GERD, clinicians should consider ambulatory 24-hour pH-impedance monitoring on PPI as an option to determine the mechanism of persisting esophageal symptoms despite therapy (if adequate expertise exists for interpretation). BEST PRACTICE ADVICE 10: Clinicians should personalize adjunctive pharmacotherapy to the GERD phenotype, in contrast to empiric use of these agents. Adjunctive agents include alginate antacids for breakthrough symptoms, nighttime H2 receptor antagonists for nocturnal symptoms, baclofen for regurgitation or belch predominant symptoms, and prokinetics for coexistent gastroparesis. BEST PRACTICE ADVICE 11: Clinicians should provide pharmacologic neuromodulation, and/or referral to a behavioral therapist for hypnotherapy, cognitive behavioral therapy, diaphragmatic breathing, and relaxation strategies in patients with functional heartburn or reflux disease associated with esophageal hypervigilance reflux hypersensitivity and/or behavioral disorders. BEST PRACTICE ADVICE 12: In patients with proven GERD, laparoscopic fundoplication and magnetic sphincter augmentation are effective surgical options, and transoral incisionless fundoplication is an effective endoscopic option in carefully selected patients. BEST PRACTICE ADVICE 13: In patients with proven GERD, Roux-en-Y gastric bypass is an effective primary anti-reflux intervention in obese patients, and a salvage option in non-obese patients, whereas sleeve gastrectomy has potential to worsen GERD. BEST PRACTICE ADVICE 14: Candidacy for invasive anti-reflux procedures includes confirmatory evidence of pathologic GERD, exclusion of achalasia, and assessment of esophageal peristaltic function.

Deep learning-based artificial intelligence model for identifying swallow types in esophageal high-resolution manometry.

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.