Curcumin-QingDai Combination for Patients With Active Ulcerative Colitis: A Randomized, Double-Blinded, Placebo-Controlled Trial.

BACKGROUND & AIMS: We evaluated the efficacy of herbal combination of curcumin-QingDai (CurQD) in active ulcerative colitis (UC). METHODS: Part I was an open-label trial of CurQD in patients with active UC, defined by a Simple Clinical Colitis Activity Index score of 5 or higher and a Mayo endoscopic subscore of 2 or higher. Part II was a placebo-controlled trial conducted in Israel and Greece, randomizing active UC patients at a 2:1 ratio to enteric-coated CurQD 3 g/d or placebo for 8 weeks. The co-primary outcome was clinical response (reduction in the Simple Clinical Colitis Activity Index of ≥3 points) and an objective response (Mayo endoscopic subscore improvement of ≥1 or a 50% fecal calprotectin reduction). Responding patients continued either maintenance curcumin or placebo alone for an additional 8 weeks. Aryl-hydrocarbon receptor activation was assessed by cytochrome P450 1A1 (CYP1A1) mucosal expression. RESULTS: In part I, 7 of 10 patients responded and 3 of 10 achieved clinical remission. Of 42 patients in part II, the week 8 co-primary outcome was achieved in 43% and 8% of CurQD and placebo patients, respectively (P = .033). Clinical response was observed in 85.7% vs 30.7% (P < .001), clinical remission in 14 of 28 (50%) vs 1 of 13 (8%; P = .01), a 50% calprotectin reduction in 46.4% vs 15.4% (P = .08), and endoscopic improvement in 75% vs 20% (P = .036) in the CurQD and placebo groups, respectively. Adverse events were comparable between groups. By week 16, curcumin-maintained clinical response, clinical remission, and clinical biomarker response rates were 93%, 80%, and 40%, respectively. CurQD uniquely up-regulated mucosal CYP1A1 expression, which was not observed among patients receiving placebo, mesalamine, or biologics. CONCLUSIONS: In this placebo-controlled trial, CurQD was effective for inducing response and remission in active UC patients. The aryl-hydrocarbon receptor pathway may merit further study as a potential UC treatment target. CLINICALTRIALS: gov ID: NCT03720002.

Pro-motility Preparation Protocol May Reduce the Rates of Failed Patency Capsule Among Patients with Crohn's Disease in Clinical Remission.

BACKGROUND: Patency capsule (PC) ingestion is commonly used to minimize capsule retention in high-risk patients with Crohn's disease (CD). However, false-positive rates remain high, precluding the use of video capsule endoscopy (VCE). We aimed to compare the efficacy of two preparation protocols in reducing failed PC rates in patients with CD. METHODS: This bi-center retrospective case-control study included adult patients with small-bowel CD in clinical remission who underwent PC ingestion. The pro-motility group followed a low-residue diet, then a clear fluid diet, and took bisacodyl after ingestion, while the control group followed only a clear fluid diet. The primary outcome was failed PC, defined as the absence of PC excretion or presence on abdominal X-ray at 30 h post-ingestion. Multivariable logistic regression was used to identify predictors of failed PC. RESULTS: Among 273 patients (83 in the pro-motility group, 190 controls), the pro-motility group was older (median 36 [27-48] vs. 31 [24-43], p = 0.012) and had a lower rate of B2/3 disease phenotype (32.5 vs. 53.1%, p = 0.002) compared to controls. The pro-motility group also had a lower failed PC rate (12.0 vs. 24.7%, p = 0.023). Longer disease duration (adjusted odds ratio (AOR) 1.053, 95% confidence interval (CI) 1.016-1.091, p = 0.005) increased the odds of failed PC, while the pro-motility protocol was protective (AOR 0.438, 95% CI 0.200-0.956, p = 0.038), outweighing the influence of B2/3 disease phenotype (AOR 1.743, 95% CI 0.912-3.332, p = 0.093). CONCLUSIONS: The pro-motility preparation protocol could substantially improve the success rates of the small-bowel patency test in patients with CD undergoing PC ingestion, potentially reducing the risk of capsule retention and associated complications.

Towards AI-Augmented Clinical Decision-Making: An Examination of ChatGPT's Utility in Acute Ulcerative Colitis Presentations.

This study explores the potential of OpenAI's ChatGPT as a decision support tool for acute ulcerative colitis presentations in the setting of an emergency department. We assessed ChatGPT's performance in determining disease severity using TrueLove and Witts criteria and the necessity of hospitalization for patients with ulcerative colitis, comparing results with those of expert gastroenterologists. Of 20 cases, ChatGPT's assessments were found to be 80% consistent with gastroenterologist evaluations and indicated a high degree of reliability. This suggests that ChatGPT could provide as a clinical decision support tool in assessing acute ulcerative colitis, serving as an adjunct to clinical judgment.

Patency Capsule: A Novel Independent Predictor for Long-Term Outcomes Among Patients With Quiescent Crohn's Disease.

INTRODUCTION: Patency capsule (PC) is a recommended procedure to rule out small bowel stenosis before video capsule endoscopy (VCE). We examined future clinical outcomes among patients with a failed PC vs patients in whom the PC had passed (passed PC). METHODS: A post hoc analysis of 2 prospective cohort studies of adult patients with quiescent small bowel Crohn's disease (CD) who underwent PC between 2013 and 2020. The primary composite outcome was the need for intestinal surgery or endoscopic dilation during follow-up in patients with or without a failed PC. RESULTS: A total of 190 patients were included (47: failed PC and 143: passed PC, median follow-up 34.12 months). Patients with a failed PC had higher rates of the primary composite outcome (21.3% vs 1.4%, hazard ratio [HR] 20.3, 95% confidence interval [CI] 4.4-93.7, P < 0.001) and also secondary outcomes including intestinal surgery (14.9% vs 0.70%, P < 0.001), endoscopic dilation (14.9% vs 0.70%, P < 0.001), admissions (23.3% vs 5.7%, P < 0.001), and clinical flares (43.9% vs 27.7%, P = 0.005) during follow-up compared with controls. Failed PC was the only statistically significant factor for surgery and/or endoscopic dilation, regardless of a B2/B3 phenotype at baseline. In sensitivity analyses restricted only to patients with a stricturing phenotype (n = 73), a failed PC still predicted the long-term composite outcome (HR 8.68, 95% CI 1.72-43.68, P = 0.002). Of the 190 patients ingesting a PC, only 1 patient with a failed PC had 48 hours of self-limiting mild symptoms. DISCUSSION: Patients with clinically stable CD with a failed PC have worse long-term clinical outcomes than those without, independently of the CD phenotype. Standalone PC may serve as a novel, safe, and affordable prognostic examination to identify patients with quiescent CD who have a higher risk for future worse clinical outcomes.

Association of fibromyalgia with cancerous and non-cancerous gastrointestinal comorbidities: a cross-sectional study.

OBJECTIVES: Several studies have shown a higher prevalence of irritable bowel syndrome (IBS) among patients with fibromyalgia yet, data regarding association between fibromyalgia and other gastrointestinal disorders have been relatively overlooked. Our aim was to investigate the association between fibromyalgia and gastrointestinal disorders including both benign and malignant conditions. METHODS: We conducted a retrospective cross-sectional study based on the comprehensive electronic database of the largest health maintenance organisation in Israel. All subjects with a diagnosis of fibromyalgia in their medical records and age- and sex-matched controls were included in the study. We investigated the association of fibromyalgia with benign gastrointestinal disorders including IBS, gastroesophageal reflux disease (GERD), peptic ulcer disease (PUD), celiac disease, Crohn's disease, ulcerative colitis, and with gastrointestinal malignancies including colorectal, pancreatic, stomach, liver, and bile duct cancers. RESULTS: The study enrolled 18,598 patients with fibromyalgia and 36,985 controls. The mean age was 56.5 years (standard deviation=14) with a female predominance (91%). Fibromyalgia was significantly associated with IBS (OR 4.61, 95% CI 4.09-5.2, p<0.001), GERD (OR 2.62, 95% CI 2.5-2.75, p<0.001), PUD (OR 2.13, 95% CI 1.98-2.3, p<0.001), celiac disease (OR 2.08, 95% CI 1.63-2.65, p<0.001), Crohn's disease (OR 1.85, 95% CI 1.408-2.32, p<0.001) and ulcerative colitis (OR 1.81, 95%CI 1.4-2.33, p<0.001). Nonetheless, no significant differences were found regarding the prevalence of gastrointestinal malignancies between the fibromyalgia patients and controls. CONCLUSIONS: Our findings suggest that FM is positively associated with various benign but not malignant GI disorders.

Risk of colorectal advanced neoplasia in patients with acute diverticulitis with and without previous colonoscopy.

BACKGROUND AND AIM: Guidelines recommend a colonoscopy after an episode of complicated diverticulitis and after a first episode of uncomplicated diverticulitis. The influence of a previous colonoscopy on postdiverticulitis colonoscopic findings has not been studied. The aim of this work was to examine the incidence of adenoma detection rate (ADR), advanced adenoma (AA) and colorectal cancer (CRC) in patients with diverticulitis with and without previous colonoscopy. METHOD: This was a retrospective case-control study of subjects with acute diverticulitis. Subsequent and previous colonoscopies were abstracted for ADR, AA and CRC diagnoses. The incidence of neoplasia was compared between patients with and without previous colonoscopy and also with that of a screening population. RESULTS: Compared with a healthy control group (n = 975), diverticulitis patients without prior colonoscopy (n = 325) had a significantly higher ADR (26.8% vs. 20.5%, p = 0.019) and invasive CRC rate (0.9% vs. 0%, p = 0.016). Risk factors for advanced neoplasia included age ≥ 70 years and complicated diverticulitis. Among subjects with diverticulitis and previous colonoscopy (n = 124), only one patient developed AA and there were no cancer cases. CONCLUSIONS: A previous normal colonoscopy within 5 years before diverticulitis probably overshadows other risk factors for findings of advanced neoplasia and should be considered in the decision to repeat a colonoscopy.

Cardiovascular Risk Factors and Physical Fitness Among Subjects with Asymptomatic Colonic Diverticulosis.

BACKGROUND: The association between diverticular disease and atherosclerotic cardiovascular disease (ASCVD) has been demonstrated previously, mainly in symptomatic subjects. AIMS: To evaluate 10 years cardiovascular risk, exercise performance and association to ASCVD among subjects with asymptomatic diverticulosis. METHODS: A retrospective cross-sectional cohort of self-referred participants in a medical screening program, who underwent a screening colonoscopy. Demographics, clinical and laboratory variables, ASCVD score, and metabolic equivalents (METs) during treadmill stress test were compared between subjects with and without diverticulosis as diagnosed on screening colonoscopy. RESULTS: 4586 participants underwent screening colonoscopy; 799 (17.4%) had diverticulosis. Among 50-69 yo participants, diverticulosis subjects had a higher ASCVD score compared to non-diverticulosis subjects. Exercise performance was comparable between the groups, across all age groups. Using logistic regression analysis, advanced age group (50-59 yo Adjusted odds ratio (AOR) [95% confidence interval (CI)] 2.57 (1.52-4.34), p < 0.001; 60-69 yo, AOR 2.87 (2.09-3.95), p < 0.001; ≥ 70 yo AOR 4.81 (3.23-7.15), p < 0.001; compared to < 50 yo age group), smoking [AOR 1.27 (1.05-1.55), p = 0.016], HTN [AOR 1.27 (1.03-1.56), p = 0.022], obesity [AOR 1.36 (1.06-1.74), p = 0.014] and male sex [AOR 1.29 (1.02-1.64), p = 0.036] were associated with diverticular detection during screening colonoscopy. Among males, achieving METs score ≥ 10 was inversely associated with diverticular detection during screening colonoscopy [AOR 0.64 (0.43-0.95), p = 0.027]. CONCLUSIONS: Ten years probability for ASCVD estimated by the ASCVD score is higher among subjects with asymptomatic diverticulosis compared to subjects without diverticulosis. Improved exercise performance is demonstrated for the first time to correlate with decreased probability for diverticular disease in screening colonoscopy.

Jejunal Inflammation in Crohn's Disease: Comparison between Diffusion Weighted Magnetic Resonance Imaging and Video Capsule Endoscopy.

BACKGROUND: Jejunal disease is associated with worse prognosis in Crohn's disease. The added value of diffusion weighted imaging for evaluating jejunal inflammation related to Crohn's Disease is scarce. OBJECTIVES: To compare diffusion weighted imaging, video capsule endoscopy, and inflammatory biomarkers in the assessment of Crohn's disease involving the jejunum. METHODS: Crohn's disease patients in clinical remission were prospectively recruited and underwent magnetic resonance (MR)-enterography and video capsule endoscopy. C-reactive protein and fecal-calprotectin levels were obtained. MR-enterography images were evaluated for restricted diffusion, and apparent diffusion coefficient values were measured. The video capsule endoscopy-based Lewis score was calculated. Associations between diffusion weighted imaging, apparent diffusion coefficient, Lewis score, and inflammatory biomarkers were evaluated. RESULTS: The study included 51 patients, and 27/51 (52.9%) with video capsule endoscopies showed jejunal mucosal inflammation. Sensitivity and specificity of restricted diffusion for video capsule endoscopy mucosal inflammation were 59.3% and 37.5% for the first reader, and 66.7% and 37.5% for the second reader, respectively. Diffusion weighted imaging was not statistically associated with jejunal video capsule endoscopy inflammation (P = 0.813). CONCLUSIONS: Diffusion weighted imaging was not an effective test for evaluation of jejunal inflammation as seen by video capsule endoscopy in patients with quiescent Crohn's disease.

Host transcriptome signatures in human faecal-washes predict histological remission in patients with IBD.

BACKGROUND: Colonoscopy is the gold standard for evaluation of inflammation in inflammatory bowel diseases (IBDs), yet entails cumbersome preparations and risks of injury. Existing non-invasive prognostic tools are limited in their diagnostic power. Moreover, transcriptomics of colonic biopsies have been inconclusive in their association with clinical features. AIMS: To assess the utility of host transcriptomics of faecal wash samples of patients with IBD compared with controls. METHODS: In this prospective cohort study, we obtained biopsies and faecal-wash samples from patients with IBD and controls undergoing lower endoscopy. We performed RNAseq of biopsies and matching faecal-washes, and associated them with endoscopic and histological inflammation status. We also performed faecal mass-spectrometry proteomics on a subset of samples. We inferred cell compositions using computational deconvolution and used classification algorithms to identify informative genes. RESULTS: We analysed biopsies and faecal washes from 39 patients (20 IBD, 19 controls). Host faecal-transcriptome carried information that was distinct from biopsy RNAseq and faecal proteomics. Transcriptomics of faecal washes, yet not of biopsies, from patients with histological inflammation were significantly correlated to one another (p=5.3×10-12). Faecal-transcriptome had significantly higher statistical power in identifying histological inflammation compared with transctiptome of intestinal biopsies (150 genes with area under the curve >0.9 in faecal samples vs 10 genes in biopsy RNAseq). These results were replicated in a validation cohort of 22 patients (10 IBD, 12 controls). Faecal samples were enriched in inflammatory monocytes, regulatory T cells, natural killer-cells and innate lymphoid cells. CONCLUSIONS: Faecal wash host transcriptome is a statistically powerful biomarker reflecting histological inflammation. Furthermore, it opens the way to identifying important correlates and therapeutic targets that may be obscured using biopsy transcriptomics.

Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice.

The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.

Venous Thromboembolism Among Patients With Inflammatory Bowel Diseases is Not Related to Increased Thrombophilia: A Case-Control Study.

GOAL: The aim was to assess whether thrombophilia significantly contributes to the risk of venous thromboembolic events (VTEs) in patients with inflammatory bowel disease (IBD). BACKGROUND: Patients with IBD have a high risk of VTE. The underlying mechanism has been only partially defined. METHODS: A case-control study in adults with IBD and an episode of VTE (IBD-VTE) were matched and compared with non-IBD patients with a VTE (non-IBD-VTE). The study population was comprised of patients seen in 2 tertiary medical centers in Israel between 2000 and 2013. Characteristics of IBD and risk factors for VTE were retrieved from medical charts, and a comprehensive thrombophilia panel was completed in all patients. RESULTS: Forty-four IBD-VTE cases (27 Crohn's disease) were matched with 127 non-IBD-VTE controls. The majority of VTE had a clear etiology and were considered provoked events. Provoked and unprovoked VTE rates were not different between the 2 groups. Likewise, thrombophilia rates were similar among patients with IBD-VTE and controls (40.9% vs. 53.5%, respectively, P=0.14). However, among patients with unprovoked VTE, thrombophilia rates were significantly lower in the IBD-VTE group compared with controls (42.1% vs. 70.7%, respectively, P=0.03). Among patients with IBD-VTE, an unprovoked event, and negative thrombophilia, 77% had active inflammation at the time of VTE. CONCLUSION: Thrombophilia rates are similar among patients with IBD-VTE and controls but are less common among patients with unprovoked IBD-VTE. This finding suggests that either inflammation or other novel pathways drive VTE in patients with IBD.

Fucosyltransferase 2 Mutations Are Associated With a Favorable Clinical Course in Crohn's Disease.

BACKGROUND: Fucosyltransferase 2 (FUT2) participates in intestinal antigen secretion and bacterial adherence. FUT2 homozygous nonsense mutations (FUT2M) and subsequent nonsecretor status is associated with Crohn's disease (CD). The common null allele is rs601338. We assessed the relationship between FUT2M and disease course. METHODS: In consecutive adult CD outpatients, clinical, biochemical, and genetic data were collected at baseline visits. Patients were longitudinally followed over 5 years. The primary outcome analyzed the relationship between FUT2M and rates of CD patients in persistent steroid-free clinical remission requiring neither surgery, biologics, nor immunomodulators. RESULTS: Sixty-two CD patients were recruited. FUT2M homozygotes (rs601338 or any mutation in linkage disequilibrium) were detected in 27% of CD (17/62). Patients with rs601338 mutations had higher rates of the primary outcome (homozygous: 46.6%, heterozygous: 28.0%, wild-type: 5.3%, P=0.02). Similar findings existed for CD patients with homozygous mutations in any single-nucleotide polymorphism for FUT2 (homozygous: 41.2%, heterozygous: 25.9%, wild-type: 5.6%, P=0.04). On multivariable analysis, rs601338 mutation was associated with the primary outcome (odds ratio=3.4, 95% confidence interval: 1.3-8.7, P=0.01), while other parameters were not. Mutation of rs601338 was associated with lower rates of penetrating disease (homozygous: 13.3%, heterozygous: 28.0%, wild-type: 52.6%, P=0.05) and particularly in high-risk patients (homozygous: 0%, heterozygous: 37.5%, wild-type: 83.3%, P=0.01). CONCLUSIONS: FUT2 mutation status is associated with a favorable clinical course in CD. Further confirmatory studies are needed.

Early Indolent Course of Crohn's Disease in Newly Diagnosed Patients Is Not Rare and Possibly Predictable.

BACKGROUND & AIMS: The early stages of Crohn's disease (CD) course are heterogeneous, and it is a challenge to predict the course of disease in patients with new diagnosis. METHODS: We performed an observational longitudinal study of 156 adults (79 male; median age, 27.7 years; 57 treatment naïve) with newly diagnosed CD (within 6 months of enrollment), referred from medical centers and community clinics in Israel from 2013 through 2017. Study participants each received semi-annual scheduled evaluations. Indolent disease was defined as a disease course without need for strict interventions to control complicated course of CD (hospitalization or surgery, or decision to start steroid, immunomodulator, or biologic therapy). Cox regression and receiver operating characteristic analyses were used to identify factors associated with early indolent or complicated course of CD. We validated our findings in an independent cohort of patients with CD from a separate medical center in Israel in 2018. RESULTS: Over a median follow-up period of 17.2 months (interquartile range, 8.8-23.8 months), 52 patients (33.3%) had an indolent course of CD, 29 (18.5%) required hospitalizations, and 75 (48%) were recommended to start steroid, immunomodulator, or biologic therapies. The median time to first intervention was 3.4 months (95% CI, 2.4-4.4). We developed a model based on clinical factors that identified 4 factors associated with complicated course in treatment-naïve patients: body mass index <25 kg/m2 (hazard ratio [HR], 2.45; 95% CI, 1.07-5.43; P = .033), serum level of vitamin B12 <350 pg/mL (HR, 2.78; 95% CI, 1.21-6.41; P = .016), white blood cells ≥7 × 103/µL (HR, 2.419; 95% CI, 1.026-5.703; P = .044), and serum level of ALT ≥25 IU/L (HR, 2.680; 95% CI, 1.186-6.058; P = .018). This model discriminated between patients with vs without a complicated course of disease with 90% and 89% accuracy at 6 and 12 months after diagnosis, respectively. A validation cohort demonstrated a discriminatory ability of 79% at 3 months after diagnosis, and a nomogram was constructed. CONCLUSIONS: In an observational longitudinal study of 156 patients with newly diagnosed CD, we found that one third have an early indolent course of disease. We identified factors that can be measured at diagnosis to identify patients at risk for an early complicated course-these might be used in patient management and selection of treatment.

Ulcer severity grading in video capsule images of patients with Crohn's disease: an ordinal neural network solution.

BACKGROUND AND AIMS: Capsule endoscopy (CE) is an important modality for diagnosis and follow-up of Crohn's disease (CD). The severity of ulcers at endoscopy is significant for predicting the course of CD. Deep learning has been proven accurate in detecting ulcers on CE. However, endoscopic classification of ulcers by deep learning has not been attempted. The aim of our study was to develop a deep learning algorithm for automated grading of CD ulcers on CE. METHODS: We retrospectively collected CE images of CD ulcers from our CE database. In experiment 1, the severity of each ulcer was graded by 2 capsule readers based on the PillCam CD classification (grades 1-3 from mild to severe), and the inter-reader variability was evaluated. In experiment 2, a consensus reading by 3 capsule readers was used to train an ordinal convolutional neural network (CNN) to automatically grade images of ulcers, and the resulting algorithm was tested against the consensus reading. A pretraining stage included training the network on images of normal mucosa and ulcerated mucosa. RESULTS: Overall, our dataset included 17,640 CE images from 49 patients; 7391 images with mucosal ulcers and 10,249 normal images. A total of 2598 randomly selected pathologic images were further graded from 1 to 3 according to ulcer severity in the 2 different experiments. In experiment 1, overall inter-reader agreement occurred for 31% of the images (345 of 1108) and 76% (752 of 989) for distinction of grades 1 and 3. In experiment 2, the algorithm was trained on 1242 images. It achieved an overall agreement for consensus reading of 67% (166 of 248) and 91% (158 of 173) for distinction of grades 1 and 3. The classification accuracy of the algorithm was 0.91 (95% confidence interval, 0.867-0.954) for grade 1 versus grade 3 ulcers, 0.78 (95% confidence interval, 0.716-0.844) for grade 2 versus grade 3, and 0.624 (95% confidence interval, 0.547-0.701) for grade 1 versus grade 2. CONCLUSIONS: CNN achieved high accuracy in detecting severe CD ulcerations. CNN-assisted CE readings in patients with CD can potentially facilitate and improve diagnosis and monitoring in these patients.

Deep learning for noninvasive liver fibrosis classification: A systematic review.

BACKGROUND AND AIMS: While biopsy is the gold standard for liver fibrosis staging, it poses significant risks. Noninvasive assessment of liver fibrosis is a growing field. Recently, deep learning (DL) technology has revolutionized medical image analysis. This technology has the potential to enhance noninvasive fibrosis assessment. We systematically examined the application of DL in noninvasive liver fibrosis imaging. METHODS: Embase, MEDLINE, Web of Science, and IEEE Xplore databases were used to identify studies that reported on the accuracy of DL for classification of liver fibrosis on noninvasive imaging. The search keywords were "liver or hepatic," "fibrosis or cirrhosis," and "neural or DL networks." Risk of bias and applicability were evaluated using the QUADAS-2 tool. RESULTS: Sixteen studies were retrieved. Imaging modalities included ultrasound (n = 10), computed tomography (n = 3), and magnetic resonance imaging (n = 3). The studies analyzed a total of 40 405 radiological images from 15 853 patients. All but two of the studies were retrospective. In most studies the "ground truth" reference was the METAVIR score for pathological staging (n = 9.56%). The majority of the studies reported an accuracy >85% when compared to histopathology. Fourteen studies (87.5%) had a high risk of bias and concerns regarding applicability. CONCLUSIONS: Deep learning has the potential to play an emerging role in liver fibrosis classification. Yet, it is still limited by a relatively small number of retrospective studies. Clinicians should facilitate the use of this technology by sharing databases and standardized reports. This may optimize the noninvasive evaluation of liver fibrosis on a large scale.

Low psoas muscle area is associated with postoperative complications in Crohn's disease.

BACKGROUND AND AIMS: Crohn's disease (CD) is associated with increased postoperative morbidity. Sarcopenia correlates with increased morbidity and mortality in various medical conditions. We assessed correlations of the lean body mass marker and psoas muscle area (PMA), with postoperative outcomes in CD patients undergoing gastrointestinal surgery. METHODS: We included patients with CD who underwent gastrointestinal surgery between June 2009 and October 2018 and had CT/MRI scans within 8 weeks preoperatively. PMA was measured bilaterally on perioperative imaging. RESULTS: Of 121 patients, the mean age was 35.98 ± 15.07 years; 51.2% were male. The mean BMI was 21.56 ± 4 kg/m2. The mean PMA was 95.12 ± 263.2cm2. Patients with postoperative complications (N = 31, 26%) had significantly lower PMA compared with patients with a normal postoperative recovery (8.5 ± 2.26 cm2 vs. 9.85 ± 2.68 cm2, P = 0.02). A similar finding was noted comparing patients with anastomotic leaks to those without anastomotic leaks (7.48 ± 0.1 cm2 vs. 9.6 ± 2.51 cm2, P = 0.04). PMA correlated with the maximum degree of complications per patient, according to the Clavien-Dindo classification (Spearman's coefficient = -0.26, P = 0.004). Patients with major postoperative complications (Clavien-Dindo ≥ 3) had lower mean PMA (8.12 ± 2.75 cm2 vs. 9.71 ± 2.57 cm2, P = 0.03). Associations were similar when stratifying by gender and operation urgency. On multivariate analysis, PMA (HR = 0.72/cm2, P = 0.02), operation urgency (HR = 3.84, P < 0.01), and higher white blood cell count (HR = 1.14, P = 0.02) were independent predictive factors for postoperative complications. CONCLUSION: PMA is an easily measured radiographic parameter associated with postoperative complications in patients with CD undergoing bowel resection.

Predictors of Immunogenicity to Infliximab among Patients with Inflammatory Bowel Disease: Does Ethnicity Matter?

BACKGROUND: Up to 60% of inflammatory bowel disease (IBD) patients treated with infliximab develop antibodies to infliximab (ATI), which are associated with low drug levels and loss of response (LOR). Hence, mapping out predictors of immunogenicity toward infliximab is essential for tailoring patient-specific therapy. Jewish Sephardi ethnicity, in addition to monotherapy, has been previously identified as a potential risk factor for ATI formation and infliximab failure. OBJECTIVES: To explore the association between Jewish sub-group ethnicity among patients with IBD and the risk of infliximab immunogenicity and therapy failure. To confirm findings of a previous cohort that addressed the same question. METHODS: This retrospective cohort study included all infliximab-treated patients of Jewish ethnicity with regular prospective measurements of infliximab trough levels and ATI. Drug and ATI levels were prospectively measured, clinical data was retrieved from medical charts. RESULTS: The study comprised 109 Jewish patients (54 Ashkenazi, 55 Sephardi) treated with infliximab. There was no statistically significant difference in proportion of ATI between Sephardi and Ashkenazi patients with IBD (32% Ashkenazi and 33% Sephardi patients developed ATI, odds ratio [OR] 0.944, P = 0.9). Of all variables explored, monotherapy and older age were the only factors associated with ATI formation (OR 0.336, 95% confidence interval 0.145-0.778, P = 0.01, median 34 vs. 28, interquartile range 28-48, 23-35 years, P = 0.02, respectively). CONCLUSIONS: Contrary to previous findings, Sephardi Jewish ethnicity was not identified as a risk factor for ATI formation compared with Ashkenazi Jewish ethnicity. Other risk factors remained unchanged.

Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis.

BACKGROUND AND AIMS: Deep learning is an innovative algorithm based on neural networks. Wireless capsule endoscopy (WCE) is considered the criterion standard for detecting small-bowel diseases. Manual examination of WCE is time-consuming and can benefit from automatic detection using artificial intelligence (AI). We aimed to perform a systematic review of the current literature pertaining to deep learning implementation in WCE. METHODS: We conducted a search in PubMed for all original publications on the subject of deep learning applications in WCE published between January 1, 2016 and December 15, 2019. Evaluation of the risk of bias was performed using tailored Quality Assessment of Diagnostic Accuracy Studies-2. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic curves were plotted. RESULTS: Of the 45 studies retrieved, 19 studies were included. All studies were retrospective. Deep learning applications for WCE included detection of ulcers, polyps, celiac disease, bleeding, and hookworm. Detection accuracy was above 90% for most studies and diseases. Pooled sensitivity and specificity for ulcer detection were .95 (95% confidence interval [CI], .89-.98) and .94 (95% CI, .90-.96), respectively. Pooled sensitivity and specificity for bleeding or bleeding source were .98 (95% CI, .96-.99) and .99 (95% CI, .97-.99), respectively. CONCLUSIONS: Deep learning has achieved excellent performance for the detection of a range of diseases in WCE. Notwithstanding, current research is based on retrospective studies with a high risk of bias. Thus, future prospective, multicenter studies are necessary for this technology to be implemented in the clinical use of WCE.

Deep learning algorithms for automated detection of Crohn's disease ulcers by video capsule endoscopy.

BACKGROUND AND AIMS: The aim of our study was to develop and evaluate a deep learning algorithm for the automated detection of small-bowel ulcers in Crohn's disease (CD) on capsule endoscopy (CE) images of individual patients. METHODS: We retrospectively collected CE images of known CD patients and control subjects. Each image was labeled by an expert gastroenterologist as either normal mucosa or containing mucosal ulcers. A convolutional neural network was trained to classify images into either normal mucosa or mucosal ulcers. First, we trained the network on 5-fold randomly split images (each fold with 80% training images and 20% images testing). We then conducted 10 experiments in which images from n - 1 patients were used to train a network and images from a different individual patient were used to test the network. Results of the networks were compared for randomly split images and for individual patients. Area under the curves (AUCs) and accuracies were computed for each individual network. RESULTS: Overall, our dataset included 17,640 CE images from 49 patients: 7391 images with mucosal ulcers and 10,249 images of normal mucosa. For randomly split images results were excellent, with AUCs of .99 and accuracies ranging from 95.4% to 96.7%. For individual patient-level experiments, the AUCs were also excellent (.94-.99). CONCLUSIONS: Deep learning technology provides accurate and fast automated detection of mucosal ulcers on CE images. Individual patient-level analysis provided high and consistent diagnostic accuracy with shortened reading time; in the future, deep learning algorithms may augment and facilitate CE reading.

Infliximab levels and antibodies in IBD-related peripheral arthralgia.

BACKGROUND: Extra-intestinal manifestations (EIM) are common in inflammatory bowel diseases (IBD) and may affect up to 40% of the patients during the course of the disease. Peripheral arthralgia (PA) is by far the most common EIM. To date, TNFα inhibitors are the most established treatment for EIMs in IBD. Infliximab (IFX) trough levels (TL) and anti-IFX antibodies (ATI) are correlated with multiple outcomes in IBD such as clinical response and remission, mucosal healing, fistular healing, and more. So far, a correlation between PA and IFX TL\ATI has not been evaluated. METHODS: This retrospective study included IBD patients followed by the gastroenterology department of Sheba Medical Center. Patients with active PA at onset of IFX treatment were included. IFX TL and ATI were evaluated at week 6, 14, and 26 and correlated with PA persistence. RESULTS: Forty patients (37 Crohn's and 3 ulcerative colitis) with IBD-related PA were included. The overall prevalence of PA was 55% (22/40), 42.5% (17/40), and 55% (22/40) after 6, 14, and 26 weeks, respectively. IFX trough drug levels were not associated with reported PA at week 6 [median, 11.8 µg/ml (IQR 6.6-15.5) vs 10.05 µg/ml (IQR 7.35-12.87), p = 0.56], week 14 [median, 4.7 µg/ml (IQR 2.3-7) vs 3.1 µg/ml (IQR 1.35-7.35), p = 0.55], and week 26 [median, 3 µg/ml (IQR 1.15-5.17) vs 3.4 µg/ml (IQR 0.13-6.75), p = 0.94]. Detectable ATI were significantly more prevalent in patients with PA than in patients without PA at week 26 [11/22 (50%) vs 3/18 (16.7%), p = 0.028]. CONCLUSIONS: In patients with IBD-related PA, ATI are associated with an increased risk of persistence of PA. No direct correlation was demonstrated between IFX TL and persistence of PA.