Is the Objective of Treatment for Crohn's Disease Mucosal or Transmural Healing?

Artificial Intelligence and IBD: Where are We Now and Where Will We Be in the Future?

PURPOSE OF REVIEW

Artificial intelligence (AI) is quickly demonstrating the ability to address problems and challenges in the care of IBD. This review with commentary will highlight today's advancements in AI applications for IBD in image analysis, understanding text, and replicating clinical knowledge and experience.

RECENT FINDINGS

Advancements in machine learning methods, availability of high-performance computing, and increasing digitization of medical data are providing opportunities for AI to assist in IBD care. Multiple groups have demonstrated the ability of AI to replicate expert endoscopic scoring in IBD, with expansion into automated capsule endoscopy, enterography, and histologic interpretations. Further, AI image analysis is being used to develop new endoscopic scoring with more granularity and detail than is possible using conventional methods. Advancements in natural language processing are proving to reduce laborious tasks required in the care of IBD, including documentation, information searches, and chart review. Finally, large language models and chatbots that can understand language and generate human-like replies are beginning to exhibit clinical intelligence that will revolutionize how we deliver IBD care. Today, AI is being deployed to replicate expert judgement in specific tasks where disagreement, subjectivity, and bias are common. However, the near future will herald contributions of AI doing what we cannot, including new detailed measures of IBD, enhanced analysis of images, and perhaps even fully automating care. As we speculate on future technologic capabilities that may improve how we care for IBD, this review will also consider how we will implement and fairly use AI in practice.

Wall Thickness Ratio-A New Magnetic Resonance Parameter-Is Associated With the Outcome of Biological Therapy in Patients With Ileal and Ileocolonic Crohn's Disease

GOALS

The present study was aimed at identifying a new magnetic resonance enterography (MRE) parameter assessing the clinical outcome of biological therapy in patients with active ileal/ileocolonic Crohn's disease (CD).

BACKGROUND

Transmural healing (TH) has been associated with improved outcomes in CD. However, some patients with clinical remission and inactive disease at endoscopy do not achieve TH.

MATERIALS AND METHODS

Ileal/ileocolonic CD patients scheduled for biological therapy were prospectively evaluated, at baseline (T0) and after 1 year of treatment (T1), with Harvey Bradshaw Index score, blood tests, ileocolonscopy, and MRE. Clinical activity was assessed after 2 years of treatment (T2). Wall thickness ratio (WTR) was calculated in the same affected ileal segment, as the ratio between the ileum wall thickness value at T1 and the ileum wall thickness value at T0.

RESULTS

A total of 103 patients were included. Mean WTR at T1 in nonresponders was significantly higher than in responders. At receiver operating characteristic analysis, WTR values were significantly associated to biological therapy responsiveness. A WTR cutoff value of 0.77 mm was identified to discriminate responders from nonresponders (sensitivity: 79%; specificity: 67%). In responders, the proportion of patients with a WTR<0.77 was significantly higher than the proportion of patients achieving TH at T1. Among patients achieving endoscopic remission, 11/29 (37.9%) presented TH, while 20/29 (68.9%) presented WTR<0.77 ( P : 0.035). At multivariate logistic regression analysis, WTR<0.77 was significantly associated to biological therapy response.

CONCLUSION

WTR index represents an easy-to-calculate MRE parameter and seems to be a promising tool for monitoring therapeutic response in CD patients during biological therapy.

Development of a multimodal machine-learning fusion model to non-invasively assess ileal Crohn's disease endoscopic activity

BACKGROUND AND OBJECTIVE

Recurrent attentive non-invasive observation of intestinal inflammation is essential for the proper management of Crohn's disease (CD). The goal of this study was to develop and evaluate a multi-modal machine-learning (ML) model to assess ileal CD endoscopic activity by integrating information from Magnetic Resonance Enterography (MRE) and biochemical biomarkers.

METHODS

We obtained MRE, biochemical and ileocolonoscopy data from the multi-center ImageKids study database. We developed an optimized multimodal fusion ML model to non-invasively assess terminal ileum (TI) endoscopic disease activity in CD from MRE data. We determined the most informative features for model development using a permutation feature importance technique. We assessed model performance in comparison to the clinically recommended linear-regression MRE model in an experimental setup that consisted of stratified 2-fold validation, repeated 50 times, with the ileocolonoscopy-based Simple Endoscopic Score for CD at the TI (TI SES-CD) as a reference. We used the predictions' mean-squared-error (MSE) and the receiver operation characteristics (ROC) area under curve (AUC) for active disease classification (TI SEC-CD≥3) as performance metrics.

RESULTS

121 subjects out of the 240 subjects in the ImageKids study cohort had all required information (Non-active CD: 62 [51%], active CD: 59 [49%]). Length of disease segment and normalized biochemical biomarkers were the most informative features. The optimized fusion model performed better than the clinically recommended model determined by both a better median test MSE distribution (7.73 vs. 8.8, Wilcoxon test, p<1e-5) and a better aggregated AUC over the folds (0.84 vs. 0.8, DeLong's test, p<1e-9).

CONCLUSIONS

Optimized ML models for ileal CD endoscopic activity assessment have the potential to enable accurate and non-invasive attentive observation of intestinal inflammation in CD patients. The presented model is available at https://tcml-bme.github.io/ML_SESCD.html.

Impact of intestinal ultrasound with a portable system in the management of Crohn's disease

Background

Intestinal ultrasound (IUS) is a valid cross-sectional imaging technique for the evaluation of Crohn’s disease (CD). With advancements in technology, portable ultrasound systems are becoming widely available, and the inevitable change to their use by non-radiologist clinicians would be a valuable contribution to improving patient care. This study aimed to investigate the diagnostic yield of IUS examination performed by a gastroenterologist with a portable system as an adjunct imaging modality in the routine care of CD patients.

Methods

A total of 117 CD patients were assessed by IUS imaging. Pre- and post-IUS clinical-management decisions were recorded. The primary outcome was to evaluate the change in the patients’ clinical-management decision following the IUS examination. The diagnostic accuracy was compared against the reference decision reached via a multidisiplinary meeting after the evaluation of all patient-related data. The endoscopic disease activity was determined using the simple endoscopic score for Crohn's disease (SES-CD).

Results

The initial clinical-management decision was changed in 47 patients (40.2%) after the IUS examination (P = 0.001). The accuracy of patient-management decisions improved from 63.2% to 90.6% in comparison to reference decisions (P < 0.001). After IUS examination, a further 13 cases (11.1%) were identified for urgent surgical/interventional procedures. The accuracy of colonoscopic (SES-CD ≥3) assessment was shown to be comparable to that of IUS (94% vs 91%). The sensitivity for disease presence was 95% with colonoscopy and 94% with the IUS assessment.

Conclusion

IUS examination with the use of a portable ultrasonography system significantly improves clinical-management decisions. With further supporting data, this practice would possibly become a requirement for CD management.

Infliximab Exposure Associates With Radiologic Evidence of Healing in Patients With Crohn's Disease

BACKGROUND & AIMS

Higher infliximab trough levels are associated with clinical and endoscopic remission in patients with Crohn's disease (CD). We investigated pharmacodynamic features of infliximab and radiological healing.

METHODS

We performed a substudy of the TAILORIX trial (patients with active luminal CD in Europe, treated with infliximab), analyzing baseline and week 54 magnetic resonance enterography (MRE) data. MREs were scored using the MaRIA score by blinded central readers. Radiologic response and remission were defined, based on MaRIA criteria in all segments, as scores below 11 and 7, respectively. We collected data on infliximab trough levels, biomarkers, and endoscopic findings. Our primary aim was to evaluate pharmacodynamic features associated with radiologic response and remission, based on MRE assessments at baseline and at 54 weeks after initiation of infliximab therapy.

RESULTS

We analyzed data from 36 patients (50% female; median age 35.7 years; interquartile age range, 25.6-48.6 years; median disease duration, 1.5 months; interquartile duration range, 0.6-22.4 months). At week 54 of treatment, 36.4% of patients had a radiologic response, 30.3% of patients were in remission, and 71% had endoscopic features of remission. At baseline, there was a correlation between the CD endoscopic index of severity and MaRIA scores (κ = 0.46; P = .008), but we found no correlation at week 54 (κ = 0.06; P = .75). Radiologic remission correlated with infliximab trough level at week 14 (P = .049) when the infliximab trough level cut-off value was set at 7.8 μg/mL (area under the curve, 0.74; 75% sensitivity; 86% specificity; 90% negative predictive value; 57% positive predictive value). Radiologic response correlated with infliximab trough levels at week 14 (P = .048) when the infliximab trough level cut-off value was set at 7.8 μg/mL (area under the curve, 0.73; 70% sensitivity; 90% specificity; 86% negative predictive value; 78% positive predictive value) and with continuous pharmacologic evidence of response (infliximab trough levels above 5.0 μg/mL at all time points) (P = .034).

CONCLUSIONS

In a substudy of data from the TAILORIX trial of patients with active luminal CD, we identified a relationship between exposure to infliximab and radiologic evidence of outcomes.

Defining the Path Forward for Biomarkers to Address Unmet Needs in Inflammatory Bowel Diseases

Despite major advances in the inflammatory bowel diseases field, biomarkers to enable personalized and effective management are inadequate. Disease course and treatment response are highly variable, with some patients experiencing mild disease progression, whereas other patients experience severe or complicated disease. Periodic endoscopy is performed to assess disease activity; as a result, it takes months to ascertain whether a treatment is having a positive impact on disease progression. Minimally invasive biomarkers for prognosis of disease course, prediction of treatment response, monitoring of disease activity, and accurate diagnosis based on improved disease phenotyping and classification could improve outcomes and accelerate the development of novel therapeutics. Rapidly developing technologies have great potential in this regard; however, the discovery, validation, and qualification of biomarkers will require partnerships including academia, industry, funders, and regulators. The Crohn's & Colitis Foundation launched the IBD Biomarker Summit to bring together key stakeholders to identify and prioritize critical unmet needs; prioritize promising technologies and consortium approaches to address these needs; and propose harmonization approaches to improve comparability of data across studies. Here, we summarize the outcomes of the 2018 and 2019 meetings, including consensus-based unmet needs in the clinical and drug development context. We highlight ongoing consortium efforts and promising technologies with the potential to address these needs in the near term. Finally, we summarize actionable recommendations for harmonization, including data collection tools for improved consistency in disease phenotyping; standardization of informed consenting; and development of guidelines for sample management and assay validation. Taken together, these outcomes demonstrate that there is an exceptional alignment of priorities across stakeholders for a coordinated effort to address unmet needs of patients with inflammatory bowel diseases through biomarker science.

Targeting mucosal healing in Crohn's disease: what the clinician needs to know

In recent years, mucosal healing has emerged as a key therapeutic goal in the clinical management of patients with Crohn's disease, as it has been associated with improved long-term clinical outcomes. With the vast improvements in endoscopic imaging techniques and the increase in available treatment options, which reportedly are able to induce mucosal healing, the practising physician is left to wonder: how is endoscopic mucosal healing exactly defined in Crohn's disease, and how can it effectively be achieved and monitored in daily clinical practice? Within this review, we will give an overview of the ongoing debate about the definition of mucosal healing and the modalities to monitor inflammation, and finally present available therapies with the capacity to induce mucosal healing.

Treat-to-target in Crohn's disease: Will transmural healing become a therapeutic endpoint?

Crohn's disease (CD) represents a chronic transmural inflammatory condition of the gastrointestinal tract, which usually leads to structural damage and significant disability. Deep remission - defined by both clinical and endoscopic remission, signifying mucosal healing - represents the current endpoint in the treat-to-target strategy, significantly improving patients' long-term outcomes. Transmural healing (TH) could be a more effective target, but this possibility remains unclear. This narrative review aims to critically review and summarize the available literature relating TH to long-term outcomes, being the first of its kind and to the best of the author's knowledge. A systematic literature search (from inception to March 31 2018) was performed, using multiple databases, and identifying seven full-text manuscripts. In those studies, long-term favorable outcomes (≥ 52 wk) included sustained clinical remission, as well as fewer therapeutic changes, CD-related hospitalizations, and surgeries. Despite heterogeneous design and methodological limitations, six of the studies demonstrated that TH or intestinal healing (TH plus mucosal healing) were predictive for the aforementioned favorable outcomes. Therefore, TH may become a reasonable therapeutic target and be included in the concept of deep remission. Further prospective, well-designed, multicenter trials aiming to better define the role of TH in personalized therapy for CD and to determine the long-term influence of TH on bowel damage and disability are warranted.