Body-wide genetic deficiency of poly(ADP-ribose) polymerase 14 sensitizes mice to colitis.

Inflammatory bowel disease (IBD) is a chronic disease of the gastrointestinal tract affecting millions of people. Here, we investigated the expression and functions of poly(ADP-ribose) polymerase 14 (Parp14), an important regulatory protein in immune cells, with an IBD patient cohort as well as two mouse colitis models, that is, IBD-mimicking oral dextran sulfate sodium (DSS) exposure and oral Salmonella infection. Parp14 was expressed in the human colon by cells in the lamina propria, but, in particular, by the epithelial cells with a granular staining pattern in the cytosol. The same expression pattern was evidenced in both mouse models. Parp14-deficiency caused increased rectal bleeding as well as stronger epithelial erosion, Goblet cell loss, and immune cell infiltration in DSS-exposed mice. The absence of Parp14 did not affect the mouse colon bacterial microbiota. Also, the colon leukocyte populations of Parp14-deficient mice were normal. In contrast, bulk tissue RNA-Seq demonstrated that the colon transcriptomes of Parp14-deficient mice were dominated by abnormalities in inflammation and infection responses both prior and after the DSS exposure. Overall, the data indicate that Parp14 has an important role in the maintenance of colon epithelial barrier integrity. The prognostic and predictive biomarker potential of Parp14 in IBD merits further investigation.

Mechanical Stress-induced Connective Tissue Growth Factor Plays a Critical Role in Intestinal Fibrosis in Crohn's-like Colitis.

Crohn's disease (CD) is an inflammatory bowel disease characterized by transmural inflammation and intestinal fibrosis. Mechanisms of fibrosis in CD are not well understood. Transmural inflammation is associated with inflammatory cell infiltration, stenosis, and distention, which present mechanical stress (MS) to the bowel wall. We hypothesize that MS induces gene expression of pro-fibrotic mediators such as connective tissue growth factor (CTGF), which may contribute to fibrosis in CD. A rodent model of CD was induced by intracolonic instillation of TNBS to the distal colon. TNBS instillation induced a localized transmural inflammation (site I), with a distended colon segment (site P) proximal to site I. We detected significant fibrosis and collagen content not only in site I, but also in site P in CD rats by day 7. CTGF expression increased significantly in sites P and I, but not in the segment distal to the inflammation site. Increased CTGF expression was detected mainly in the smooth muscle cells (SMC). When rats were fed exclusively with clear liquid diet to prevent mechanical distention in colitis, expression of CTGF in sites P and I was blocked. Direct stretch led to robust expression of CTGF in colonic SMC. Treatment of CD rats with anti-CTGF antibody FG-3149 reduced fibrosis and collagen content in both sites P and I and exhibited consistent trends towards normalizing expression of collagen mRNAs. In conclusion, our studies suggest that mechanical stress, by up-regulating pro-fibrotic mediators i.e. CTGF, may play a critical role in fibrosis in CD.

Revolution in diet therapy for inflammatory bowel disease.

Until recently, diet as a therapeutic tool to treat inflammatory bowel disease (IBD) has not been proven effective. Nearly a century in the making we are in the grips of a revolution in diet therapies for IBD, driven by emerging data revealing diet as a key environmental factor associated with IBD susceptibility, and observational studies suggesting that dietary intake may play a role in the disease course of established IBD. This review summarizes the current evidence for diets trialed as induction and maintenance therapy for IBD. For Crohn's disease, exclusive enteral nutrition and the Crohn's disease exclusion diet with partial enteral nutrition are supported by emerging high-quality evidence as induction therapy, but are short-term approaches that are not feasible for prolonged use. Data on diet as maintenance therapy for Crohn's disease are conflicting, with some studies supporting fortification, and others suppression, of certain food components. For ulcerative colitis, data are not as robust for diet as induction and maintenance therapy; however, consistent themes are emerging, suggesting benefits for diets that are plant-based, high in fiber and low in animal protein. Further studies for both Crohn's disease and ulcerative colitis are eagerly awaited, which will allow specific recommendations to be made. Until this time, recommendations default to population based healthy eating guidelines.

Possible poor prognosis in younger-onset Crohn's disease-associated anorectal cancer: A subanalysis of the Nationwide Japanese study.

Background and aims: Crohn's disease (CD)-associated intestinal cancers are characterized by their high incidence, particularly at the anorectal site in the Japanese population. Accumulating evidence revealed that younger-onset sporadic colorectal cancer may exhibit unique biological features. To the best of our knowledge, few previous articles reported clinicopathological features in patients with CD-associated anorectal cancer (CDAAC). Therefore, we aimed to clarify the relationship between the younger onset of cancer and clinicopathological characteristics and prognosis, and the efficacy of cancer surveillance in patients with CDAAC. Methods: CD patients who had been diagnosed with intestinal cancers from 1983 to 2020 were collected from 39 Japanese institutions in this study. Of 316 patients with CD-associated intestinal cancers, we analyzed 211 patients with CDAAC. We divided the patients into two groups according to the median age at cancer diagnosis (45 years old). Results: Younger-onset CDAAC (YO-CDAAC) patients were significantly more likely to have a poor outcome than those with older-onset CDAAC (OO-CDAAC) in terms of both disease-free survival (DFS) (p = 0.0014) and overall survival (OS) (p = 0.023). Multivariate analysis showed that age under 45 years old at diagnosis of cancer was one of the independent factors for poor DFS and OS (hazard ratios: 2.15, 95% confidence interval: 1.09-4.26, p = 0.028, hazard ratios: 1.95, 95% confidence interval: 1.05-3.60, p = 0.033, respectively). Patients detected via surveillance showed significantly better DFS and OS rates than symptomatic patients in YO-CDAAC (p = 0.012 and 0.0031, respectively). Conclusions: YO-CDAAC may have a poorer prognosis compared with OO-CDAAC. Surveillance could be important to improve cancer prognosis, especially in young CD patients with anorectal disease.

Initiation of vedolizumab did not provoke new-onset spondylarthritis in patients with inflammatory bowel disease: A prospective 24-week study with imaging assessments.

BACKGROUND: A temporal relationship between vedolizumab and new-onset spondyloarthritis (SpA) has been suggested. AIMS: We evaluated the relationship between vedolizumab initiation and development of new-onset SpA in patients with inflammatory bowel disease (IBD) through serial clinical evaluation and magnetic resonance imaging (MRI). METHODS: A single-centre prospective observational study of 24 patients with IBD. Patients were eligible if they had active ulcerative colitis or Crohn's disease (CD), were initiating vedolizumab, had no prior history of arthritis or SpA and were suitable for serial MRI. A rheumatologist performed clinical evaluation prior to the first dose and 8 and 24 weeks. Axial MRI was evaluated by a blinded central reader and performed at baseline 8 and 24 weeks. RESULTS: Nine tumor necrosis factor (TNF) inhibitor-naïve patients (4 male; mean age 53.2 years; 6 UC; 3 CD) and eight TNF inhibitor-experienced patients (7 male; mean age 48 years; 3 UC; 5 CD) completed all assessments. No patients developed new features of axial arthritis or features of peripheral SpA (inflammatory oligoarthritis, enthesitis, dactylitis, or psoriasis (nail, body, or scalp)). Both groups demonstrated a good intestinal response. CONCLUSION: Vedolizumab initiation did not induce new features of axial or peripheral SpA after 24 weeks of treatment in TNF inhibitor-experienced or TNF inhibitor-naive patients with IBD.

Development and validation of a scale to measure the care needs of Crohn's disease patients: a mixed-methods study.

BACKGROUND: Crohn's disease (CD) patients require varying levels of supportive care. In order to facilitate caregivers and nurses in precisely evaluating the caregiving requirements of these patients, we developed the CD-specific Care Needs Scale (CD-CNS). METHODS: This study employed a mixed-methods approach, integrating qualitative and quantitative methodologies. The initial items of the scale were developed through qualitative interviews, Delphi expert consultation, and literature review, while the final items were refined through clinical testing. Qualitative interviews were conducted based on the supportive care needs framework and Maslow's hierarchy of needs, and scale items were constructed through a literature search and qualitative interviews. The initial version of the scale with 45 items was obtained after the items were verified and modified by expert consultation. A total of 250 CD patients admitted to the gastroenterology department of a hospital in China were selected for verification of the initial version of the scale. A self-designed general questionnaire was used to obtain patients' medical history and sociodemographic data, and the Chinese version of the Inflammatory Bowel Disease Questionnaire (IBDQ) was used as the criterion. Exploratory factor analysis (EFA) was performed on the CD-CNS to evaluate the dimensions, factor structure, reliability, criterion validity, and construct validity. RESULTS: EFA identified 5 dimensions and retained 27 items with strong internal consistency reliability (α = 0.940). The Cronbach's α coefficients for each dimension ranged from 0.824 to 0.921. Criterion validity was assessed using Spearman's coefficient, which demonstrated a significant correlation with the IBDQ (P < 0.050). The test-retest reliability for each dimension after two weeks ranged from 0.655 to 0.895. CONCLUSIONS: We developed and validated a new scale that can be used to assess the care needs of CD patients. This new tool can guide the specific supportive care of CD patients. TRIAL REGISTRATION: This study was reviewed and approved by the Ethics Committee of the Second Hospital of Nanjing (2021-LS-ky-022). The study was duly registered and approved online through the Trial Center of the Second Hospital of Nanjing in 2021. Confidentiality was ensured by anonymizing all the data. The entire study process was conducted under the supervision of the Ethics Committee of Nanjing Second Hospital. Informed consent was obtained from the patients, and each patient volunteered and agreed to participate.

The Utility of Magnetic Resonance Enterography and Double Balloon Enteroscopy-Assisted Endoscopic Balloon Dilatation for Small Bowel Strictures in Crohn's Disease: A Retrospective Observational Study.

Introduction: Crohn's disease (CD) of the small bowel is associated with a severe course and increased risk of complications. Strictures at this location are challenging to diagnose and out-of-reach of colonoscopy. We aimed to evaluate the detection rate of small bowel strictures with magnetic resonance enterography (MRE) and assess the efficacy of double balloon enteroscopy-assisted endoscopic balloon dilatation (DBE-assisted EBD) in managing these strictures. Methods: A retrospective study included all patients with DBE-assisted EBD of small bowel strictures in CD in our facility. All patients had MRE to detect strictures prior to the dilatation. Sequential dilatation protocol was performed using through-the-scope (TTS) working channel balloons. The outcomes included technical success defined by the passage of the enteroscope post-dilatation, resolution of symptoms, and the requirement of repeated procedures or surgery during 12 months of follow-up. Results: Twenty DBE-assisted EBDs of small bowel strictures were attempted during 13 DBE procedures in 10 patients (6 males, median age 42). MRE identified 75% of the strictures with 100% accuracy in localisation. Retrograde DBE was the approach in 16/20 (80%) strictures. Anaesthetic intubation was used in 8/20 (40%). DBE reached 19/20 strictures. All the reached strictures were dilated successfully; the technical success following dilatation was 72.2%. The median DBE insertion time with TTS balloon dilatation was 66 min. Three patients required follow-up dilatations within 2-3 months. Surgery was not needed during the follow-up period. Conclusions: MRE is essential in diagnosing and localising small bowel strictures in CD. DBE reached 95% of strictures with successful dilatation. Immediate technical success was high, and safety was demonstrated. Planned repeat procedures for sequential dilatation were performed in a few patients. Surgical resection was avoided in all patients.

Predicting Therapeutic Intervention for Patients with Quiescent Crohn's Disease Using the Small Bowel Capsule Endoscopy Score.

Introduction: Small bowel (SB) capsule endoscopy (SBCE) is a sensitive modality for screening the entire SB of patients with Crohn's disease (CD); however, the prognostic impact of the results is unclear. We evaluated the ability of the SBCE score to predict therapeutic intervention for patients with CD and SB lesions without clinical symptoms as well as negative C-reactive protein (CRP) levels. Methods: Fifty-six patients who underwent a patency evaluation and had a CD activity index (CDAI) score <150 mg/dL and CRP level <0.5 mg/dL were included. Twenty-one and 35 patients had CD classified as Montreal classifications L1 and L3, respectively. The initial SBCE scores were subsequently grouped according to the presence or absence of intervention based on cutoff values. We examined whether the scores could predict the need for therapeutic intervention at 1 year, 2 years, and 5 years. The CD activity in capsule endoscopy (CDACE) score was used as the SBCE score. Results: The median observation period was 1,326 days. Twenty-one patients received therapeutic intervention. There were significant differences between patients with and without treatment intervention according to the CDACE cutoff value of 420 at 1 year, 2 years, and 5 years. Significant differences between patients with Montreal classification L1 with and without intervention were observed at 1 year and 2 years. The CDACE score was moderately and strongly correlated with the Lewis score and capsule endoscopy CDAI score, respectively (Spearman rank correlation coefficient: ρ = 0.6462 and ρ = 0.9199, respectively; p < 0.0001). Conclusion: A CDACE score ≥420 is predictive of intervention after 1 year for patients with CD, a CDAI score <150, and a CRP level <0.5 mg/dL. A larger study with a prospective design is necessary to validate our findings.

What Happens to Patients with Inflammatory Bowel Disease Who Are Intolerant to Thiopurines?

Introduction: The clinical consequences for patients with inflammatory bowel disease (IBD) who stop treatment owing to side effects have not been fully investigated. Methods: This retrospective observational study aimed to compare patients who discontinued thiopurine treatment due to side effects with those who tolerated thiopurine treatment in the use of other IBD drugs, surgery, and fecal calprotectin values in the first 5 years after the start of thiopurine treatment. Results: The proportion of patients with IBD who initiated thiopurine treatment at our clinic was 44% (32% ulcerative colitis and 64% Crohn's disease) and 31% (n = 94) of those patients had to stop thiopurine treatment within 5 years due to side effects. Patients who discontinued thiopurine treatment due to intolerance were significantly older (median age 33 vs. 27 years, p = 0.003), significantly more often used prednisolone (89 vs. 76%, p = 0.009), and used to a lesser extent TNF inhibitors at the start of thiopurine treatment (3% vs. 9%, p = 0.062). Budesonide treatment and non-TNF inhibitor second-line therapy were significantly more commonly used in patients who discontinued thiopurine treatment owing to side effects, but there were no statistically significant differences in the use of other treatments. The proportion of patients with a median FC >200 µg/g was significantly higher during follow-up in patients with UC who discontinued thiopurine treatment owing to side effects. Conclusions: Patients who discontinued thiopurines owing to side effects were prescribed more budesonide and non-TNF inhibitor second-line therapy, but there were no differences in the use of TNF inhibitors, prednisolone, or surgery.

Development and Validation of an E-Learning Educational Program for Acquiring Basic Knowledge in Inflammatory Bowel Disease Nursing.

Introduction: This study focuses on developing and validating an e-learning educational program for nurturing inflammatory bowel disease (IBD) nursing specialists. Methods: The program was developed using the attention, relevance, confidence, and satisfaction models within the instructional design framework. The program validation encompassed four steps: (1) nurses took a basic IBD knowledge test (pretest), (2) participants scoring <80% were encouraged to undergo web-based training, (3) a follow-up test (posttest) gauged post-training improvement, and (4) participant satisfaction with e-learning was assessed. Results: The analysis included 63 participants. The average score in the pretest was 81.3%, 40 participants exceeded the pretest passing score, which is 80% (average: 88.3%), and 23 participants failed (average: 69.1%). Of those who failed, 19 participants showed improvement after undergoing web-based training, with their posttest scores exceeding the passing threshold (average: 97.4%). The comparison results between the passing and failing groups revealed no correlation between the baseline characteristics of the participants. The participants were highly satisfied with the e-learning program. Conclusion: The program was effective as an educational program for acquiring basic knowledge to foster IBD nursing professionals. The learning design was adapted to the participants' lifestyles and tailored to the readiness of the nurse, ensuring a satisfactory e-learning user experience for the nurses.

AGA Clinical Practice Update on the Role of Intestinal Ultrasound in Inflammatory Bowel Disease: Commentary.

DESCRIPTION: In the past 3 years, the use of intestinal ultrasound (IUS) for monitoring inflammatory bowel disease in clinical practice has grown substantially in the United States. This American Gastroenterological Association (AGA) Institute Clinical Practice Update (CPU) aims to review the available evidence and guidance regarding the role of intestinal ultrasound in inflammatory bowel disease care. METHODS: This CPU was commissioned and approved by the AGA Institute Clinical Practice Updates Committee (CPUC) and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership and underwent internal peer review by the CPUC and external peer review through standard procedures of Clinical Gastroenterology and Hepatology. This expert commentary incorporates important and recently published studies in this field, and it reflects the experiences of the multidisciplinary group of authors composed of adult and pediatric gastroenterologists.

Integrating plasma proteomics with genome-wide association data to identify novel drug targets for inflammatory bowel disease.

Inflammatory bowel disease (IBD) is a chronic disease that includes Crohn's disease (CD) and ulcerative colitis (UC). Although genome-wide association studies (GWASs) have identified many relevant genetic risk loci, the impact of these loci on protein abundance and their potential utility as clinical therapeutic targets remain uncertain. Therefore, this study aimed to investigate the pathogenesis of IBD and identify effective therapeutic targets through a comprehensive and integrated analysis. We systematically integrated GWAS data related to IBD, UC and CD (N = 25,305) by the study of de Lange KM with the human blood proteome (N = 7213) by the Atherosclerosis Risk in Communities (ARIC) study. Proteome-wide association study (PWAS), mendelian randomisation (MR) and Bayesian colocalisation analysis were used to identify proteins contributing to the risk of IBD. Integrative analysis revealed that genetic variations in IBD, UC and CD affected the abundance of five (ERAP2, RIPK2, TALDO1, CADM2 and RHOC), three (VSIR, HGFAC and CADM2) and two (MST1 and FLRT3) cis-regulated plasma proteins, respectively (P < 0.05). Among the proteins identified via Bayesian colocalisation analysis, CADM2 was found to be an important common protein between IBD and UC. A drug and five druggable target genes were identified from DGIdb after Bayesian colocalisation analysis. Our study's findings from genetic and proteomic approaches have identified compelling proteins that may serve as important leads for future functional studies and potential drug targets for IBD (UC and CD).

Systematic review: effectiveness and safety of switching between originator infliximab and biosimilar infliximab in patients with inflammatory bowel disease.

INTRODUCTION: Infliximab (IFX) biosimilars are available to treat inflammatory bowel disease (IBD), offering cost reductions versus originator IFX in some jurisdictions. However, concerns remain regarding the efficacy and safety of originator-to-biosimilar switching. This systematic literature review evaluated safety and effectiveness of switching between IFX products in patients with IBD, including multiple switchers. METHODS: Embase, PubMed, Cochrane Database of Systematic Reviews, Cochrane Central Register of Controlled Trials were searched to capture studies (2012-2022) including patients with IBD who switched between approved IFX products. Effectiveness outcomes: disease activity; disease severity; response to treatment; patient-reported outcomes (PROs). Safety outcomes: incidence and rate of adverse events (AEs); discontinuations due to AEs, failure rate; hospitalizations; surgeries. Immunogenicity outcomes (n, %): anti-drug antibodies; patients receiving concomitant immunomodulatory medication. RESULTS: Data from 85 publications (81 observational, two randomized controlled trials) were included. Clinical effectiveness outcomes were consistent with the known profile of originator IFX with no difference after switching. There were no unexpected/serious AEs after switching, and rates of AEs were generally consistent with the known profile of IFX. CONCLUSIONS: Most studies reported that clinical, PROs, and safety outcomes for originator-to-biosimilar switching were clinically equivalent to originator responses. Limited data are available regarding multiple switches. PROTOCOL REGISTRATION: www.crd.york.ac.uk/prospero identifier is CRD42021289144.

Different infliximab induction dosing regimens do not affect remission rates up to 1 year in children with Crohn's disease.

OBJECTIVES: Multiple studies in patients with Crohn's disease (CD) treated with anti-tumor necrosis factor alpha agents have shown that proactive therapeutic drug monitoring (TDM) during the maintenance phase leads to improved outcomes. We aimed to assess whether accelerated infliximab administration during induction resulted in improved outcomes. METHODS: This retrospective study included CD patients aged 5-17.9 years that were treated with infliximab. We compared outcomes of patients treated during induction with 5-8 mg/kg dosing at Weeks 0, 2, 6, and 14 (Group 1), versus accelerated dosing (≥8 mg/kg and/or >4 infusions until Week 14, Group 2) of infliximab. Primary outcome was steroid-free clinical remission by Week 52. RESULTS: Sixty-eight patients were included, of whom seven discontinued infliximab before Week 14, due to infusion reactions, immunogenic failure, or primary nonresponse. Comparison of Group 1 (n = 25) and Group 2 (n = 36) showed similar clinical characteristics, as well as inflammatory markers, at infliximab initiation. Despite receiving significantly more infliximab, and reaching a higher trough level by Week 14 (10.3 ± 1.2 vs. 3.3 ± 0.7, p < 0.001), the median Pediatric Crohn's disease Activity Index (PCDAI) was slightly higher in Group 2 versus Group 1 (14 [5-20] vs. 5 [0-15], p = 0.02). However, at Weeks 26 and 52 the PCDAI and inflammatory markers were comparable between the groups. Moreover, about 70% in both groups achieved the desirable trough infliximab levels by Week 52. CONCLUSION: Accelerated infliximab dosing during induction did not result in improved outcomes up to 12 months follow-up. Prospective studies are required to determine the exact timing in which proactive TDM should be applied.

An international multicentre study of SwiTching from Intravenous to subcutaneous inflixiMab and vEdolizumab in inflammatory bowel diseases: The TIME study.

BACKGROUND AND AIMS: Subcutaneous (SC) formulations of infliximab (IFX) and vedolizumab (VDZ) are approved for the treatment of inflammatory bowel diseases (IBDs). Our aim was to evaluate the effectiveness of switching from intravenous (IV) to SC formulations of IFX and VDZ in IBDs. METHODS: This multicentre, retrospective study collected data of adult patients with Crohn's disease (CD) or ulcerative colitis (UC) switched to SC IFX or VDZ. The primary endpoint was clinical remission at 12 months stratified based on timing of switch. A composite endpoint consisting of therapy discontinuation, reverse-switch, need for steroids, and drug optimization was evaluated. A multivariate analysis investigated the association between patients' characteristics and outcomes. RESULTS: Two hundred and thirty-one patients (59% UC, 53% male, mean age 44 ± 15 years, 68% IFX) from 13 centres were included. The switch occurred at Week 6 in a third of cases (36%). Median time to switch was 13 months. Most patients switched to SC IFX and VDZ were in clinical remission at 3 (87% and 77%), 6 (86% and 83%) and 12 (63% and 60%) months. In the multivariate analysis, there was no difference in clinical remission rate at 12 months; however, patients switched at Week 6 had a higher rate of experiencing any therapeutic changes at 3 (false discovery rate (FDR) = .002), 6 (FDR <1 × 10-10) or 12 months (FDR = .08). Clinical disease activity at baseline (only in UC) (FDR = .07) and previous exposure to biologics (FDR = .001) were risk factors for composite endpoint at 6 and 12 months. CONCLUSION: SC IFX and VDZ are effective in daily clinical practice in IBD patients. Switching patients in remission reduces the risk of negative outcomes.

Comprehensive assessment of machine learning methods for diagnosing gastrointestinal diseases through whole metagenome sequencing data.

The gut microbiome, linked significantly to host diseases, offers potential for disease diagnosis through machine learning (ML) pipelines. These pipelines, crucial in modeling diseases using high-dimensional microbiome data, involve selecting profile modalities, data preprocessing techniques, and classification algorithms, each impacting the model accuracy and generalizability. Despite whole metagenome shotgun sequencing (WMS) gaining popularity for human gut microbiome profiling, a consensus on the optimal methods for ML pipelines in disease diagnosis using WMS data remains elusive. Addressing this gap, we comprehensively evaluated ML methods for diagnosing Crohn's disease and colorectal cancer, using 2,553 fecal WMS samples from 21 case-control studies. Our study uncovered crucial insights: gut-specific, species-level taxonomic features proved to be the most effective for profiling; batch correction was not consistently beneficial for model performance; compositional data transformations markedly improved the models; and while nonlinear ensemble classification algorithms typically offered superior performance, linear models with proper regularization were found to be more effective for diseases that are linearly separable based on microbiome data. An optimal ML pipeline, integrating the most effective methods, was validated for generalizability using holdout data. This research offers practical guidelines for constructing reliable disease diagnostic ML models with fecal WMS data.

Computed tomography-based radiomics combined with machine learning allows differentiation between primary intestinal lymphoma and Crohn's disease.

BACKGROUND: Due to similar clinical manifestations and imaging signs, differential diagnosis of primary intestinal lymphoma (PIL) and Crohn's disease (CD) is a challenge in clinical practice. AIM: To investigate the ability of radiomics combined with machine learning methods to differentiate PIL from CD. METHODS: We collected contrast-enhanced computed tomography (CECT) and clinical data from 120 patients form center 1. A total of 944 features were extracted single-phase images of CECT scans. Using the last absolute shrinkage and selection operator model, the best predictive radiographic features and clinical indications were screened. Data from 54 patients were collected at center 2 as an external validation set to verify the robustness of the model. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity were used for evaluation. RESULTS: A total of five machine learning models were built to distinguish PIL from CD. Based on the results from the test group, most models performed well with a large area under the curve (AUC) (> 0.850) and high accuracy (> 0.900). The combined clinical and radiomics model (AUC = 1.000, accuracy = 1.000) was the best model among all models. CONCLUSION: Based on machine learning, a model combining clinical data with radiologic features was constructed that can effectively differentiate PIL from CD.