Development and Validation of a Novel Prediction Model for Differential Diagnosis Between Crohn's Disease and Intestinal Tuberculosis

Artificial intelligence-aided colonoscopic differential diagnosis between Crohn's disease and gastrointestinal tuberculosis

BACKGROUND AND AIM

Differentiating between Crohn's disease (CD) and gastrointestinal tuberculosis (GITB) is challenging. We aimed to evaluate the clinical applicability of an artificial intelligence (AI) model for this purpose.

METHODS

The AI model was developed and assessed using an internal dataset comprising 1,132 colonoscopy images of CD and 1,045 colonoscopy images of GITB at a tertiary referral center. Its stand-alone performance was further evaluated in an external dataset comprising 67 colonoscopy images of 17 CD patients and 63 colonoscopy images of 14 GITB patients from other institutions. Additionally, a crossover trial involving three expert endoscopists and three trainee endoscopists compared AI-assisted and unassisted human interpretations.

RESULTS

In the internal dataset, the sensitivity, specificity, and accuracy of the AI model in distinguishing between CD and GITB were 95.3%, 100.0%, and 97.7%, respectively, with an area under the ROC curve of 0.997. In the external dataset, the AI model exhibited a sensitivity, specificity, and accuracy of 77.8%, 85.1%, and 81.5%, respectively, with an area under the ROC curve of 0.877. In the human endoscopist trial, AI assistance increased the pooled accuracy of the six endoscopists from 86.2% to 88.8% (P = 0.010). While AI did not significantly enhance diagnostic accuracy for the experts (96.7% with AI vs 95.6% without, P = 0.360), it significantly improved accuracy for the trainees (81.0% vs 76.7%, P = 0.002).

CONCLUSIONS

This AI model shows potential in aiding the accurate differential diagnosis between CD and GITB, particularly benefiting less experienced endoscopists.

New diagnostic strategies to distinguish Crohn's disease and gastrointestinal tuberculosis

PURPOSE OF REVIEW

Despite advances in our radiological, histological and microbiological armamentarium, distinguishing between Crohn's disease (CD) and intestinal tuberculosis (ITB), especially in a TB endemic country, continues to be a challenging exercise in a significant number of patients. This review aims to summarize current available evidence on novel diagnostic techniques which have a potential to fill the gap in our knowledge of differentiating between ITB and CD.

RECENT FINDINGS

Both ITB and CD are associated with altered host immune responses, and detection of these altered innate and adaptive immune cells has potential to distinguish ITB from CD. ITB and CD have different epigenetic, proteomic and metabolomic signatures, and recent research has focused on detecting these differences. In addition, the gut microbiome, which is involved in mucosal immunity and inflammatory responses, is considerably altered in both ITB and CD, and is another potential frontier, which can be tapped to discriminate between the two diseases. With technological advancements, we have newer radiological modalities including perfusion CT and dual-layer spectral detector CT enterography and evidence is emerging of their role in differentiating ITB from CD. Finally, time will tell whether the advent of artificial intelligence, with rapidly accumulating data in this field, will be the gamechanger in solving this puzzle of diagnostic dilemma between ITB and Crohn's disease.

SUMMARY

Recent advances need to be clinically validated before they can be used as novel diagnostic measures to differentiate Intestinal TB from CD.

Clinical Usefulness of Immune Profiling for Differential Diagnosis between Crohn's Disease, Intestinal Tuberculosis, and Behcet's Disease

It is important to make a differential diagnosis between inflammatory diseases of the bowel with similar clinical and endoscopic features. The profiling of immune cells could be helpful for accurately diagnosing inflammatory bowel diseases. We compared immune marker expression between Crohn's disease (CD), intestinal Behcet's disease (BD), and intestinal tuberculosis (TB) and evaluated the usefulness of immune profiling in differentiating between these diseases. Biopsy specimens were acquired around ulcerations on the terminal ileum or cecum from five patients with each disease. Panel 1 included multiplex immunohistochemistry staining for CD8, CD4, Foxp3, CD20, programmed death-1, and granzyme B. CD56, CD68, CD163, CD11c, and HLA-DR were analyzed in panel 2. The differences in cytotoxic T cells (CD8+CD4-Fopx3-CD20-), helper T cells (CD8-CD4+Fopx3-CD20-), and regulatory T cells (CD8-CD4+Fopx3+CD20-) were also not significant. However, M1 macrophage (CD68+CD163-HLA-DR-) cell densities were significantly higher in intestinal BD than in other diseases. The expression level of dendritic cells (CD56-CD68-CD163-CD11c+HLA-DR+) was highest in intestinal TB and lowest in intestinal BD. The expression of immune cells, including M1 macrophages and dendritic cells, was different between CD, intestinal BD, and intestinal TB. Immune profiling can be helpful for establishing differential diagnoses of inflammatory bowel diseases.

Differentiating gastrointestinal tuberculosis and Crohn's disease- a comprehensive review

Gastrointestinal Tuberculosis (GITB) and Crohn's disease (CD) are both chronic granulomatous diseases with a predilection to involve primarily the terminal ileum. GITB is often considered a disease of the developing world, while CD and inflammatory bowel disease are considered a disease of the developed world. But in recent times, the epidemiology of both diseases has changed. Differentiating GITB from CD is of immense clinical importance as the management of both diseases differs. While GITB needs anti-tubercular therapy (ATT), CD needs immunosuppressive therapy. Misdiagnosis or a delay in diagnosis can lead to catastrophic consequences. Most of the clinical features, endoscopic findings, and imaging features are not pathognomonic for either of these two conditions. The definitive diagnosis of GITB can be clinched only in a fraction of cases with microbiological positivity (acid-fast bacilli, mycobacterial culture, or PCR-based tests). In most cases, the diagnosis is often based on consistent clinical, endoscopic, imaging, and histological findings. Similarly, no single finding can conclusively diagnose CD. Multiparametric-based predictive models incorporating clinical, endoscopy findings, histology, radiology, and serology have been used to differentiate GITB from CD with varied results. However, it is limited by the lack of validation studies for most such models. Many patients, especially in TB endemic regions, are initiated on a trial of ATT to see for an objective response to therapy. Early mucosal response assessed at two months is an objective marker of response to ATT. Prolonged ATT in CD is recognized to have a fibrotic effect. Therefore, early discrimination may be vital in preventing the delay in the diagnosis of CD and avoiding a complicated course.

Clinical characteristics and diagnosis of intestinal tuberculosis in clinical practice at Thailand's largest national tertiary referral center: An 11-year retrospective review

BACKGROUND

Diagnosing intestinal tuberculosis (ITB) is challenging due to the low diagnostic sensitivity of current methods. This study aimed to assess the clinical characteristics and diagnosis of ITB at our tertiary referral center, and to explore improved methods of ITB diagnosis.

METHODS

This retrospective study included 177 patients diagnosed with ITB at Siriraj Hospital (Bangkok, Thailand) during 2009-2020.

RESULTS

The mean age was 49 years, 55.4% were male, and 42.9% were immunocompromised. Most diagnoses (108/177) were made via colonoscopy; 12 patients required more than one colonoscopy. Among those, the sensitivity of tissue acid-fast bacilli (AFB), presence of caseous necrosis, polymerase chain reaction (PCR), and culture was 40.7%, 13.9%, 25.7%, and 53.4%, respectively. Among patients with negative tissue histopathology, 4 (3.7%) and 13 (12.0%) were ITB positive on tissue PCR and culture, respectively. The overall sensitivity when all diagnostic methods were used was 63%. Seventy-six patients had stool tests for mycobacteria. The overall sensitivity of stool tests was 75.0%. However, when analyzing the 31 patients who underwent both endoscopy and stool testing, the sensitivity of stool testing when using tissue biopsy as a reference was 45.8%. Combining stool testing and tissue biopsy did not significantly increase the sensitivity compared to tissue biopsy alone (83.9% vs. 77.4%, respectively).

CONCLUSION

Despite the availability of PCR and culture for TB, the overall diagnostic sensitivity was found to be low. The sensitivity increased when the tests were used in combination. Repeated colonoscopy may be beneficial. Adding stool mycobacteria tests did not significantly increase the diagnostic yield if endoscopy was performed, but it could be beneficial if endoscopy is unfeasible.

Saudi Arabia consensus guidance for the diagnosis and management of adults with inflammatory bowel disease

Optimal management of inflammatory bowel disease (IBD) relies on a clear understanding and tailoring evidence-based interventions by clinicians in partnership with patients. This article provides concise guidelines for the management of IBD in adults, based on the most up-to-date information at the time of writing and will be regularly updated. These guidelines were developed by the Saudi Ministry of Health in collaboration with the Saudi Gastroenterology Association and the Saudi Society of Clinical Pharmacy. After an extensive literature review, 78 evidence-and expert opinion-based recommendations for diagnosing and treating ulcerative colitis and Crohn's disease in adults were proposed and further refined by a voting process. The consensus guidelines include the finally agreed on statements with their level of evidence covering different aspects of IBD diagnosis and treatment.

Differential diagnosis of Crohn’s disease and intestinal tuberculosis: development and assessment of a nomogram prediction model

Background

China is a region with a high incidence of tuberculosis, and the incidence of IBD has also been rising rapidly in recent years. Differentiating Crohn’s disease(CD) from intestinal tuberculosis (ITB) has become a very challenging issue. We aimed to develop and assess a diagnostic nomogram to differentiate between CD and ITB to improve the accuracy and practicability of the model.

Methods

A total of 133 patients (CD 90 and ITB 43) were analyzed retrospectively. Univariate and multivariate logistic regression analysis was included to determine the independent predictive factors and establish the regression equation. On this basis, the nomogram prediction model was constructed. The discrimination, calibration and clinical efficiency of the nomogram were assessed using area under the curve(AUC), C-index, calibration curve, decision curve analysis (DCA) and clinical impact curve.

Results

T-SPOT positive, cobblestone appearance, comb sign and granuloma were significant predictors in differentiating CD from ITB. Base on the above independent predictors, a diagnostic nomogram was successfully established. The sensitivity, specificity, accuracy of the prediction model are 94.4%, 93.0%, 94.0% respectively. The AUC and the C-index of the prediction model are both 0.988, which suggest that the model had a good discrimination power. The calibration curve indicated a high calibration degree of the prediction model. The DCA and clinical impact curve indicated a good clinical efficiency of the prediction model which could bring clinical benefits.

Conclusion

A nomogram prediction model for distinguishing CD from ITB was developed and assessed, with high discrimination, calibration and clinical efficiency. It can be used as an accurate and convenient diagnostic tool to distinguish CD from ITB, facilitating clinical decision-making.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12876-022-02519-z.

Applying logistic LASSO regression for the diagnosis of atypical Crohn's disease

In countries with a high incidence of tuberculosis, the typical clinical features of Crohn's disease (CD) may be covered up after tuberculosis infection, and the identification of atypical Crohn's disease and intestinal tuberculosis (ITB) is still a dilemma for clinicians. Least absolute shrinkage and selection operator (LASSO) regression has been applied to select variables in disease diagnosis. However, its value in discriminating ITB and atypical Crohn's disease remains unknown. A total of 400 patients were enrolled from January 2014 to January 2019 in second Xiangya hospital Central South University.Among them, 57 indicators including clinical manifestations, laboratory results, endoscopic findings, computed tomography enterography features were collected for further analysis. R software version 3.6.1 (glmnet package) was used to perform the LASSO logistic regression analysis. SPSS 20.0 was used to perform Pearson chi-square test and binary logistic regression analysis. In the variable selection step, LASSO regression and Pearson chi-square test were applied to select the most valuable variables as candidates for further logistic regression analysis. Secondly, variables identified from step 1 were applied to construct binary logistic regression analysis. Receiver operating characteristic (ROC) curve analysis was performed on these models to assess the ability and the optimal cutoff value for diagnosis. The area under the ROC curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy rate, together with their 95% confidence and intervals (CIs) were calculated. MedCalc software (Version 16.8) was applied to analyze the ROC curves of models. 332 patients were eventually enrolled to build a binary logistic regression model to discriminate CD (including comprehensive CD and tuberculosis infected CD) and ITB. However, we did not get a satisfactory diagnostic value via applying the binary logistic regression model of comprehensive CD and ITB to predict tuberculosis infected CD and ITB (accuracy rate:79.2%VS 65.1%). Therefore, we further established a binary logistic regression model to discriminate atypical CD from ITB, based on Pearsonchi-square test (model1) and LASSO regression (model 2). Model 1 showed 89.9% specificity, 65.9% sensitivity, 88.5% PPV, 68.9% NPV, 76.9% diagnostic accuracy, and an AUC value of 0.811, and model 2 showed 80.6% specificity, 84.4% sensitivity, 82.3% PPV, 82.9% NPV, 82.6% diagnostic accuracy, and an AUC value of 0.887. The comparison of AUCs between model1 and model2 was statistically different (P < 0.05). Tuberculosis infection increases the difficulty of discriminating CD from ITB. LASSO regression showed a more efficient ability than Pearson chi-square test based logistic regression on differential diagnosing atypical CD and ITB.

Enterogenous Microbiotic Markers in the Differential Diagnosis of Crohn's Disease and Intestinal Tuberculosis

Crohn’s disease (CD) is a chronic intestinal disorder characterized by refractory gastrointestinal ulcerations. Intestinal tuberculosis (ITB) is one common intestinal disease in east Asia. The two diseases share similar clinical manifestations and endoscopic characteristics. Thus, it is difficult to establish a definite diagnosis of CD, CD concomitant with ITB (CD-ITB), and ITB in practice. Some enterogeneous microbiotic markers have been applied to differentiate CD and ITB, but it remains unknown how they work for the three groups of patients. The aim of our study was to explore the diagnostic values of these enterogeneous microbiotic markers (ASCA IgG, ASCA IgA, ACCA, Anti-I2 and AMCA) among CD, CD-ITB, and ITB patients. A total of 124 individuals were retrospectively enrolled in this study, namely, 103 CD patients, 10 CD-ITB patients, 9 ITB patients, and 68 healthy controls. The demographic and clinical characteristics of these patients were collected and analyzed. The values of these individual or combined enterogeneous microbiotic markers in diagnosis and classification were assessed in CD, CD-ITB, and ITB patients. ASCA IgG, ASCA IgA, and AMCA could accurately differentiate CD patients from healthy controls with an area under curve (AUC) of 0.688, 0.601, and 0.638, respectively. ASCA IgG was significantly higher in CD patients than in CD-ITB patients (P = 0.0003). The Anti-I2 antibody was appropriate for distinguishing CD-ITB from ITB patients (P = 0.039). In CD patients, ASCA IgG was higher in severe patients than in mild (P <0.0001) and inactive patients (P <0.0001), respectively. AMCA was significantly elevated in severe and moderate patients compared to inactive patients (P = 0.001, P = 0.003, respectively). AMCA was associated with a higher risk of CD-related surgery with a significant P-value of 0.0038. In our cohort, ASCAs and AMCA could accurately distinguish CD from healthy controls with an acceptable AUC. A combination of elevated ASCA IgG and AMCA antibodies established a higher sensitivity in differentiating CD from healthy controls. Elevated ASCA IgG demonstrated a differential diagnostic value between CD and CD-ITB. Anti-I2 could also distinguish CD-ITB from ITB. The level of AMCA was associated with both disease severity and CD-related surgery. Likewise, the level of ASCA IgG was also related to disease severity.

ECCO Topical Review on Clinicopathological Spectrum and Differential Diagnosis of Inflammatory Bowel Disease

INTRODUCTION

Many diseases can imitate inflammatory bowel disease [IBD] clinically and pathologically. This review outlines the differential diagnosis of IBD and discusses morphological pointers and ancillary techniques that assist with the distinction between IBD and its mimics.

METHODS

European Crohn's and Colitis Organisation [ECCO] Topical Reviews are the result of an expert consensus. For this review, ECCO announced an open call to its members and formed three working groups [WGs] to study clinical aspects, pathological considerations, and the value of ancillary techniques. All WGs performed a systematic literature search.

RESULTS

Each WG produced a draft text and drew up provisional Current Practice Position [CPP] statements that highlighted the most important conclusions. Discussions and a preliminary voting round took place, with subsequent revision of CPP statements and text and a further meeting to agree on final statements.

CONCLUSIONS

Clinicians and pathologists encounter a wide variety of mimics of IBD, including infection, drug-induced disease, vascular disorders, diverticular disease, diversion proctocolitis, radiation damage, and immune disorders. Reliable distinction requires a multidisciplinary approach.

Epidemiology and diagnosis of inflammatory bowel diseases

Background: Over the past three decades, inflammatory bowel diseases (IBD) have been rapidly increasing in the African, South American, and Asian countries, including Korea. However, in Korea, the public awareness of IBD remains low, and diagnostic delay is not uncommon due to the physicians' lack of clinical experience. It is essential to understand the trends and regional differences in the epidemiology of IBD for proper diagnosis and treatment.Current Concepts: Although lower than those of the West, the prevalence and incidence of IBD in Korea rank among the highest in Asia and are steadily increasing. In the past 10 years, the prevalence of IBD has almost doubled, while its incidence has decreased gradually. As compared to Western IBD patients, Korean patients have higher proportion of proctitis in ulcerative colitis, male predominance, more ileocolonic involvement, and higher incidence of perianal fistula in Crohn disease. There is no single gold standard for the diagnosis of IBD. Thus, diagnosis can be made by clinical evaluation, including a detailed history taking, physical examination, and a combination of endoscopic, radiologic, laboratory, and histologic findings.Discussion and Conclusion: Population-based studies have revealed the current trends and characteristics of the epidemiology of IBD in Korea. Continued education and development of diagnostic tools will help clinicians to diagnose IBD accurately and differentiate it from other diseases such as intestinal tuberculosis.

Deep-learning system for real-time differentiation between Crohn's disease, intestinal Behçet's disease, and intestinal tuberculosis

BACKGROUND AND AIM

Pattern analysis of big data can provide a superior direction for the clinical differentiation of diseases with similar endoscopic findings. This study aimed to develop a deep-learning algorithm that performs differential diagnosis between intestinal Behçet's disease (BD), Crohn's disease (CD), and intestinal tuberculosis (ITB) using colonoscopy images.

METHODS

The typical pattern for each disease was defined as a typical image. We implemented a convolutional neural network (CNN) using Pytorch and visualized a deep-learning model through Gradient-weighted Class Activation Mapping. The performance of the algorithm was evaluated using the area under the receiver operating characteristic curve (AUROC).

RESULTS

A total of 6617 colonoscopy images of 211 CD, 299 intestinal BD, and 217 ITB patients were used. The accuracy of the algorithm for discriminating the three diseases (all-images: 65.15% vs typical images: 72.01%, P = 0.024) and discriminating between intestinal BD and CD (all-images: 78.15% vs typical images: 85.62%, P = 0.010) was significantly different between all-images and typical images. The CNN clearly differentiated colonoscopy images of the diseases (AUROC from 0.7846 to 0.8586). Algorithmic prediction AUROC for typical images ranged from 0.8211 to 0.9360.

CONCLUSION

This study found that a deep-learning model can discriminate between colonoscopy images of intestinal BD, CD, and ITB. In particular, the algorithm demonstrated superior discrimination ability for typical images. This approach presents a beneficial method for the differential diagnosis of the diseases.

Development and validation of a new algorithm model for differential diagnosis between Crohn's disease and intestinal tuberculosis: a combination of laboratory, imaging and endoscopic characteristics

Background

Sometimes in clinical practice, it is a great challenge to distinguish Crohn's disease (CD) and intestinal tuberculosis (ITB), we conducted this study to identify simple and useful algorithm for distinguishing them.

Methods

We retrospectively reviewed the medical history of the patients who were diagnosed as ITB or CD. We firstly identified ITB patients, and then the patients diagnosed with CD were matched by age, sex, and admission time in a 1:1 ratio. Patients who admitted between May 1, 2013 and April 30, 2019 were regarded as training cohort, and patients admitted between May 1, 2019 and May 1, 2020 were regarded as validation cohort. We used multivariate analysis to identify the potential variables, and then we used R package rpart to build the classification and regression tree (CART), and validated the newly developed model.

Results

In total, the training cohort included 84 ITB and 84 CD patients, the validation cohort included 22 ITB and 22 CD patients. Multivariate analysis showed that, positive interferon-gamma release assays (IGRAs), ≥ 4 segments involved, longitudinal ulcer, circular ulcer, and aphthous ulcer were confirmed as independent discriminating factors. Using these parameters to build the CART model made an overall accuracy rate was 88.64%, with sensitivity, specificity, NPV, and PPV being 90.91%, 86.36%, 90.48% and 86.96%, respectively.

Conclusion

We developed a simple and novel algorithm model covering laboratory, imaging, and endoscopy parameters with CART to differentiate ITB and CD with good accuracy. Positive IGRAs and circular ulcer were suggestive of ITB, while ≥ 4 segments involved, longitudinal ulcer, and aphthous ulcer were suggestive of CD.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12876-021-01838-x.

Gastrointestinal tuberculosis: A systematic review of epidemiology, presentation, diagnosis and treatment

Tuberculosis (TB) once considered a disease of the developing world is infrequent in the developing world too. Its worldwide prevalence with a huge impact on the healthcare system both in economic and health terms has prompted the World Health Organization to make it a top priority infectious disease. Tuberculous infection of the pulmonary system is the most common form of this disease, however, extrapulmonary TB is being increasingly recognized and more often seen in immunocompromised situations. Gastrointestinal TB is a leading extrapulmonary TB manifestation that can defy diagnosis. Overlap of symptoms with other gastrointestinal diseases and limited accuracy of diagnostic tests demands more awareness of this disease. Untreated gastrointestinal TB can cause significant morbidity leading to prolonged hospitalization and surgery. Prompt diagnosis with early initiation of therapy can avoid this. This timely review discusses the epidemiology, risk factors, pathogenesis, clinical presentation, current diagnostic tools and therapy.

Intestinal Tuberculosis: A Diagnostic Challenge

Diagnosing intestinal tuberculosis (TB) with uncommon clinical manifestations is often challenging. Here, we report a case of an alcoholic patient who presented with vague symptoms and was later diagnosed with intestinal TB. This patient experienced multiorgan failure causing hemodynamic instability requiring ionotropic support; acute hypoxic respiratory failure managed with non-invasive positive pressure ventilation, hepatic failure, transudative peritoneal effusion, and transudative pleural effusion. These conditions clouded our judgment to pursue colonoscopy for a definite diagnosis and delayed the anti-tuberculosis treatment. When intestinal tuberculosis TB is suspected, the differential diagnosis must be established with other gastrointestinal involving diseases, including mycobacterium avium complex (MAC) and Crohn's disease (CD). MAC can show overlapping features with intestinal TB or coexist with it; Acid-fast stain and tissue culture are the key tests to differentiate these two. In the presence of diagnostic uncertainty between intestinal TB and CD, a therapeutic trial with anti-tuberculous therapy may be warranted.

Validation of models using basic parameters to differentiate intestinal tuberculosis from Crohn's disease: A multicenter study from Asia

BACKGROUND

Data on external validation of models developed to distinguish Crohn's disease (CD) from intestinal tuberculosis (ITB) are limited. This study aimed to validate and compare models using clinical, endoscopic, and/or pathology findings to differentiate CD from ITB.

METHODS

Data from newly diagnosed ITB and CD patients were retrospectively collected from 5 centers located in Thailand or Hong Kong. The data was applied to Lee, et al., Makharia, et al., Jung, et al., and Limsrivilai, et al. model.

RESULTS

Five hundred and thirty patients (383 CD, 147 ITB) with clinical and endoscopic data were included. The area under the receiver operating characteristic curve (AUROC) of Limsrivilai's clinical-endoscopy (CE) model was 0.853, which was comparable to the value of 0.862 in Jung's model (p = 0.52). Both models performed significantly better than Lee's endoscopy model (AUROC: 0.713, p<0.01). Pathology was available for review in 199 patients (116 CD, 83 ITB). When 3 modalities were combined, Limsrivilai's clinical-endoscopy-pathology (CEP) model performed significantly better (AUROC: 0.887) than Limsrivilai's CE model (AUROC: 0.824, p = 0.01), Jung's model (AUROC: 0.798, p = 0.005) and Makharia's model (AUROC: 0.637, p<0.01). In 83 ITB patients, the rate of misdiagnosis with CD when used the proposed cutoff values in each original study was 9.6% for Limsrivilai's CEP, 15.7% for Jung's, and 66.3% for Makharia's model.

CONCLUSIONS

Scoring systems with more parameters and diagnostic modalities performed better; however, application to clinical practice is still limited owing to high rate of misdiagnosis of ITB as CD. Models integrating more modalities such as imaging and serological tests are needed.

Criteria for evaluating risk prediction of multiple outcomes

Risk prediction models have been developed in many contexts to classify individuals according to a single outcome, such as risk of a disease. Emerging “-omic” biomarkers provide panels of features that can simultaneously predict multiple outcomes from a single biological sample, creating issues of multiplicity reminiscent of exploratory hypothesis testing. Here I propose definitions of some basic criteria for evaluating prediction models of multiple outcomes. I define calibration in the multivariate setting and then distinguish between outcome-wise and individual-wise prediction, and within the latter between joint and panel-wise prediction. I give examples such as screening and early detection in which different senses of prediction may be more appropriate. In each case I propose definitions of sensitivity, specificity, concordance, positive and negative predictive value and relative utility. I link the definitions through a multivariate probit model, showing that the accuracy of a multivariate prediction model can be summarised by its covariance with a liability vector. I illustrate the concepts on a biomarker panel for early detection of eight cancers, and on polygenic risk scores for six common diseases.

Intestinal tuberculosis or Crohn's disease: a review of the diagnostic models designed to differentiate between these two gastrointestinal diseases

Differentiating Crohn’s disease (CD) from intestinal tuberculosis (ITB) is a diagnostic dilemma, particularly in regions where ITB is prevalent and CD incidence is increasing, because both diseases can present quite similarly, and diagnostic tests to identify Mycobacterium tuberculosis in tissue samples have rather poor sensitivity. Studies that were conducted to determine the factors that differentiate CD from ITB identified some significant characteristics, but none of those characteristics are exclusive to either ITB or CD. Many diagnostic models or scoring systems that use one to several diagnostic parameters have been proposed to help distinguish these two intestinal diseases. Early models consisted of parameters common to routine clinical practice, such as clinical features, and endoscopic and pathologic findings. The later models also include more advanced diagnostic parameters like high-resolution imaging and serological testing. However, the number and types of parameters differ among diagnostic models, and the systems used to calculate scoring also vary from model to model. Enhanced awareness and understanding of the currently available diagnostic models will help physicians determine which model(s) is/are most suitable for differentiating CD from ITB in their clinical practice.

Gastrointestinal Bleeding in a Patient With Gastric Lymphoma, Tuberculosis Enteritis, and Cytomegalovirus Enteritis

Bleeding from the small bowel can be challenging to identify by endoscopic or radiographic evaluation. We present the case of a patient with incompletely treated latent tuberculosis and medical history of T-cell lymphoma who developed gastrointestinal bleeding because of concurrent Burkitt lymphoma, tuberculosis enteritis, and cytomegalovirus enteritis. The interplay of these 3 diagnoses is discussed.

Crohn's disease

Crohn's disease is an inflammatory bowel disease that is characterized by chronic inflammation of any part of the gastrointestinal tract, has a progressive and destructive course and is increasing in incidence worldwide. Several factors have been implicated in the cause of Crohn's disease, including a dysregulated immune system, an altered microbiota, genetic susceptibility and environmental factors, but the cause of the disease remains unknown. The onset of the disease at a young age in most cases necessitates prompt but long-term treatment to prevent disease flares and disease progression with intestinal complications. Thus, earlier, more aggressive treatment with biologic therapies or novel small molecules could profoundly change the natural history of the disease and decrease complications and the need for hospitalization and surgery. Although less invasive biomarkers are in development, diagnosis still relies on endoscopy and histological assessment of biopsy specimens. Crohn's disease is a complex disease, and treatment should be personalized to address the underlying pathogenetic mechanism. In the future, disease management might rely on severity scores that incorporate prognostic factors, bowel damage assessment and non-invasive close monitoring of disease activity to reduce the severity of complications.

British Society of Gastroenterology consensus guidelines on the management of inflammatory bowel disease in adults

Ulcerative colitis and Crohn's disease are the principal forms of inflammatory bowel disease. Both represent chronic inflammation of the gastrointestinal tract, which displays heterogeneity in inflammatory and symptomatic burden between patients and within individuals over time. Optimal management relies on understanding and tailoring evidence-based interventions by clinicians in partnership with patients. This guideline for management of inflammatory bowel disease in adults over 16 years of age was developed by Stakeholders representing UK physicians (British Society of Gastroenterology), surgeons (Association of Coloproctology of Great Britain and Ireland), specialist nurses (Royal College of Nursing), paediatricians (British Society of Paediatric Gastroenterology, Hepatology and Nutrition), dietitians (British Dietetic Association), radiologists (British Society of Gastrointestinal and Abdominal Radiology), general practitioners (Primary Care Society for Gastroenterology) and patients (Crohn's and Colitis UK). A systematic review of 88 247 publications and a Delphi consensus process involving 81 multidisciplinary clinicians and patients was undertaken to develop 168 evidence- and expert opinion-based recommendations for pharmacological, non-pharmacological and surgical interventions, as well as optimal service delivery in the management of both ulcerative colitis and Crohn's disease. Comprehensive up-to-date guidance is provided regarding indications for, initiation and monitoring of immunosuppressive therapies, nutrition interventions, pre-, peri- and postoperative management, as well as structure and function of the multidisciplinary team and integration between primary and secondary care. Twenty research priorities to inform future clinical management are presented, alongside objective measurement of priority importance, determined by 2379 electronic survey responses from individuals living with ulcerative colitis and Crohn's disease, including patients, their families and friends.

British Society of Gastroenterology consensus guidelines on the management of inflammatory bowel disease in adults

Ulcerative colitis and Crohn's disease are the principal forms of inflammatory bowel disease. Both represent chronic inflammation of the gastrointestinal tract, which displays heterogeneity in inflammatory and symptomatic burden between patients and within individuals over time. Optimal management relies on understanding and tailoring evidence-based interventions by clinicians in partnership with patients. This guideline for management of inflammatory bowel disease in adults over 16 years of age was developed by Stakeholders representing UK physicians (British Society of Gastroenterology), surgeons (Association of Coloproctology of Great Britain and Ireland), specialist nurses (Royal College of Nursing), paediatricians (British Society of Paediatric Gastroenterology, Hepatology and Nutrition), dietitians (British Dietetic Association), radiologists (British Society of Gastrointestinal and Abdominal Radiology), general practitioners (Primary Care Society for Gastroenterology) and patients (Crohn's and Colitis UK). A systematic review of 88 247 publications and a Delphi consensus process involving 81 multidisciplinary clinicians and patients was undertaken to develop 168 evidence- and expert opinion-based recommendations for pharmacological, non-pharmacological and surgical interventions, as well as optimal service delivery in the management of both ulcerative colitis and Crohn's disease. Comprehensive up-to-date guidance is provided regarding indications for, initiation and monitoring of immunosuppressive therapies, nutrition interventions, pre-, peri- and postoperative management, as well as structure and function of the multidisciplinary team and integration between primary and secondary care. Twenty research priorities to inform future clinical management are presented, alongside objective measurement of priority importance, determined by 2379 electronic survey responses from individuals living with ulcerative colitis and Crohn's disease, including patients, their families and friends.

Intestinal tuberculosis and Crohn's disease: the importance and difficulty of a differential diagnosis

Tuberculosis (TB) is the most prevalent infection worldwide and affects one third of the population, predominantly in developing countries. Intestinal TB (ITB) is the sixth most frequent extra-pulmonary TB infection. Crohn's disease (CD) is a chronic inflammatory bowel disease that arises from the interaction of immunological, environmental and genetic factors. Due to changes in the epidemiology of both diseases, distinguishing CD from ITB is a challenge, particularly in immunocompromised patients and those from areas where TB is endemic. Furthermore, both TB and CD have a predilection for the ileocecal area. In addition, they share very similar clinical, radiological and endoscopic findings. An incorrect diagnosis and treatment may increase morbidity and mortality. Thus, a great degree of caution is required as well as a familiarity with certain characteristics of the diseases, which will aid the differentiation between the two diseases.

Imaging in discriminating intestinal tuberculosis and Crohn's disease: past, present and the future

Introduction: Intestinal tuberculosis (ITB) and Crohn's disease (CD) have similar clinical presentation, but require different treatment approaches. Despite advances in various endoscopic, imaging, microbiological, and histological techniques, the differentiation of these two entities is often difficult. Newer radiological and image acquisition modalities have now become indispensable tools for evaluation of these two diseases.Areas covered: This review summarizes the currently available literature on various radiological investigations to differentiate ITB from CD. This review also enumerates the newer modalities in image acquisition techniques and their potential role for differentiating these two diseases. At present abdominal computed tomography (CT) scan is used as a first line investigation for differentiating ITB from CD. Magnetic resonance imaging (MRI) is preferred in pediatric patients and for follow-up studies.Expert opinion: Role of newer modalities like contrast enhanced abdominal ultrasound, perfusion CT, advanced MRI and positron emission tomography (PET) is evolving and requires further exploration. Till further robust studies are available, differentiation between ITB and CD requires use of a combination of clinical, endoscopic, serological, histological, and radiological parameters rather than relying on a single test.

An algorithm for the classification of study designs to assess diagnostic, prognostic and predictive test accuracy in systematic reviews

Results of medical tests are the main source to inform clinical decision making. The main information to assess the usefulness of medical tests for correct discrimination of patients are accuracy measures. For the estimation of test accuracy measures, many different study designs can be used. The study design is related to the clinical question to be answered (diagnosis, prognosis, prediction), determines the accuracy measures that can be calculated and it might have an influence on risk of bias. Therefore, a clear and consistent distinction of the different study designs in systematic reviews on test accuracy studies is very important. In this paper, we propose an algorithm for the classification of study designs of test accuracy, that compare the results of an index test (the test to be evaluated) with the results of a reference test (the test whose results are considered as correct/the gold standard) studies in systematic reviews.

Analysis of Phenotypic Variables and Differentiation Between Untypical Crohn's Disease and Untypical Intestinal Tuberculosis

BACKGROUND

The differentiation between untypical intestinal tuberculosis (UITB) and untypical Crohn's disease (UCD) is a challenge.

AIMS

To analyze phenotypic variables and propose a novel prediction model for differential diagnosis of two conditions.

METHODS

A total of 192 patients were prospectively enrolled. The clinical, laboratory, endoscopic, and radiological features were investigated and subjected to univariable and multivariable analyses. The final prediction model for differentiation between UCD and UITB was developed by logistic regression analysis and Fisher discriminant analysis on the training set. The same discriminant function was tested on the validation set.

RESULTS

Twenty-five candidates were selected from 52 phenotypic variables of typical Crohn's disease (TCD), UCD, and UITB patients. UCD's variables overlapped with both TCD and UITB. The percentages of tuberculosis history, positive PPD, and positive T-SPOT result in UCD were all significantly higher than that in TCD (11.6% vs. 0.0%, 27.9% vs. 0.0%, 25.6% vs. 4.5%, respectively, P < 0.05). The regression equations and Fisher discriminant function for discrimination between UCD and UITB were developed. In the training data, the area under the receiver operating characteristic of equations was 0.834, 0.69, and 0.648 in the clinical-laboratory, endoscopic, and radiological model, respectively. The accuracy of Fisher discriminant function for discrimination was 86% in UCD and 73% in UITB in the validation data.

CONCLUSIONS

Phenotypes of UCD patients in TB-endemic countries may be associated with TB infection history. Fisher discriminant analysis is a good choice to differentiate UCD from UITB, which is worthy of verification in clinical practice.

Development and Validation of a Novel Diagnostic Nomogram to Differentiate Between Intestinal Tuberculosis and Crohn's Disease: A 6-year Prospective Multicenter Study

OBJECTIVES

Differentiating Crohn's disease (CD) from intestinal tuberculosis (ITB) remains a diagnostic challenge. Misdiagnosis carries potential grave implications. We aimed to develop and validate a novel diagnostic nomogram for differentiating them.

METHODS

In total, 310 eligible patients were recruited from 6 tertiary inflammatory bowel disease centers. Among them, 212 consecutive patients (143 CD and 69 ITB) were used in the derivation cohort for the establishment of diagnostic equation and nomogram; 7 investigative modalities including clinical manifestations, laboratory results, endoscopic findings, computed tomography enterography features, and histology results were used to derive the diagnostic model and nomogram. Ninety-eight consecutive patients (76 CD and 22 ITB) were included for validation of the diagnostic model.

RESULTS

Eight out of total 79 parameters were identified as valuable parameters used for establishing diagnostic equations. Two regression models were built based on 7 differential variables: age, transverse ulcer, rectum involvement, skipped involvement of the small bowel, target sign, comb sign, and interferon-gamma release assays (for model 1) or purified protein derivative (for model 2), respectively. Accordingly, 2 nomograms of the above 2 models were developed for clinical practical use, respectively. Further validation test verified the efficacy of the nomogram 1 with 90.9% specificity, 86.8% sensitivity, 97.1% PPV, 66.7% negative predictive value (NPV), and 87.8% accuracy for identifying CD, and the efficacy of the nomogram 2 with 100% specificity, 84.2% sensitivity, 100% positive predictive value, 64.7% NPV, and 87.8% accuracy for diagnosing CD.

CONCLUSIONS

The derivation and validation cohorts identified and validated 2 highly accurate and practical diagnostic nomograms for differentiating CD from ITB. These diagnostic nomograms can be conveniently used to identify some difficult CD or ITB cases, allowing for decision-making in a clinical setting.

Differentiating Crohn’s disease from intestinal tuberculosis

Differentiating Crohn’s disease (CD) and intestinal tuberculosis (ITB) has remained a dilemma for most of the clinicians in the developing world, which are endemic for ITB, and where the disease burden of inflammatory bowel disease is on the rise. Although, there are certain clinical (diarrhea/hematochezia/perianal disease common in CD; fever/night sweats common in ITB), endoscopic (longitudinal/aphthous ulcers common in CD; transverse ulcers/patulous ileocaecal valve common in ITB), histologic (caseating/confluent/large granuloma common in ITB; microgranuloma common in CD), microbiologic (positive stain/culture for acid fast-bacillus in ITB), radiologic (long segment involvement/comb sign/skip lesions common in CD; necrotic lymph node/contiguous ileocaecal involvement common in ITB), and serologic differences between CD and ITB, the only exclusive features are caseation necrosis on biopsy, positive smear for acid-fast bacillus (AFB) and/or AFB culture, and necrotic lymph node on cross-sectional imaging in ITB. However, these exclusive features are limited by poor sensitivity, and this has led to the development of multiple multi-parametric predictive models. These models are also limited by complex formulae, small sample size and lack of validation across other populations. Several new parameters have come up including the latest Bayesian meta-analysis, enumeration of peripheral blood T-regulatory cells, and updated computed tomography based predictive score. However, therapeutic anti-tubercular therapy (ATT) trial, and subsequent clinical and endoscopic response to ATT is still required in a significant proportion of patients to establish the diagnosis. Therapeutic ATT trial is associated with a delay in the diagnosis of CD, and there is a need for better modalities for improved differentiation and reduction in the need for ATT trial.

Clinical characteristics and long-term prognosis of elderly-onset Crohn's disease

OBJECTIVES

This study aimed to evaluate the clinical characteristics and clinical course of Asian elderly-onset Crohn's disease (EOCD) patients in a large well-defined cohort of South Korean IBD patients.

MATERIALS AND METHODS

From the Asan inflammatory bowel disease registry, we identified 29 EOCD patients (diagnosed with CD in age of 60 years or over) out of 2989 CD patients (1.0%). After excluding two patients with unclear data, 27 EOCD were matched with 108 young-onset CD (YOCD) and 108 middle age-onset CD (MOCD) for the interval from symptom onset to diagnosis (±3 years) and follow-up duration (±3 years).

RESULTS

Females were predominant in the EOCD group (59.3%) compared to MOCD (31.5%) and YOCD (29.6%) groups (p = .012). In EOCD group, terminal ileal location was the most common (63.0%) at diagnosis, whereas ileocolonic location in other groups (57.4% in MOCD and 78.7% in YOCD, respectively) (p < .001). Patients with perianal fistula at CD diagnosis were less common (14.8% in EOCD vs. 28.7% in MOCD vs. 49.1% in YOCD, p < .001). During follow-up, thiopurines were used less frequently in the EOCD group (48.1% in EOCD vs. 87.0% in MOCD vs. 89.8% in YOCD, p < .001), but the risk for intestinal resection was comparable among three groups (p = .583).

CONCLUSIONS

EOCD may have a better clinical course than MOCD and YOCD, as demonstrated by the similar risk for intestinal resection despite the less frequent use of thiopurines.

Temporal trends in the misdiagnosis rates between Crohn's disease and intestinal tuberculosis

AIM

To investigate the temporal trends in the misdiagnosis rate between Crohn's disease (CD) and intestinal tuberculosis (ITB) in South Korea.

METHODS

We retrospectively reviewed the medical records of patients managed for CD or ITB at Asan Medical Center, a tertiary referral hospital, Seoul, Korea between 1996 and 2014. The temporal trends in the misdiagnosis rates between the two diseases were analyzed. The demographic and clinical characteristics were compared between CD patients who were initially misdiagnosed as ITB (final CD group) and vice versa (final ITB group). Final diagnostic criteria for ITB and medication for CD before definite diagnosis of TB were also analyzed in final ITB group.

RESULTS

In total, 2760 patients were managed for CD and 772 patients for ITB between 1996 and 2014. As well, 494 of the 2760 CD patients (17.9%) were initially misdiagnosed as ITB and 83 of the 772 ITB patients (10.8%) as CD. The temporal trend in misdiagnosing CD as ITB showed a decrease (OR = 0.89, 95%CI: 0.87-0.91, P < 0.001), whereas the temporal trend in misdiagnosing ITB as CD showed an increase (OR = 1.06, 95%CI: 1.01-1.11, P = 0.013). Age at diagnosis, presenting symptoms, and proportion of patients with active/past perianal fistula and active/inactive pulmonary tuberculosis (TB) were significantly different between final CD group and final ITB group. Forty patients (48.2%) in final ITB group were diagnosed by favorable response to empirical anti-TB treatment. Seventeen patients (20.5%) in final ITB group had inappropriately received corticosteroids and/or thiopurines due to misdiagnosis as CD. However, there were no mortalities in both groups.

CONCLUSION

Cases of CD misdiagnosed as ITB have been decreasing, whereas cases of ITB misdiagnosed as CD have been increasing over the past two decades.