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

A novel multidisciplinary machine learning approach based on clinical, imaging, colonoscopy, and pathology features for distinguishing intestinal tuberculosis from Crohn's disease

OBJECTIVES

Differentiating intestinal tuberculosis (ITB) from Crohn's disease (CD) remains a diagnostic dilemma. Misdiagnosis carries potential grave implications. We aim to establish a multidisciplinary-based model using machine learning approach for distinguishing ITB from CD.

METHODS

Eighty-two patients including 25 patients with ITB and 57 patients with CD were retrospectively recruited (54 in training cohort and 28 in testing cohort). The region of interest (ROI) for the lesion was delineated on magnetic resonance enterography (MRE) and colonoscopy images. Radiomic features were extracted by least absolute shrinkage and selection operator regression. Pathological feature was extracted automatically by deep-learning method. Clinical features were filtered by logistic regression analysis. Diagnostic performance was evaluated by receiver operating characteristic (ROC) curve and decision curve analysis (DCA). Delong's test was applied to compare the efficiency between the multidisciplinary-based model and the other four single-disciplinary-based models.

RESULTS

The radiomics model based on MRE features yielded an AUC of 0.87 (95% confidence interval [CI] 0.68-0.96) on the test data set, which was similar to the clinical model (AUC, 0.90 [95% CI 0.71-0.98]) and higher than the colonoscopy radiomics model (AUC, 0.68 [95% CI 0.48-0.84]) and pathology deep-learning model (AUC, 0.70 [95% CI 0.49-0.85]). Multidisciplinary model, integrating 3 clinical, 21 MRE radiomic, 5 colonoscopy radiomic, and 4 pathology deep-learning features, could significantly improve the diagnostic performance (AUC of 0.94, 95% CI 0.78-1.00) on the bases of single-disciplinary-based models. DCA confirmed the clinical utility.

CONCLUSIONS

Multidisciplinary-based model integrating clinical, MRE, colonoscopy, and pathology features was useful in distinguishing ITB from CD.

Few-shot learning for the classification of intestinal tuberculosis and Crohn's disease on endoscopic images: A novel learn-to-learn framework

Background and aim

Standard deep learning methods have been found inadequate in distinguishing between intestinal tuberculosis (ITB) and Crohn's disease (CD), a shortcoming largely attributed to the scarcity of available samples. In light of this limitation, our objective is to develop an innovative few-shot learning (FSL) system, specifically tailored for the efficient categorization and differential diagnosis of CD and ITB, using endoscopic image data with minimal sample requirements.

Methods

A total of 122 white-light endoscopic images (99 CD images and 23 ITB images) were collected (one ileum image from each patient). A 2-way, 3-shot FSL model that integrated dual transfer learning and metric learning strategies was devised. Xception architecture was selected as the foundation and then underwent a dual transfer process utilizing oesophagitis images sourced from HyperKvasir. Subsequently, the eigenvectors derived from the Xception for each query image were converted into predictive scores, which were calculated using the Euclidean distances to six reference images from the support sets.

Results

The FSL model, which leverages dual transfer learning, exhibited enhanced performance metrics (AUC 0.81) compared to a model relying on single transfer learning (AUC 0.56) across three evaluation rounds. Additionally, its performance surpassed that of a less experienced endoscopist (AUC 0.56) and even a more seasoned specialist (AUC 0.61).

Conclusions

The FSL model we have developed demonstrates efficacy in distinguishing between CD and ITB using a limited dataset of endoscopic imagery. FSL holds value for enhancing the diagnostic capabilities of rare conditions.

Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches

Eosinophilic chronic rhinosinusitis (ECRS) is a distinct subset of chronic rhinosinusitis characterized by heightened eosinophilic infiltration and increased symptom severity, often resisting standard treatments. Traditional diagnosis requires invasive histological evaluation. This study aims to develop predictive models for ECRS based on patient clinical parameters, eliminating the need for invasive biopsy. Utilizing logistic regression with lasso regularization, random forest (RF), gradient-boosted decision tree (GBDT), and deep neural network (DNN), we trained models on common clinical data. The predictive performance was evaluated using metrics such as area under the curve (AUC) for receiver operator characteristics, decision curves, and feature ranking analysis. In a cohort of 437 eligible patients, the models identified peripheral blood eosinophil ratio, absolute peripheral blood eosinophil, and the ethmoidal/maxillary sinus density ratio (E/M) on computed tomography as crucial predictors for ECRS. This predictive model offers a valuable tool for identifying ECRS without resorting to histological biopsy, enhancing clinical decision-making.

The Risk of Developing Disabling Crohn's Disease: Validation of a Clinical Prediction Rule to Improve Treatment Decision Making

BACKGROUND

Crohn's disease (CD) is characterized by the development of complications over the course of the disease. It is crucial to identify predictive factors of disabling disease, in order to target patients for early intervention. We evaluated risk factors of disabling CD and developed a prognostic model.

METHODS

In total, 511 CD patients were retrospectively analyzed. Univariate and multivariate logistic regression analyses were used to identify demographic, clinical, and biological risk factors. A predictive nomogram model was developed in a subgroup of patients with noncomplicated CD (inflammatory pattern and no perianal disease).

RESULTS

The rate of disabling CD within 5 years after diagnosis was 74.6%. Disabling disease was associated with gender, location of disease, requirement of steroids for the first flare, and perianal lesions. In the subgroup of patients (310) with noncomplicated CD, the rate of disabling CD was 80%. In the multivariate analysis age at onset <40 years (OR = 3.46, 95% confidence interval [CI] = 1.52-7.90), extensive disease (L3/L4) (OR = 2.67, 95% CI = 1.18-6.06), smoking habit (OR = 2.09, 95% CI = 1.03-4.27), requirement of steroids at the first flare (OR = 2.20, 95% CI = 1.09-4.45), and albumin (OR = 0.59, 95% CI = 0.36-0.96) were associated with development of disabling disease. The developed predictive nomogram based on these factors presented good discrimination, with an area under the receiver operating characteristic curve of 0.723 (95% CI: 0.670-0.830).

CONCLUSION

We identified predictive factors of disabling CD and developed an easy-to-use prognostic model that may be used in clinical practice to help identify patients at high risk and address treatment effectively.

Building a trustworthy AI differential diagnosis application for Crohn's disease and intestinal tuberculosis

BACKGROUND

Differentiating between Crohn's disease (CD) and intestinal tuberculosis (ITB) with endoscopy is challenging. We aim to perform more accurate endoscopic diagnosis between CD and ITB by building a trustworthy AI differential diagnosis application.

METHODS

A total of 1271 electronic health record (EHR) patients who had undergone colonoscopies at Peking Union Medical College Hospital (PUMCH) and were clinically diagnosed with CD (n = 875) or ITB (n = 396) were used in this study. We build a workflow to make diagnoses with EHRs and mine differential diagnosis features; this involves finetuning the pretrained language models, distilling them into a light and efficient TextCNN model, interpreting the neural network and selecting differential attribution features, and then adopting manual feature checking and carrying out debias training.

RESULTS

The accuracy of debiased TextCNN on differential diagnosis between CD and ITB is 0.83 (CR F1: 0.87, ITB F1: 0.77), which is the best among the baselines. On the noisy validation set, its accuracy was 0.70 (CR F1: 0.87, ITB: 0.69), which was significantly higher than that of models without debias. We also find that the debiased model more easily mines the diagnostically significant features. The debiased TextCNN unearthed 39 diagnostic features in the form of phrases, 17 of which were key diagnostic features recognized by the guidelines.

CONCLUSION

We build a trustworthy AI differential diagnosis application for differentiating between CD and ITB focusing on accuracy, interpretability and robustness. The classifiers perform well, and the features which had statistical significance were in agreement with clinical guidelines.

A diagnostic model based on routine blood examination for serious bacterial infections in neonates-a cross-sectional study

Routine blood examination is an easy way to examine infectious diseases. This study is aimed to develop a model to diagnose serious bacterial infections (SBI) in ICU neonates based on routine blood parameters. This was a cross-sectional study, and data were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III). SBI was defined as suffering from one of the following: pyelonephritis, bacteraemia, bacterial meningitis, sepsis, pneumonia, cellulitis, and osteomyelitis. Variables with statistical significance in the univariate logistic regression analysis and log systemic immune-inflammatory index (SII) were used to develop the model. The area under the curve (AUC) was calculated to assess the performance of the model. A total of 1,880 participants were finally included for analysis. Weight, haemoglobin, mean corpuscular volume, white blood cell, monocyte, premature delivery, and log SII were selected to develop the model. The developed model showed a good performance to diagnose SBI for ICU neonates, with an AUC of 0.812 (95% confidence interval (CI): 0.737-0.888). A nomogram was developed to make this model visualise. In conclusion, our model based on routine blood parameters performed well in the diagnosis of neonatal SBI, which may be helpful for clinicians to improve treatment recommendations.

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.

Computed tomography enterography-based multiregional radiomics model for differential diagnosis of Crohn's disease from intestinal tuberculosis

PURPOSE

To build computed tomography enterography (CTE)-based multiregional radiomics model for distinguishing Crohn's disease (CD) from intestinal tuberculosis (ITB).

MATERIALS AND METHODS

A total of 105 patients with CD and ITB who underwent CTE were retrospectively enrolled. Volume of interest segmentation were performed on CTE and radiomic features were obtained separately from the intestinal wall of lesion, the largest lymph node (LN), and region surrounding the lesion in the ileocecal region. The most valuable radiomic features was selected by the selection operator and least absolute shrinkage. We established nomogram combining clinical factors, endoscopy results, CTE features, and radiomic score through multivariate logistic regression analysis. Receiver operating characteristic (ROC) curves and decision curve analysis (DCA) were used to evaluate the prediction performance. DeLong test was applied to compare the performance of the models.

RESULTS

The clinical-radiomic combined model comprised of four variables including one radiomic signature from intestinal wall, one radiomic signature from LN, involved bowel segments on CTE, and longitudinal ulcer on endoscopy. The combined model showed good diagnostic performance with an area under the ROC curve (AUC) of 0.975 (95% CI 0.953-0.998) in the training cohort and 0.958 (95% CI 0.925-0.991) in the validation cohort. The combined model showed higher AUC than that of the clinical model in cross-validation set (0.958 vs. 0.878, P = 0.004). The DCA showed the highest benefit for the combined model.

CONCLUSION

Clinical-radiomic combined model constructed by combining CTE-based radiomics from the intestinal wall of lesion and LN, endoscopy results, and CTE features can accurately distinguish CD from ITB.

Lymphoepithelial carcinoma of the head and neck: a SEER analysis of prognostic factors for survival

OBJECTIVE

To explore the epidemiological characteristics of patients with lymphoepithelial carcinoma (LEC) of the head and neck and the prognostic factors.

METHODS

We conducted a retrospective cohort study of cases of head and neck LEC retrieved from the Surveillance, Epidemiology and End Results database. Kaplan-Meier survival analysis and the log-rank test were employed to assess overall survival (OS) and cancer-specific survival (CSS). Univariate and multivariate analyses were used to construct Cox regression models. We established nomograms to predict OS and CSS among patients with nasopharyngeal LEC, who were divided into high- and low-risk groups based on the OS nomograms to compare the effects of treatment using the restricted mean survival time (RMST).

RESULTS

The 5-year OS and CSS rates of the cohort were 70.8% and 74.8%, respectively. Advanced age, unmarried status, black race, distant metastasis, and the absence of surgical treatment were significantly associated with decreased survival rates. RMST did not differ between the combined treatment (radiotherapy and chemotherapy) and radiotherapy monotherapy groups, but chemotherapy alone displayed poor efficacy.

CONCLUSIONS

Head and neck LEC is associated with a favorable prognosis. Radiotherapy plays a significant role in managing patients with nasopharyngeal LEC, which is influenced by multiple prognostic factors.

Clinical Analysis of Intestinal Tuberculosis: A Retrospective Study

PURPOSE

This study aimed to summarize and analyze the clinical data of intestinal tuberculosis (ITB) in order to provide guidance for accurate diagnosis and treatment of ITB.

METHODS

This study consecutively included patients with ITB who were admitted to our hospital from 2008 to 2021 and retrospectively analyzed their clinical features.

RESULTS

Forty-six patients were included. The most common clinical symptom was weight loss (67.4%). Seventy percent of 20 patients were positive for tuberculin skin test; 57.1% of 14 patients were positive for mycobacterium tuberculosis specific cellular immune response test, while 84.6% of 26 patients were positive for tuberculosis infection T cell spot test. By chest computed tomography (CT) examination, 25% and 5.6% of 36 patients were diagnosed with active pulmonary tuberculosis and with inactive pulmonary tuberculosis, respectively. By abdominal CT examination, the most common sign was abdominal lymph node enlargement (43.2%). Forty-two patients underwent colonoscopy, and the most common endoscopic manifestation was ileocecal ulcer (59.5%), followed by colonic ulcer (35.7%) and ileocecal valve deformity (26.2%). ITB most frequently involved the terminal ileum/ileocecal region (76.1%). Granulomatous inflammation with multinucleated giant cells and caseous necrosis was found via endoscopic biopsies, the ultrasound-guided percutaneous biopsy of enlarged mesentery lymph nodes, and surgical interventions. The acid-fast bacilli were discovered in 53.1% of 32 samples. Twenty-one cases highly suspected of ITB were confirmed after responding to empiric anti-tuberculosis therapy.

CONCLUSIONS

It was necessary to comprehensively analyze clinical features to make an accurate diagnosis of ITB and aid in distinguishing ITB from diseases such as Crohn's disease and malignant tumors.

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.

Novel postoperative nomograms for predicting individual prognoses of hepatitis B-related hepatocellular carcinoma with cirrhosis

Background

Liver cirrhosis is a well-known risk factor for carcinogenesis of hepatocellular carcinoma (HCC). The aim of the present study was to construct individual prognostic models for HCC with cirrhosis.

Methods

The clinical differences between HCC patients with and without cirrhosis were compared using a large cohort of 1003 cases. The patients with cirrhosis were randomly divided into a training cohort and a validation cohort in a ratio of 2:1. Univariate and multivariate analyses were performed to reveal the independent risk factors for recurrence-free survival (RFS) and overall survival (OS) in HCC patients with cirrhosis. These factors were subsequently used to construct nomograms.

Results

Multivariate analyses revealed that five clinical variables (hepatitis B e antigen (HBeAg) positivity, alpha-fetoprotein (AFP) level, tumour diameter, microvascular invasion (MVI), and satellite lesions) and seven variables (HBeAg positivity, AFP level, tumour diameter, MVI, satellite lesions, gamma-glutamyl transpeptidase level, and histological differentiation) were significantly associated with RFS and OS, respectively. The C-indices of the nomograms for RFS and OS were 0.739 (P < 0.001) and 0.789 (P < 0.001), respectively, in the training cohort, and 0.752 (P < 0.001) and 0.813 (P < 0.001), respectively, in the validation cohort. The C-indices of the nomograms were significantly higher than those of conventional staging systems (P < 0.001). The calibration plots showed optimal consistence between the nomogram-predicted and observed prognoses.

Conclusions

The nomograms developed in the present study showed good performance in predicting the prognoses of HCC patients with hepatitis B virus-associated cirrhosis.

Prognostic nomograms for lung neuroendocrine carcinomas based on lymph node ratio: a SEER database analysis

Objective

The current study aimed to explore the prognostic value of the lymph node ratio (LNR) in patients with lung neuroendocrine carcinomas (LNECs).

Methods

Data for 1564 elderly patients with LNECs between 1998 and 2016 were obtained from the Surveillance, Epidemiology, and End Results database. The cases were assigned randomly to training (n = 1086) and internal validation (n = 478) sets. The association between LNR and survival was investigated by Cox regression.

Results

Multivariate analyses identified age, tumor grade, summary stage, M stage, surgery, and LNR as independent prognostic factors for both overall survival (OS) and lung cancer-specific survival (LCSS). Tumor size was also a prognostic determinant for LCSS. Prognostic nomograms combining LNR with other informative variables showed good discrimination and calibration abilities in both the training and validation sets. In addition, the C-index of the nomograms was statistically superior to the American Joint Committee on Cancer (AJCC) staging system in both the training and validation cohorts.

Conclusions

These nomograms, based on LNR, showed superior prognostic predictive accuracy compared with the AJCC staging system for predicting OS and LCSS in patients with LNECs.

Computed tomography enterography increases the ability of endoscopy to differentiate Crohn's disease from intestinal Behçet's disease

Background

Distinguishing Crohn's disease (CD) and intestinal Behçet's disease (BD) is difficult in clinical practice.

Aim

To evaluate the ability of CT enterography (CTE) to enhance the diagnostic value of endoscopy in differentiating CD from intestinal BD and to establish differential diagnosis models.

Methods

A total of 113 patients with CD and 70 patients with intestinal BD from seven tertiary inflammatory bowel disease centers were enrolled. The univariate and multivariate analyses were used by SAS software version 9.2. Three differential scoring models based on the multivariate analysis of endoscopic features alone (model 1), endoscopic features combined with clinical symptoms (model 2), and endoscopic features combined with clinical symptoms and CTE (model 3) were established.

Results

The results showed that model 2 increased the efficacy of model 1 in differential diagnosis and model 3 had the highest accuracy of 84.15% at a cutoff value of two points. The scoring of model 3 was as follows: genital ulcer (−3 points), skin lesions (−3 points), oval ulcer (-2 points), longitudinal ulcer (1 point), number of ulcers > 5 (3 points), inflammatory polyps (2 points), mucosal severe enhancement (2 points), and fibrofatty proliferation (1 point).

Conclusion

Clinical symptoms and CTE increased the ability of endoscopy to differentiate CD from intestinal BD.

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.

Preoperative and postoperative nomograms for predicting early recurrence of hepatocellular carcinoma without macrovascular invasion after curative resection

BACKGROUND

Postoperative early recurrence (ER) is a major obstacle to long-term survival after curative liver resection (LR) in patients with hepatocellular carcinoma (HCC). This study aimed to establish preoperative and postoperative nomograms to predict ER in HCC without macrovascular invasion.

METHODS

Patients who underwent curative LR for HCC between January 2012 and December 2016 were divided into training and internal prospective validation cohorts. Nomograms were constructed based on independent risk factors derived from the multivariate logistic regression analyses in the training cohort. The predictive performances of the nomograms were validated using the internal prospective validation cohort.

RESULTS

In total, 698 patients fulfilled the eligibility criteria. Among them, 265 of 482 patients (55.0%) in the training cohort and 120 of 216 (55.6%) patients in the validation cohort developed ER. The preoperative risk factors associated with ER were age, alpha-fetoprotein, tumor diameter, and tumor number, and the postoperative risk factors associated with ER were age, tumor diameter, tumor number, microvascular invasion, and differentiation. The pre- and postoperative nomograms based on these factors showed good accuracy, with concordance indices of 0.712 and 0.850 in the training cohort, respectively, and 0.754 and 0.857 in the validation cohort, respectively. The calibration curves showed optimal agreement between the predictions by the nomograms and actual observations. The area under the receiver operating characteristic curves of the pre- and postoperative nomograms were 0.721 and 0.848 in the training cohort, respectively, and 0.754 and 0.844 in the validation cohort, respectively.

CONCLUSIONS

The nomograms constructed in this study showed good performance in predicting ER for HCC without macrovascular invasion before and after surgery. These nomograms would be helpful for doctors when determining treatments and selecting patients for regular surveillance or administration of adjuvant therapies.

Network Clinical Collaboration to Improve Quality of Care of Patients With Inflammatory Bowel Disease in China

The burden of IBD management in China is increasing due to the mounting number of patients. We presented in the 2021 China IBD Special Issue a series of original articles, which will be important for encouraging and inspiring more network collaboration to improve quality of care of patients with IBD in China.

Two Novel Nomograms Predicting the Risk and Prognosis of Pancreatic Cancer Patients With Lung Metastases: A Population-Based Study

Background

Pancreatic cancer (PC) is one of the most common malignant types of cancer, with the lung being the frequent distant metastatic site. Currently, no population-based studies have been done on the risk and prognosis of pancreatic cancer with lung metastases (PCLM). As a result, we intend to create two novel nomograms to predict the risk and prognosis of PCLM.

Methods

PC patients were selected from the Surveillance, Epidemiology, and End Results Program (SEER) database from 2010 to 2016. A multivariable logistic regression analysis was used to identify risk factors for PCLM at the time of diagnosis. The multivariate Cox regression analysis was carried out to assess PCLM patient's prognostic factors for overall survival (OS). Following that, we used area under curve (AUC), time-dependent receiver operating characteristics (ROC) curves, calibration plots, consistency index (C-index), time-dependent C-index, and decision curve analysis (DCA) to evaluate the effectiveness and accuracy of the two nomograms. Finally, we compared differences in survival outcomes using Kaplan-Meier curves.

Results

A total of 803 (4.22%) out of 19,067 pathologically diagnosed PC patients with complete baseline information screened from SEER database had pulmonary metastasis at diagnosis. A multivariable logistic regression analysis revealed that age, histological subtype, primary site, N staging, surgery, radiotherapy, tumor size, bone metastasis, brain metastasis, and liver metastasis were risk factors for the occurrence of PCLM. According to multivariate Cox regression analysis, age, grade, tumor size, histological subtype, surgery, chemotherapy, liver metastasis, and bone metastasis were independent prognostic factors for PCLM patients' OS. Nomograms were constructed based on these factors to predict 6-, 12-, and 18-months OS of patients with PCLM. AUC, C-index, calibration curves, and DCA revealed that the two novel nomograms had good predictive power.

Conclusion

We developed two reliable predictive models for clinical practice to assist clinicians in developing individualized treatment plans for patients.

Differential Diagnosis of Crohn’s Disease and Ulcerative Primary Intestinal Lymphoma: A Scoring Model Based on a Multicenter Study

Background

Differential diagnosis of Crohn’s disease (CD) and ulcerative primary intestinal lymphoma (UPIL) is a tough problem in clinical practice.

Aims

Our study identified key differences between CD and UPIL patients and aimed to further establish a scoring model for differential diagnosis.

Methods

A total of 91 CD and 50 UPIL patients from 9 tertiary inflammatory bowel disease centers were included. Univariate and multivariate analyses were used to determine significant markers for differentiating CD and UPIL. A differential scoring model was established by logistic regression analysis.

Results

The differential model was based on clinical symptoms, endoscopic and imaging features that were assigned different scores: intestinal bleeding (−2 points), extraintestinal manifestation (2 points), segmental lesions (1 point), cobblestone sign (2 points), homogeneous enhancement (−1 point), mild enhancement (−1 point), engorged vasa recta (1 point). A total score of ≥1 point indicates CD, otherwise UPIL was indicated. This model produced an accuracy of 83.66% and an area under the ROC curve of 0.947. The area under the ROC curve for validation using the 10-fold validation method was 0.901.

Conclusion

This study provided a convenient and useful model to differentiate CD from UPIL.

Nomogram and Machine Learning Models Predict 1-Year Mortality Risk in Patients With Sepsis-Induced Cardiorenal Syndrome

Objective

Early prediction of long-term outcomes in patients with sepsis-induced cardiorenal syndrome (CRS) remains a great challenge in clinical practice. Herein, we aimed to construct a nomogram and machine learning model for predicting the 1-year mortality risk in patients with sepsis-induced CRS.

Methods

This retrospective study enrolled 340 patients diagnosed with sepsis-induced CRS in Shanghai Tongji Hospital between January 2015 and May 2019, as a discovery cohort. Two predictive models, the nomogram and machine learning model, were used to predict 1-year mortality. The prognostic variables used to develop the nomogram were identified based on a forward stepwise binary logistic regression, and the predictive ability of the nomogram was evaluated by the areas under the receiver operating characteristic curve (AUC) and the calibration curve. Meanwhile, machine learning (ML) techniques, such as support vector machine, random forest (RF), and gradient boosted decision tree, were assessed mainly by accuracy and AUC. Feature ranking analysis was performed using the ML algorithm. Both nomogram and ML models were externally validated by an independent cohort of 103 patients diagnosed with sepsis-induced CRS between June 2019 and December 2020.

Results

Age, sequential sepsis-related organ failure score (SOFA), serum myoglobin (MYO), vasopressor use, and mechanical ventilation were identified as independent risk factors for 1-year mortality in the nomogram predictive model. In the discovery cohort, the nomogram yielded higher AUC for predicting mortality than did the SOFA score (0.855 [95% CI: 0.815–0.895] vs. 0.756 [95% CI: 0.705–0.808]). For ML, the model developed by RF showed the highest accuracy (0.765) and AUC (0.854). In feature ranking analysis, factors such as age, MYO, SOFA score, vasopressor use, and baseline serum creatinine were identified as important features affecting 1-year prognosis. Moreover, the nomogram and RF model both performed well in external validation, with an AUC of 0.877 and 0.863, respectively.

Conclusion

Our nomogram and ML models showed that age, SOFA score, serum MYO levels, and the use of vasopressors during hospitalization were the main factors influencing the risk of long-term mortality. Our models may serve as useful tools for assessing long-term prognosis in patients with sepsis-induced CRS.

Comments on validation of conventional non-invasive fibrosis scoring systems in patients with metabolic associated fatty liver disease

To evaluate and predict liver fibrosis in patients with nonalcoholic fatty liver disease (NAFLD), several non-invasive scoring systems were built and widely used in the progress of diagnosis and treatment, which showed great diagnostic efficiency, such as aspartate aminotransferase to platelet ratio index, fibrosis-4 index, body mass index, aspartate aminotransferase to alanine aminotransferase ratio, diabetes score and NAFLD fibrosis score. Since the new concept of metabolic associated fatty liver disease (MAFLD) was proposed, the clinical application value of the non-invasive scoring systems mentioned above has not been assessed in MAFLD. The evaluation of the diagnostic performance of these non-invasive scoring systems will provide references for clinicians in the diagnosis of MAFLD.

Metastasis Pattern and Survival Analysis in Primary Small Bowel Adenocarcinoma: A SEER-Based Study

Background: Small bowel adenocarcinoma (SBA) is a rare gastrointestinal tumor with high malignancy. The aim of this study was to comprehensively evaluate the distant metastasis pattern and establish nomograms predicting survival for SBA. Methods: From 2010 to 2015, patients diagnosed with SBA were identified based on the Surveillance, Epidemiology, and End Results (SEER) database. Kaplan-Meier survival analysis was applied to compare survival differences between metastasis patterns. Then, univariate and multivariate cox analyses were applied to screened out independent prognostic factors of cancer-specific survival (CSS) and overall survival (OS), and identify the risk factors for metastasis of SBA. To assess the discrimination and calibration of nomograms, the concordance index (C-index), calibration curves, receiver-operating characteristic curve (ROC), and decision curve analysis (DCA) were calculated. Results: Kaplan-Meier curves revealed that metastasis patterns were significantly correlated with CSS (p < 0.001) and OS (p < 0.001). Then, the metastasis pattern was showed to be an independent prognostic factor of OS and CSS in patients with SBA, as well as age, grade, T stage, N stage, surgery, retrieval of regional lymph nodes, and chemotherapy. Combining these factors, we constructed prognostic nomograms, which suggested that the metastasis pattern made the greatest contribution to the survival of patients with SBA. Nomograms for OS and CSS had a C-index of 0.787 and 0.793, respectively. Calibration curves showed an excellent agreement between probability and actual observation in the training and validation cohort. Decision curve analysis also exhibited its clinical value with an improved net benefit. In addition, the models we constructed had better prognostic accuracy and clinical utility than traditional TNM staging based on C-index and ROC. Further, Cox regression analysis showed that old age, poor differentiation, N2, and not receiving chemotherapy were the risk factors for prognosis in patients with metastatic SBA. Conclusion: As an independent prognostic factor, the metastasis pattern exhibited the greatest predictive effect on OS and CSS for patients with SBA. Adjuvant chemotherapy had a positive effect on the survival of patients with SBA. Nomograms for predicting 3-and 5-year OS and CSS of patients with SBA were constructed, which could identify patients with higher risk and might be superior in predicting the survival of patients with SBA than TNM staging.

A Novel Clinical Radiomics Nomogram to Identify Crohn's Disease from Intestinal Tuberculosis

Purpose

To establish a clinical radiomics nomogram to differentiate Crohn’s disease (CD) from intestinal tuberculosis (ITB).

Patients and Methods

Ninety-three patients with CD and 67 patients with ITB were recruited (111 in training cohort and 49 in test cohort). The region of interest (ROI) for the lesions in the ileocecal region was delineated on computed tomography enterography and radiomics features extracted. Radiomics features were filtered by the gradient boosting decision tree (GBDT), and a radiomics score was calculated by using the radiomics signature-based formula. We constructed a clinical radiomics model and nomogram combining clinical factors and radiomics score through multivariate logistic regression analysis, and the internal validation was undertaken by ten-fold cross validation. Analyses of receiver operating characteristic (ROC) curves and decision curve analysis (DCA) were used to evaluate the prediction performance. DeLong test was applied to evaluate the performance of the clinical, radiomics and combined model.

Results

The clinical radiomics nomogram, which was based on the 9 radiomics signature and two clinical factors, indicated that the clinical radiomics model had an area under the ROC curve (AUC) value of 0.96 (95% confidence interval [CI]: 0.93–0.99) in the training cohort and 0.93 (95% CI: 0.86–1.00) in validation cohort. The clinical radiomics model was superior to the clinical model and radiomics model, and the difference was significant (P = 0.006, 0.004) in the training cohort. DCA confirmed the clinical utility of clinical radiomics nomogram.

Conclusion

CTE-based radiomics model has a good performance in distinguishing CD from ITB. A nomogram constructed by combining radiomics and clinical factors can help clinicians accurately diagnose and select appropriate treatment strategies between CD and ITB.

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.

Alterations of Gut Microbiota in Patients With Intestinal Tuberculosis That Different From Crohn's Disease

Intestinal tuberculosis (ITB) and Crohn's disease (CD) are chronic inflammatory bowel disorders that are associated with dysregulated mucosal immunity. The gut microbiota plays an important role in the regulation of host immunity and inflammatory response. Although mounting evidence has linked CD with the dysbiosis of gut microbiota, the characteristic profiles of mucosal bacteria in ITB remain unclear. The aim of this study was to assess the alterations of the gut microbiota in ITB and compare the microbial structure of ITB with CD. A total of 71 mucosal samples were collected from patients with ITB, CD, and healthy controls (HC), and then, 16S rRNA gene sequencing was performed. The overall composition of gut microbiota in ITB was strikingly different from HC, with the dominance of Proteobacteria and reduction of Firmicutes. Of note, the short-chain fatty acids (SCFAs)-producing bacteria such as Faecalibacterium, Roseburia, and Ruminococcus were decreased in ITB relative to HC, while Klebsiella and Pseudomonas were enriched. Multiple predictive functional modules were altered in ITB, including the over-representation of lipopolysaccharide biosynthesis, bacterial invasion of epithelial cells, and pathogenic Escherichia coli infection that can promote inflammation. Additionally, the microbial structure in CD was distinctly different from ITB, characterized by lower alpha diversity and increased abundance of Bacteroides, Faecalibacterium, Collinsella, and Klebsiella. These four bacterial markers distinguished ITB from CD with an area under the curve of 97.6%. This study established the compositional and functional perturbation of the gut microbiome in ITB and suggested the potential for using gut microbiota as biomarkers to differentiate ITB from CD.

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.

Development and External Validation a Novel Inflammation-Based Score for Acute Kidney Injury and Prognosis in Intensive Care Unit Patients

Purpose

We aimed to evaluate the predictive ability of an integrated score based on several inflammatory indices of acute kidney injury (AKI) in patients in the intensive care unit (ICU).

Patients and Methods

In this observational study, 2555 patients from the Medical Information Mart for Intensive Care III database were randomly assigned to the test set (n=1599) and internal validation set (n=656). Moreover, 412 coronary care unit patients from Zhongnan Hospital, Wuhan University were also included in the external validation set. The AKI-specific inflammatory index (ASII) was created using various inflammatory indices significantly associated with AKI. We further developed and validated two nomograms based on the ASII and other informative clinical features of AKI and prognosis.

Results

The ASII was calculated as 2.317×MLR+0.417×GPS+0.007×ALRI. In the training set, patients with a high ASII had a higher risk of incident AKI (odds ratio [OR], 5.33; 95% confidence index [CI], 3.60–7.88; P<0.001) than those with a low ASII with or without pre-existing chronic kidney disease. The nomograms for AKI and prognosis based on the ASII and other significant clinical characteristics had high predictive value in the prediction of AKI and prognosis in patients in the ICU. Moreover, the results in the internal validation set and in the external validation cohort were almost consistent with those in the training set.

Conclusion

The ASII is an AKI-specific tool based on the combination of available inflammatory indices. A high ASII is a strong predictor of a higher risk of AKI and worse survival outcomes in patients in the ICU.

Infectious diseases affecting the small bowel - what not to miss

PURPOSE OF REVIEW

This review summarizes infectious diseases involving the small bowel (SB) with a focus on recent literature related to diagnosis and pathophysiology.

RECENT FINDINGS

Typical symptom for SB infections is diarrhea, mostly self-limiting. Pathogens include bacteria, viruses, fungi, protozoan parasites, and helminths. Host-pathogen interaction is of special interest in infections with potentially severe or prolonged course. Research uses increasingly enterocyte cell culture systems. SARS-CoV2 can also infect enterocytes via angiotensin converting enzyme 2 (ACE2) receptor and causes gastrointestinal complaints in some patients. Chronic SB infections as tuberculosis, Cytomegalovirus, or Epstein-Barr virus have to be differentiated from Crohn's and other diseases. Severe rare fungal and protozoan parasitic infections can cause relevant morbidity in immunocompromised patients. Soil-transmitted helminthic infections are a special issue in endemic areas.

SUMMARY

Many infections involve the SB, typically causing mild and self-limiting diarrhea. Symptomatic therapy, hygiene, and isolation are the mainstay of management. However, some patients develop severe or chronic disease. Immunosuppression is a major cause for severe, but also for rare opportunistic systemic infections that can also affect the SB.

Challenges in the diagnosis and management of inflammatory bowel disease in resource-limited settings in Asia

Inflammatory bowel disease (IBD) is increasing in prevalence in resource-limited settings in Asia. Although the prevalence of IBD is lower in these settings than in high-income countries, the high disease burden due to large population size is projected to overtake that of high-income countries in the near future. Unique challenges exist for diagnosing and managing IBD in Asia. On one hand, the inadequate disease awareness in physicians and the general population, the scarcity of diagnostic services, the infectious mimics of IBD (specifically intestinal tuberculosis), and the widespread use of empirical antibiotics and antitubercular therapy pose diagnostic challenges. On the other hand, the absence of a centralised health-care delivery system or universal health insurance, the high cost of therapy, limited access to biologics, and the high risk of opportunistic infections with immunosuppressive therapy present therapeutic challenges. The high probability of tuberculosis reactivation often precludes biological therapy because Asia is highly endemic for tuberculosis and has a high prevalence of latent tuberculosis. Current screening strategies are often ineffective in ruling out latent tuberculosis. Hence, management strategies are often modified according to these challenges. This Series paper discusses the challenges in the diagnosis and management of IBD in resource-limited settings in Asia.

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.

Can natural language processing help differentiate inflammatory intestinal diseases in China? Models applying random forest and convolutional neural network approaches

Background

Differentiating between ulcerative colitis (UC), Crohn’s disease (CD) and intestinal tuberculosis (ITB) using endoscopy is challenging. We aimed to realize automatic differential diagnosis among these diseases through machine learning algorithms.

Methods

A total of 6399 consecutive patients (5128 UC, 875 CD and 396 ITB) who had undergone colonoscopy examinations in the Peking Union Medical College Hospital from January 2008 to November 2018 were enrolled. The input was the description of the endoscopic image in the form of free text. Word segmentation and key word filtering were conducted as data preprocessing. Random forest (RF) and convolutional neural network (CNN) approaches were applied to different disease entities. Three two-class classifiers (UC and CD, UC and ITB, and CD and ITB) and a three-class classifier (UC, CD and ITB) were built.

Results

The classifiers built in this research performed well, and the CNN had better performance in general. The RF sensitivities/specificities of UC-CD, UC-ITB, and CD-ITB were 0.89/0.84, 0.83/0.82, and 0.72/0.77, respectively, while the values for the CNN of CD-ITB were 0.90/0.77. The precisions/recalls of UC-CD-ITB when employing RF were 0.97/0.97, 0.65/0.53, and 0.68/0.76, respectively, and when employing the CNN were 0.99/0.97, 0.87/0.83, and 0.52/0.81, respectively.

Conclusions

Classifiers built by RF and CNN approaches had excellent performance when classifying UC with CD or ITB. For the differentiation of CD and ITB, high specificity and sensitivity were achieved as well. Artificial intelligence through machine learning is very promising in helping unexperienced endoscopists differentiate inflammatory intestinal diseases.

Conference

The abstract of this article has won the first prize of the Young Investigator Award during the Asian Pacific Digestive Week (APDW) 2019 held in Kolkata, India.

Development and validation of a novel scoring system developed from a nomogram to identify malignant pleural effusion

BACKGROUND

This study aimed to establish and validate a novel scoring system based on a nomogram for the differential diagnosis of malignant pleural effusion (MPE) and benign pleural effusion (BPE).

METHODS

Patients with PE and confirmed aetiology who underwent diagnostic thoracentesis were included in this study. One retrospective set (N = 1261) was used to develop and internally validate the predictive model. The clinical, radiological and laboratory features were collected and subjected to logistic regression analyses. The primary predictive model was displayed as a nomogram and then modified into a novel scoring system, which was externally validated in an independent set (N = 172).

FINDINGS

The novel scoring system was composed of fever (3 points), erythrocyte sedimentation rate (4 points), effusion adenosine deaminase (7 points), serum carcinoembryonic antigen (CEA) (4 points), effusion CEA (10 points) and effusion/serum CEA (8 points). With a cutoff value of 15 points, the area under the curve, specificity and sensitivity for identifying MPE were 0.913, 89.10%, and 82.63%, respectively, in the training set, 0.922, 93.48%, 81.51%, respectively, in the internal validation set and 0.912, 87.61%, 81.36%, respectively, in the external validation set. Moreover, this scoring system was exclusively applied to distinguish lung cancer with PE from tuberculous pleurisy and showed a favourable diagnostic performance in the training and validation sets.

INTERPRETATION

This novel scoring system was developed from a retrospective study and externally validated in an independent set based on six easily accessible clinical variables, and it exhibited good diagnostic performance for identifying MPE.

FUNDING

NFSC grants (no. 81572942, no. 81800094).

A validated survival nomogram for early-onset diffuse gastric cancer

This study aimed to establish and independently validate a prognostic nomogram for individual risk prediction in patients with early-onset diffuse gastric cancer (EODGC). Data for 794 patients with EODGC from the SEER database were randomly assigned to training (N=558) and internal validation (N=236) sets, and data for 82 patients from the Renmin Hospital of Wuhan University (RMHWHU) were used as an independent validation cohort. Our LASSO regression analyses of the training set yielded five clinicopathological features (race, AJCC stage, surgery for primary site, chemotherapy and tumor size), which were used to create a survival nomogram. Our survival nomogram achieved better predictive performance than the AJCC staging system, the current standard. Additionally, the calibration curves of the prognostic nomogram revealed good agreement between the predicted survival probabilities and the ground truth values. Indeed, our nomogram, which estimates individualized survival probabilities for patients with EODGC, shows good predictive accuracy and calibration ability for both the SEER and RMHWHU cohorts. These results suggest that a survival nomogram may be better at predicting OS for EODGC patients than the AJCC staging system.

Long Noncoding RNA and Predictive Model To Improve Diagnosis of Clinically Diagnosed Pulmonary Tuberculosis

Clinically diagnosed pulmonary tuberculosis (PTB) patients lack microbiological evidence of Mycobacterium tuberculosis, and misdiagnosis or delayed diagnosis often occurs as a consequence. We investigated the potential of long noncoding RNAs (lncRNAs) and corresponding predictive models to diagnose these patients. We enrolled 1,764 subjects, including clinically diagnosed PTB patients, microbiologically confirmed PTB cases, non-TB disease controls, and healthy controls, in three cohorts (screening, selection, and validation).

Clinically diagnosed pulmonary tuberculosis (PTB) patients lack microbiological evidence of Mycobacterium tuberculosis, and misdiagnosis or delayed diagnosis often occurs as a consequence. We investigated the potential of long noncoding RNAs (lncRNAs) and corresponding predictive models to diagnose these patients. We enrolled 1,764 subjects, including clinically diagnosed PTB patients, microbiologically confirmed PTB cases, non-TB disease controls, and healthy controls, in three cohorts (screening, selection, and validation). Candidate lncRNAs differentially expressed in blood samples of the PTB and healthy control groups were identified by microarray and reverse transcription-quantitative PCR (qRT-PCR) in the screening cohort. Logistic regression models were developed using lncRNAs and/or electronic health records (EHRs) from clinically diagnosed PTB patients and non-TB disease controls in the selection cohort. These models were evaluated by area under the concentration-time curve (AUC) and decision curve analyses, and the optimal model was presented as a Web-based nomogram, which was evaluated in the validation cohort. Three differentially expressed lncRNAs (ENST00000497872, n333737, and n335265) were identified. The optimal model (i.e., nomogram) incorporated these three lncRNAs and six EHRs (age, hemoglobin, weight loss, low-grade fever, calcification detected by computed tomography [CT calcification], and interferon gamma release assay for tuberculosis [TB-IGRA]). The nomogram showed an AUC of 0.89, a sensitivity of 0.86, and a specificity of 0.82 in differentiating clinically diagnosed PTB cases from non-TB disease controls of the validation cohort, which demonstrated better discrimination and clinical net benefit than the EHR model. The nomogram also had a discriminative power (AUC, 0.90; sensitivity, 0.85; specificity, 0.81) in identifying microbiologically confirmed PTB patients. lncRNAs and the user-friendly nomogram could facilitate the early identification of PTB cases among suspected patients with negative M. tuberculosis microbiological evidence.

Prospective validation of CD4+CD25+FOXP3+ T-regulatory cells as an immunological marker to differentiate intestinal tuberculosis from Crohn's disease

Background/Aims

Crohn’s disease (CD) and intestinal tuberculosis (ITB) remain “difficult-to-differentiate” diseases. We have previously documented peripheral blood frequency of CD4⁺ CD25⁺ FOXP3⁺ T-regulatory cells (Treg) as a biomarker to differentiate CD and ITB. We tried to validate these results in a larger cohort of CD and ITB patients.

Methods

Seventy treatment naïve patients of CD (n = 23) and ITB (n = 47) (diagnosed by standard criteria) were recruited prospectively from October 2016 to May 2017. Patients with history of antitubercular therapy in the past were excluded. The frequency of Treg cells in peripheral blood was determined by flow cytometry, and compared between CD and ITB patients.

Results

Similar to our previous study, frequency of Treg cells in peripheral blood was significantly increased in ITB as compared to CD patients (40.9 [interquartile range, 33–50] vs. 24.9 [interquartile range, 14.4–29.6], P<0.001). Further, the receiver operating characteristics curve also showed good diagnostic accuracy with an area under the curve (AUC) of 0.77 (95% confidence interval, 0.65–0.89) and a FOXP3⁺ cutoff value of > 31.3% had a sensitivity and specificity of 83% and 82.6% respectively, to differentiate ITB from CD. Even for the indeterminate cases (n = 33), Treg cell frequency had similar diagnostic accuracy with an AUC of 0.85 (95% confidence interval, 0.68–0.95) and a cutoff of 32.37% had sensitivity and specificity of 87% and 95% respectively, to differentiate ITB from CD.

Conclusions

The current findings validate that the increased frequency of CD4⁺ CD25⁺ FOXP3⁺ Treg in the peripheral blood can be used as a biomarker with high diagnostic accuracy to differentiate ITB from CD.

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.

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.