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.

Pulmonary and intestinal tuberculosis with COVID-19 complicated with fluidopneumothorax and colovesical fistula: The importance of diagnosis complexity in line with clinical setting.

The complication of hydropneumothorax and colovesical fistula is rare, especially in patients with tuberculosis (TB) and COVID-19. This particular situation poses a management difficulty, and can significantly threaten the patient's life without a clear diagnosis and timely treatment. We report a 28-year-old woman with pulmonary and intestinal TB with COVID-19 complicated with hydropneumothorax and colovesical fistula (CVF) which worsened her condition. Treatment for this patient was given according to the diagnosis. Her condition improved and she was discharged after 30 days of hospitalization, while elective surgery for CVF was not performed because there were no clinical symptoms complained of by this patient after completing TB treatment (9 months after hospital discharge). This case report highlights the importance of considering pulmonary and intestinal TB with COVID-19 as the cause of hydropneumothorax and CVF. Early and complex diagnosis is essential for proper management, as well as the efficacy of medical therapy and treatment for controlling such advanced stages of the disease. A complex condition with many symptoms can overlap with other diseases. Clinicians should consider the clinical symptoms, radiological imaging, and standard or supporting examination for accurate diagnosis to find the etiology of the diseases. Complete treatment for TB should be considered as the treatment choice (nonsurgical therapy) for CVF caused by TB before deciding on surgical intervention.

Coexistence of Carcinoma and Tuberculosis in the Cecum: A Clinical Conundrum.

The coexistence of carcinoma of the colon and tuberculosis (TB) represents a rare and intricate clinical scenario. It poses significant challenges in both diagnosis and management. Clinical prediction of this coexistence is challenging since the clinical features of these two conditions are often similar. Likewise, the radiology is not decisive because of the significant overlap in the image findings of carcinoma and TB. A conclusive diagnosis relies on histopathological evidence of both malignancy and TB. Here, we report a case of a 58-year-old female who presented with chronic abdominal pain. Computed tomography showed the presence of a mass in the cecum. Histopathology of tissue retrieved through colonoscopy was indicative of features of both TB and adenocarcinoma of the cecum. Mycobacterium tuberculosis was detected in the tissue by cartridge-based nucleic acid amplification test. The patient was initiated on antitubercular treatment. She underwent surgical resection of the mass and is planned for adjuvant chemotherapy.

Acute abdomen revealing abdominal tuberculosis complicated by a proximal jejunal perforation: Case report.

Abdominal tuberculosis (TB) remains a significant health concern globally, particularly in regions with high endemicity such as North Africa and Morocco. Despite advances in diagnostic modalities, the nonspecific presentation of abdominal TB poses challenges for timely diagnosis and management. Here, we report a case of abdominal TB in a critically state of a young man from Morocco, presenting with acute abdominal pain and signs of sepsis. Radiological investigations revealed features suggestive of intestinal perforation complicating peritoneal TB. Urgent laparotomy confirmed the diagnosis, yet the patient succumbed to advanced sepsis postoperatively. This case underscores the complexity of abdominal TB diagnosis and management, necessitating a high index of suspicion and multidisciplinary collaboration. With evolving surgical techniques and ongoing research efforts, optimizing strategies for early detection and treatment of abdominal TB remains imperative, particularly in endemic regions.

Immunohistochemistry and real-time Polymerase Chain Reaction: importance in the diagnosis of intestinal tuberculosis in a Peruvian population.

INTRODUCTION: The diagnosis of intestinal tuberculosis is challenging even nowadays. This study aims to report the positivity rates of new diagnostic methods such as immunohistochemistry and Real-Time Polymerase Chain Reaction in patients with intestinal tuberculosis, as well as describe the pathological and endoscopic features of intestinal tuberculosis in our population. METHODS: This was a retrospective observational study conducted in patients diagnosed with intestinal tuberculosis, between 2010 to 2023 from the Hospital Nacional Daniel Alcides Carrion and a Private Pathology Center, both located in Peru. Clinical data was obtained, histologic features were independently re-evaluated by three pathologists; and immunohistochemistry and real-time Polymerase Chain Reaction evaluation were performed. The 33 patients with intestinal tuberculosis who fulfilled the inclusion criteria were recruited. RESULTS: Immunohistochemistry was positive in 90.9% of cases, while real-time Polymerase Chain Reaction was positive in 38.7%. The ileocecal region was the most affected area (33.3%), and the most frequent endoscopic appearance was an ulcer (63.6%). Most of the granulomas were composed solely of epithelioid histiocytes (75.8%). Crypt architectural disarray was the second most frequent histologic finding (78.8%) after granulomas, but most of them were mild. CONCLUSION: Since immunohistochemistry does not require an intact cell wall, it demonstrates higher sensitivity compared to Ziehl-Neelsen staining. Therefore, it could be helpful for the diagnosis of paucibacillary tuberculosis.

Differential diagnosis of Crohn's disease and intestinal tuberculosis based on ATR-FTIR spectroscopy combined with machine learning.

BACKGROUND: Crohn's disease (CD) is often misdiagnosed as intestinal tuberculosis (ITB). However, the treatment and prognosis of these two diseases are dramatically different. Therefore, it is important to develop a method to identify CD and ITB with high accuracy, specificity, and speed. AIM: To develop a method to identify CD and ITB with high accuracy, specificity, and speed. METHODS: A total of 72 paraffin wax-embedded tissue sections were pathologically and clinically diagnosed as CD or ITB. Paraffin wax-embedded tissue sections were attached to a metal coating and measured using attenuated total reflectance fourier transform infrared spectroscopy at mid-infrared wavelengths combined with XGBoost for differential diagnosis. RESULTS: The results showed that the paraffin wax-embedded specimens of CD and ITB were significantly different in their spectral signals at 1074 cm-1 and 1234 cm-1 bands, and the differential diagnosis model based on spectral characteristics combined with machine learning showed accuracy, specificity, and sensitivity of 91.84%, 92.59%, and 90.90%, respectively, for the differential diagnosis of CD and ITB. CONCLUSION: Information on the mid-infrared region can reveal the different histological components of CD and ITB at the molecular level, and spectral analysis combined with machine learning to establish a diagnostic model is expected to become a new method for the differential diagnosis of CD and ITB.

Asymptomatic intestinal tuberculosis of the terminal ileum diagnosed on colonoscopy: a case report and literature review.

Objective: Colonoscopy is useful in diagnosing intestinal tuberculosis. However, the terminal ileum is generally not examined during routine colonoscopy. Therefore, even with colonoscopy, the diagnosis can be missed in patients with lesions confined to the terminal ileum. Herein, we report the case of an asymptomatic patient with intestinal tuberculosis, in whom a colonoscope insertion into the terminal ileum led to the diagnosis. Patient: An asymptomatic 71-year-old man visited our hospital for a colonoscopy after a positive fecal occult blood test. Results: Colonoscopy revealed diffuse edematous and erosive mucosa in the terminal ileum. Mycobacterium tuberculosis was detected by polymerase chain reaction and culture of biopsy specimens from the erosions, leading to the diagnosis of intestinal tuberculosis. The patient was treated with antitubercular agents for 6 months, and a follow-up colonoscopy revealed healing of the lesions. Conclusion: Asymptomatic intestinal tuberculosis may occasionally be detected on colonoscopy following a positive fecal occult blood test and is sometimes confined to the terminal ileum. Therefore, clinicians should consider intestinal tuberculosis in the differential diagnosis of the causes of positive fecal occult blood test results and perform colonoscopies, including observation of the terminal ileum.

Co-occurrence of Tuberculous Meningitis and Intestinal Perforation in Abdominal Tuberculosis (TB): A Report of a Rare Case From Pakistan.

Tuberculosis (TB) remains a significant global health concern, with millions affected worldwide each year. Extrapulmonary TB, particularly involving the digestive tract and central nervous system, poses distinctive difficulties in both diagnosis and treatment. We report a case involving a 15-year-old girl with a history of intestinal TB on anti-tuberculous therapy who presented with symptoms suggestive of meningitis, along with abdominal pain and distension. Our initial suspicion was tuberculous meningitis, considering the underlining abdominal TB, which was later supported by cerebrospinal fluid analysis showing lymphocytic-predominant pleocytosis and positive acid-fast bacilli staining. Concurrently, the patient developed hemodynamic instability and severe abdominal pain, which on repeat X-rays of the abdomen showed air under the diaphragms, prompting surgical exploration and revealing multiple ileal perforations. Histopathological examination confirmed TB as the cause of perforation. This case highlights the diagnostic and therapeutic complexities of concurrent tuberculous meningitis and intestinal TB perforation. Early recognition and interdisciplinary management are crucial for optimal patient outcomes.

Deep Learning Radiomics Analysis of CT Imaging for Differentiating Between Crohn's Disease and Intestinal Tuberculosis.

This study aimed to develop and evaluate a CT-based deep learning radiomics model for differentiating between Crohn's disease (CD) and intestinal tuberculosis (ITB). A total of 330 patients with pathologically confirmed as CD or ITB from the First Affiliated Hospital of Zhengzhou University were divided into the validation dataset one (CD: 167; ITB: 57) and validation dataset two (CD: 78; ITB: 28). Based on the validation dataset one, the synthetic minority oversampling technique (SMOTE) was adopted to create balanced dataset as training data for feature selection and model construction. The handcrafted and deep learning (DL) radiomics features were extracted from the arterial and venous phases images, respectively. The interobserver consistency analysis, Spearman's correlation, univariate analysis, and the least absolute shrinkage and selection operator (LASSO) regression were used to select features. Based on extracted multi-phase radiomics features, six logistic regression models were finally constructed. The diagnostic performances of different models were compared using ROC analysis and Delong test. The arterial-venous combined deep learning radiomics model for differentiating between CD and ITB showed a high prediction quality with AUCs of 0.885, 0.877, and 0.800 in SMOTE dataset, validation dataset one, and validation dataset two, respectively. Moreover, the deep learning radiomics model outperformed the handcrafted radiomics model in same phase images. In validation dataset one, the Delong test results indicated that there was a significant difference in the AUC of the arterial models (p = 0.037), while not in venous and arterial-venous combined models (p = 0.398 and p = 0.265) as comparing deep learning radiomics models and handcrafted radiomics models. In our study, the arterial-venous combined model based on deep learning radiomics analysis exhibited good performance in differentiating between CD and ITB.

Deep learning model to differentiate Crohn's disease from intestinal tuberculosis using histopathological whole slide images from intestinal specimens.

Crohn's disease (CD) and intestinal tuberculosis (ITB) share similar histopathological characteristics, and differential diagnosis can be a dilemma for pathologists. This study aimed to apply deep learning (DL) to analyze whole slide images (WSI) of surgical resection specimens to distinguish CD from ITB. Overall, 1973 WSI from 85 cases from 3 centers were obtained. The DL model was established in internal training and validated in external test cohort, evaluated by area under receiver operator characteristic curve (AUC). Diagnostic results of pathologists were compared with those of the DL model using DeLong's test. DL model had case level AUC of 0.886, 0.893 and slide level AUC of 0.954, 0.827 in training and test cohorts. Attention maps highlighted discriminative areas and top 10 features were extracted from CD and ITB. DL model's diagnostic efficiency (AUC = 0.886) was better than junior pathologists (*1 AUC = 0.701, P = 0.088; *2 AUC = 0.861, P = 0.788) and inferior to senior GI pathologists (*3 AUC = 0.910, P = 0.800; *4 AUC = 0.946, P = 0.507) in training cohort. In the test cohort, model (AUC = 0.893) outperformed senior non-GI pathologists (*5 AUC = 0.782, P = 0.327; *6 AUC = 0.821, P = 0.516). We developed a DL model for the classification of CD and ITB, improving pathological diagnosis accuracy effectively.

Revisiting the Era of Intestinal Tuberculosis: A Case Presenting As Small Bowel Obstruction With Classical Imaging and Histopathological Appearances.

The incidence of tuberculosis (TB) worldwide is still significantly high, with India contributing a high global TB burden. This case study features a 49-year-old male who had complaints of pain and abdominal distention for one and a half months. An erect abdominal radiograph showed features suggesting small bowel obstruction. Contrast-enhanced computed tomography (CT) of the abdomen was done. It showed multiple strictures involving the distal jejunum and ileum, causing small bowel obstruction. There was mesenteric and retroperitoneal lymphadenopathy with central necrosis and ascites. The patient was operated on for a small bowel obstruction. The resected intestine showed four strictures, tiny nodules on the serosal surface, and many enlarged lymph nodes. Representative tissue from these areas showed the typical picture of multiple caseating granulomas and fibrosis. Ziehl-Neelsen (ZN) staining highlighted the acid-fast bacilli (AFB). The suspicion index for intestinal tuberculosis (ITB) should be kept high while evaluating patients with intestinal obstruction presenting in endemic areas and high-risk populations, such as HIV-infected, undernourished, immunocompromised, and those with diabetes, smoking, and alcohol addiction.

Intestinal tuberculosis with small bowel stricture and hemorrhage as the predominant manifestation: Three case reports.

BACKGROUND: Intestinal tuberculosis is a chronic disease caused by Mycobacterium tuberculosis that mainly affects the ileum and cecum. Small bowel tuberculosis, characterized by predominant involvement of the small intestine, is an extremely rare condition with highly atypical clinical presentations, making diagnosis even more challenging. CASE SUMMARY: We report three cases of small intestinal tuberculosis, two of the patients presented primarily with abdominal pain, and one presented with gastrointestinal bleeding. All patients underwent blood tests and imaging examinations. Small bowel endoscopy (SBE) revealed that the main lesions in these patients were intestinal stenosis or gastrointestinal bleeding caused by small intestinal ulcers. One patient ultimately underwent surgical treatment. Following a complex diagnostic process and comprehensive analysis, all patients were confirmed to have small intestinal tuberculosis and received standard antituberculosis treatment, leading to an improvement in their condition. CONCLUSION: Patients with SBTs present with nonspecific symptoms such as abdominal pain, weight loss, and occasional gastrointestinal bleeding. Accurate diagnosis requires a thorough evaluation of clinical symptoms and various tests to avoid misdiagnosis and complications.

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.

Significance of Epidemiological Background in Preventing the Misdiagnosis of Intestinal Tuberculosis as Crohn's Disease.

The misdiagnosis of intestinal tuberculosis (ITB), such as Crohn's disease (CD), and subsequent treatment with immunosuppressive therapies can lead to severe outcomes. However, the differential diagnosis between these two conditions can be challenging. We herein report a patient from Myanmar who was initially diagnosed with CD due to the presence of non-caseating granulomas. The patient's symptoms were aggravated with steroid treatment, eventually leading to a diagnosis of ITB. In the international medical community, we encounter patients from countries, such as Myanmar, where tuberculosis is endemic. Therefore, it is necessary to understand the epidemiological background of each country to accurately distinguish between CD and ITB.

A meta-analysis of the accuracy of Xpert MTB/RIF in diagnosing intestinal tuberculosis.

OBJECTIVE: A detection method with high efficiency and accuracy is urgently needed in clinical work. The purpose of our study was to determine the diagnostic accuracy of the Xpert MTB/RIF assay for intestinal tuberculosis (ITB). METHODS: We searched PubMed and 4 other databases from their establishment to July 19, 2022, for published essays of diagnostic performance in which Xpert MTB/RIF was used to test patients with clinically suspected ITB. An assessment of the quality of the selected literature was conducted using QUADAS-2. We built forest plots by MetaDiSc software. RESULTS: The pooled Xpert MTB/RIF sensitivity was 48%, and the specificity was 99%. Moreover, the positive likelihood ratio for ITB diagnosis was 21.61. The negative likelihood ratio was 0.54. There were substantial variations between the study estimates of sensitivity (I2 = 87.6%) and specificity (I2 = 82.4%). CONCLUSION: Intestinal TB is detected with limited diagnostic sensitivity by Xpert MTB/RIF but with high specificity. An Xpert-positive result may facilitate the rapid identification of ITB cases. Nevertheless, a negative result has less certainty in excluding the disease.

Artificial intelligence for discrimination of Crohn's disease and gastrointestinal tuberculosis: A systematic review.

BACKGROUND AND AIM: Discrimination of gastrointestinal tuberculosis (GITB) and Crohn's disease (CD) is difficult. Use of artificial intelligence (AI)-based technologies may help in discriminating these two entities. METHODS: We conducted a systematic review on the use of AI for discrimination of GITB and CD. Electronic databases (PubMed and Embase) were searched on June 6, 2022, to identify relevant studies. We included any study reporting the use of clinical, endoscopic, and radiological information (textual or images) to discriminate GITB and CD using any AI technique. Quality of studies was assessed with MI-CLAIM checklist. RESULTS: Out of 27 identified results, a total of 9 studies were included. All studies used retrospective databases. There were five studies of only endoscopy-based AI, one of radiology-based AI, and three of multiparameter-based AI. The AI models performed fairly well with high accuracy ranging from 69.6-100%. Text-based convolutional neural network was used in three studies and Classification and regression tree analysis used in two studies. Interestingly, irrespective of the AI method used, the performance of discriminating GITB and CD did not match in discriminating from other diseases (in studies where a third disease was also considered). CONCLUSION: The use of AI in differentiating GITB and CD seem to have acceptable accuracy but there were no direct comparisons with traditional multiparameter models. The use of multiple parameter-based AI models have the potential for further exploration in search of an ideal tool and improve on the accuracy of traditional models.

Misdiagnosed periappendiceal and intestinal tuberculosis during the COVID-19 pandemic.

Introduction and importance: The coronavirus disease 2019 (COVID-19) was first reported in Wuhan, Hubei Province, China. It mainly involves the respiratory system, causing fever, cough, chest tightness, and other symptoms. However, when combined with other common or rare diseases, such as appendicitis and intestinal tuberculosis (TB), it can cause other systemic lesions, thus making the original disease lose its specific clinical manifestations. This case highlights the importance of early identification and clinical precision medicine diagnosis and treatment. Case presentation: A young woman presented with intermittent pain and discomfort in the right lower quadrant. Ultrasonography suggested appendicitis with a peripheral abscess. The nucleic acid test of COVID-19 was positive, and the chest computed tomography scan showed pulmonary involvement. She was sent for surgery. Postoperative body temperature increased regularly, and the TB T-cell test was positive. Clinical discussion: Multiple infections caused by common bacteria, pandemic virus, and specific mycobacterium TB cause a series of nonspecific clinical manifestations, which brings challenges to clinical diagnosis and treatment. Therefore, when facing a complex infection case, the authors should consider the possibility of multiple infections and give targeted treatment for the pathogens. Conclusions: During the epidemic of COVID-19, the incidence of intestinal TB is relatively low, which is easy to be overlooked and misdiagnosed, especially in the case of appendicitis. Therefore, clinicians must be highly vigilant in the diagnosis process to avoid missed diagnosis or misdiagnosis, so as to provide the best diagnosis and treatment plan.

Hereditary Ichthyosis With Gastrointestinal Manifestations: A Case Report.

Gut inflammation and defect in the gut mucosal barrier appear to have a correlation with skin diseases and vice versa. The coexistence of hereditary ichthyosis with active colitis has never been reported. We present a 17-year-old female with ichthyosis since birth, abdomen pain for 3 months, with acute colitis. After the initial diagnosis, the patient was started on antituberculous therapy (ATT), steroids, and mesalamine. She followed up with us for 1 year where there was resolution of symptoms. Steroids were stopped after 16 weeks, mesalamine was stopped after 20 weeks in view of low absolute neutrophil counts and ATT was stopped after 1 year. She was asymptomatic post 18 months of stopping ATT.

Case report: a case report and literature analysis on intestinal tuberculosis intestinal perforation complicated by umbilical intestinal fistula and bladder ileal fistula.

BACKGROUND: Intestinal tuberculosis is a chronic and specific infection caused by Mycobacterium tuberculosis invading the intestine. Due to the nonspecific clinical presentation, it is stressed that intestinal perforation complicates umbilical intestinal fistula and bladder ileal fistula is very rare and extremely difficult to be diagnosed. It is significant to identify the disease and take urgent intervene in the early stage. CASE PRESENTATION: An 18-month-old boy patient presented with abdominal pain. Abdominal CT suggested abscess formation in the right lower abdomen and pelvis. The patient underwent resection of necrotic and stenotic intestinal segments with the creation of an ileostomy, cystostomy and vesicoureteral fistula repair for the presence of intestinal perforation complicated by vesicoureteral fistula and umbilical enterocutaneous fistula. Histopathology confirmed the intestinal tuberculosis. The patient was discharged successfully after 11 days post anti-tuberculosis treatment. CONCLUSION: Our case report here is a rare case of umbilical intestinal fistula with bladder ileal fistula secondary to intestinal perforation from intestinal tuberculosis. The purpose of this report is to make the surgical community aware of atypical presentations of intestinal tuberculosis. If our peers encounter the similar situation, they can be prepared for corresponding diagnosis and treatment.

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.