EUVIMEDOpdag EUVIMED
Validierungsstudie

Development and Prospective Validation of a Machine Learning‐Based Mobile Application (CROHN'S AID ) for Differentiating Crohn's Disease From Intestinal Tuberculosis in Tuberculosis‐Endemic Regions

Srikant Mohta iD, Rintu Kutum, Akshat Dhoundiyal iD, Ritvik Pendyala, Harshal Dev, Bhaskar Kante iD, Sudheer Kumar Vuyyuru iD, Peeyush Kumar, Himanshu Narang iD, Mridul Mahajan iD, Shubi Virmani, Mukesh Kumar and 10 more

Alimentary Pharmacology & Therapeutics · 2026

DOI: 10.1111/apt.70984 ↗

At a glance

Validierungsstudie in Alimentary Pharmacology & Therapeutics, 2026. Written by Srikant Mohta and 21 co-authors. Institution: All India Institute of Medical Sciences, New Delhi, India. Major MEDLINE topics: Tuberculosis, Gastrointestinal, Crohn Disease, Machine Learning, Mobile Applications. Cited 1 times so far (Crossref); 20 references. Funded by: Indian Council of Medical Research.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Differentiating Intestinal tuberculosis (ITB) from Crohn's disease is a major diagnostic challenge in endemic regions, often leading to inappropriate treatment. We aimed to develop and prospectively validate a machine learning‐based mobile application, “Crohn's Aid”, to provide an accurate, real‐time clinical decision support tool at the point of care.

Methods

Retrospective analysis of a prospectively maintained database of 1066 patients (CD = 650; ITB = 416) from a tertiary centre in India. Thirty clinical, endoscopic and radiological variables were used to train multiple machine learning models, including CatBoost, Random forest and logistic regression. The lead model (CatBoost) was integrated into a mobile application. Performance was evaluated using area under the receiver operating characteristic (AUROC) and prospectively validated on a cohort of patients. Explainable AI (SHAP) values were used to identify key diagnostic drivers. The model was then validated on a prospective validation cohort of 121 patients at the same centre.

Results

Internal cross‐validation was repeated ten times, and the CatBoost model achieved a mean AUROC of 0.886 with a mean sensitivity of 76.0% and specificity of 84.1%. In the prospective validation cohort ( n = 121), the model maintained high diagnostic accuracy—AUROC 0.921(0.870–0.963) and outperformed the standard Bayesian reference standard (AUROC 0.750). At the optimum threshold, the model demonstrated a balanced sensitivity and specificity of 86.4% and 85.5%, respectively. Key predictors included symptom duration, transverse ulcers, granuloma, rectosigmoid involvement, and perianal disease.

Conclusion

Crohn's Aid represents a step forward in the application of digital health to solve a long‐standing clinical dilemma by combining the power of gradient‐boosted decision trees with the ubiquity of smartphone technology to reduce misdiagnosis between ITB and CD in resource‐limited settings.

Subjects

MeSH terms (MEDLINE)

Tuberculosis, GastrointestinalCrohn DiseaseMachine LearningMobile ApplicationsHumansFemaleDiagnosis, DifferentialMaleAdultProspective StudiesRetrospective StudiesIndiaROC CurveBoosting Machine Learning AlgorithmsSensitivity and SpecificityMiddle AgedYoung AdultRandom Forest

Author keywords

artificial intelligencecrohn's diseasedifferential diagnosisdigital healthintestinal tuberculosismachine learning

Authors and institutions

  • All India Institute of Medical Sciences, New Delhi, India.
  • Ashoka University, Sonipat, Haryana, India.
  • Netaji Subhas University of Technology, New Delhi, India.
  • Indraprastha Institute of Information Technology, Delhi, India.
  • Independent Researcher, British Columbia, Canada.

ORCID profiles: Srikant Mohta, Akshat Dhoundiyal, Bhaskar Kante, Sudheer Kumar Vuyyuru, Himanshu Narang, Mridul Mahajan, Prasenjit Das, Govind Makharia, Saurabh Kedia, Ravi Holani, Vineet Ahuja

Funding

  • Indian Council of Medical Research

Cite

APA

Mohta, S., Kutum, R., Dhoundiyal, A., Pendyala, R., Dev, H., Kante, B., Vuyyuru, S. K., Kumar, P., Narang, H., Mahajan, M., Virmani, S., Kumar, M., Bahl, S., Jayswal, N., Das, P., Sharma, R., Makharia, G., Chaudhury, S., Kedia, S., …, & Ahuja, V. (2026). Development and Prospective Validation of a Machine Learning‐Based Mobile Application (CROHN'S AID ) for Differentiating Crohn's Disease From Intestinal Tuberculosis in Tuberculosis‐Endemic Regions. Alimentary Pharmacology & Therapeutics. https://doi.org/10.1111/apt.70984

Vancouver

Mohta S, Kutum R, Dhoundiyal A, Pendyala R, Dev H, Kante B, et al. Development and Prospective Validation of a Machine Learning‐Based Mobile Application (CROHN'S AID ) for Differentiating Crohn's Disease From Intestinal Tuberculosis in Tuberculosis‐Endemic Regions. Alimentary Pharmacology & Therapeutics. 2026. doi:10.1111/apt.70984

BibTeX
@article{Mohta2026,
  author = {Mohta, Srikant and Kutum, Rintu and Dhoundiyal, Akshat and Pendyala, Ritvik and Dev, Harshal and Kante, Bhaskar and Vuyyuru, Sudheer Kumar and Kumar, Peeyush and Narang, Himanshu and Mahajan, Mridul and Virmani, Shubi and Kumar, Mukesh and Bahl, Stuti and Jayswal, Nikhil and Das, Prasenjit and Sharma, Raju and Makharia, Govind and Chaudhury, Santanu and Kedia, Saurabh and Sethi, Tavpritesh and Holani, Ravi and Ahuja, Vineet},
  title = {Development and Prospective Validation of a Machine Learning‐Based Mobile Application (CROHN'S AID ) for Differentiating Crohn's Disease From Intestinal Tuberculosis in Tuberculosis‐Endemic Regions},
  journal = {Alimentary Pharmacology & Therapeutics},
  year = {2026},
  doi = {10.1111/apt.70984}
}
Start for free →