Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comparative Study
. 2022 Feb 2;12(1):1714.
doi: 10.1038/s41598-022-05571-7.

Differentiation of intestinal tuberculosis and Crohn's disease through an explainable machine learning method

Futian Weng #  1   2   3 , Yu Meng #  4   5 , Fanggen Lu  6 , Yuying Wang  3   7 , Weiwei Wang  1   2   3 , Long Xu  4   5 , Dongsheng Cheng  8 , Jianping Zhu  9   10   11
Affiliations
Comparative Study

Differentiation of intestinal tuberculosis and Crohn's disease through an explainable machine learning method

Futian Weng et al. Sci Rep. .

Abstract

Differentiation between Crohn's disease and intestinal tuberculosis is difficult but crucial for medical decisions. This study aims to develop an effective framework to distinguish these two diseases through an explainable machine learning (ML) model. After feature selection, a total of nine variables are extracted, including intestinal surgery, abdominal, bloody stool, PPD, knot, ESAT-6, CFP-10, intestinal dilatation and comb sign. Besides, we compared the predictive performance of the ML methods with traditional statistical methods. This work also provides insights into the ML model's outcome through the SHAP method for the first time. A cohort consisting of 200 patients' data (CD = 160, ITB = 40) is used in training and validating models. Results illustrate that the XGBoost algorithm outperforms other classifiers in terms of area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision and Matthews correlation coefficient (MCC), yielding values of 0.891, 0.813, 0.969, 0.867 and 0.801 respectively. More importantly, the prediction outcomes of XGBoost can be effectively explained through the SHAP method. The proposed framework proves that the effectiveness of distinguishing CD from ITB through interpretable machine learning, which can obtain a global explanation but also an explanation for individual patients.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Overview of the proposed framework.
Figure 2
Figure 2
SHAP summary plot for the XGBoost algorithm.
Figure 3
Figure 3
Bar chart plot for the nine significant variables contributing to the XGBoost model’s prediction for distinguishing CD from ITB.
Figure 4
Figure 4
SHAP explanation plot for three patients from our testing dataset.
See this image and copyright information in PMC

References

    1. Pratap Mouli V, Munot K, Ananthakrishnan A, Kedia S, Addagalla S, Garg S, et al. Endoscopic and clinical responses to anti-tubercular therapy can differentiate intestinal tuberculosis from Crohn’s disease. Aliment. Pharmacol. Ther. 2017;45(1):27–36. doi: 10.1111/apt.13840. - DOI - PubMed
    1. Sood A, Midha V, Singh A. Differential diagnosis of Crohn’s disease versus ileal tuberculosis. Curr. Gastroenterol. Rep. 2014;16(11):418. doi: 10.1007/s11894-014-0418-9. - DOI - PubMed
    1. Gao X, Zhang Y. Serological markers facilitate the diagnosis of Crohn’s disease. Postgrad. Med. 2021;133(3):286–290. doi: 10.1080/00325481.2021.1873649. - DOI - PubMed
    1. Wei, J. P. et al. Misdiagnosis and mistherapy of Crohn’s disease as intestinal tuberculosis: Case report and literature review. Medicine95(1), e2436 (2016). - PMC - PubMed
    1. Makharia GK, Srivastava S, Das P, Goswami P, Singh U, Tripathi M, et al. Clinical, endoscopic, and histological differentiations between Crohn’s disease and intestinal tuberculosis. Am. J. Gastroenterol. 2010;105(3):642–651. doi: 10.1038/ajg.2009.585. - DOI - PubMed

Publication types