Yufeng Shu,1,* Zhe Chen,2,* Jingshu Chi,1 Sha Cheng,1 Huan Li,1 Peng Liu,3 Ju Luo2 

1Department of Gastroenterology, Third Xiangya Hospital, Central South University., Changsha, Hunan, People’s Republic of China; 2Department of Gerontology, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China., Changsha, Hunan, People’s Republic of China; 3Department of Gastroenterology, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China., Changsha, Hunan, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Peng Liu, Department of Gastroenterology, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, No. 161, South Shaoshan Road, Changsha, Hunan, People’s Republic of China, Email liupeng920416@163.com Ju Luo, Department of Gerontology, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, No. 161, South Shaoshan Road, Changsha, Hunan, People’s Republic of China, Email philip841018@sina.com

Background: Whether machine learning (ML) can assist in the diagnosis of Crohn’s disease (CD) and intestinal tuberculosis (ITB) remains to be explored.
Methods: We collected clinical data from 241 patients, and 51 parameters were included. Six ML methods were tested, including logistic regression, decision tree, k-nearest neighbor, multinomial NB, multilayer perceptron, and XGBoost. SHAP and LIME were subsequently introduced as interpretability methods. The ML model was tested in a real-world clinical practice and compared with a multidisciplinary team (MDT) meeting.
Results: XGBoost displays the best performance among the six ML models. The diagnostic AUROC and the accuracy of XGBoost were 0.946 and 0.884, respectively. The top three clinical features affecting our ML model’s result prediction were T-spot, pulmonary tuberculosis, and onset age. The ML model’s accuracy, sensitivity, and specificity in clinical practice were 0.860, 0.833, and 0.871, respectively. The agreement rate and kappa coefficient of the ML and MDT methods were 90.7% and 0.780, respectively (P< 0.001).
Conclusion: We developed an ML model based on XGBoost. The ML model could provide effective and efficient differential diagnoses of ITB and CD with diagnostic bases. The ML model performs well in real-world clinical practice, and the agreement between the ML model and MDT is strong.

Keywords: artificial intelligence, machine learning, crohn’s disease, intestinal tuberculosis, multidisciplinary team