Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

Keynote webinar | Spotlight on medication adherence

LIVE: Thursday 27th June 2024, 18:00-19:30 (CEST)
Join our expert panel to discover why you need to understand the drivers of non-adherence in your patients, and how you can optimize medication adherence in your clinics to drastically improve patient outcomes.
ADVANCED SEARCH
Log in
Top
BMC Medical Informatics and Decision Making
Published in: BMC Medical Informatics and Decision Making 1/2023

Open Access 01-12-2023 | Crohn's Disease | Research article

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

Authors: Keming Lu, Yuanren Tong, Si Yu, Yucong Lin, Yingyun Yang, Hui Xu, Yue Li, Sheng Yu

Published in: BMC Medical Informatics and Decision Making | Issue 1/2023

Login to get access

Abstract

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.
Appendix
Available only for authorised users
Footnotes
Literature
1.
He Y, Zhu Z, Chen Y, Chen F, Wang Y, Ouyang C, ... Chen M. Development and validation of a novel diagnostic Nomogram to differentiate between intestinal tuberculosis and Crohn's disease: a 6-year prospective multicenter study. J Am College Gastroenterol. 2019;114(3):490–499.
2.
Sundararajan M, Taly A, Yan Q. Axiomatic attribution for deep networks. In: International Conference on Machine Learning. 2017. p. 3319–28 PMLR.
3.
Liu F, Avci B. Incorporating priors with feature attribution on text classification. 2019. arXiv preprint arXiv:1906.08286.CrossRef
4.
Chen H, Zheng G, Ji Y. Generating hierarchical explanations on text classification via feature interaction detection. 2020. arXiv preprint arXiv:2004.02015.CrossRef
5.
Singh C, Murdoch WJ, Yu B. Hierarchical interpretations for neural network predictions. 2018. arXiv preprint arXiv:1806.05337.
6.
Graziani M, Andrearczyk V, Marchand-Maillet S, Müller H. Concept attribution: Explaining cnn decisions tophysicians. Comput Biol Med. 2020;123:103865.CrossRef
7.
Hu S, Gao Y, Niu Z, Jiang Y, Li L, Xiao X, Wang M, Fang EF, Menpes-Smith W, Xia J, et al. Weakly supervised deep learning for covid-19 infection detection and classification from ct images. IEEE Access. 2020;8:118869–83.CrossRef
8.
Preuer K, Klambauer G, Rippmann F, et al. Interpretable deep learning in drug discovery[J]. Explainable AI: interpreting, explaining and visualizing deep learning. 2019. p. 331-45.
9.
Lauritsen SM, Kristensen M, Olsen MV, Larsen MS, Lauritsen KM, Jørgensen MJ, Lange J, Thiesson B. Explainable artificial intelligence model to predict acute critical illness from electronic health records. Nat Commun. 2020;11(1):1–11.CrossRef
10.
Sayres R, Taly A, Rahimy E, Blumer K, Coz D, Hammel N, Krause J, Narayanaswamy A, Rastegar Z, Derek Wu, et al. Using a deep learning algorithm and integrated gradients explanation to assist grading for diabetic retinopathy. Ophthalmology. 2019;126(4):552–64.CrossRefPubMed
11.
Cui Y, Che W, Liu T, Qin B, Yang Z, Wang S, Hu G. Pre-training with whole word masking for chinese bert. 2019. arXiv preprint arXiv:1906.08101.
12.
Devlin J, Chang MW, Lee K, Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. 2018. arXiv preprint arXiv:1810.04805.
13.
Zhenyu J, Sun S, Sun K. Chinese lexical analysis with deep bi-gru-crf network. 2018. arXiv preprint arXiv:1807.01882.
14.
Lin TY, Goyal P, Girshick R, He K, Dollár P. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. 2017. p. 2980–8.
15.
Kim Y. Convolutional neural networks for sentence classification. corr abs/1408.5882. 2014. arXiv preprint arXiv:1408.5882.
16.
Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. 2015. arXiv preprint arXiv:1503.02531.
17.
Lee YJ, Yang SK, Byeon JS, Myung SJ, Chang HS, Hong SS, ... Yu CS. Analysis of colonoscopic findings in the differential diagnosis between intestinal tuberculosis and Crohn’s disease. Endoscopy. 2006;38(06):592–597.
18.
Tong Y, Lu K, Yang Y, Li J, Lin Y, Wu D, ... Qian J. Can natural language processing help differentiate inflammatory intestinal diseases in China? Models applying random forest and convolutional neural network approaches. BMC Med Inform Decision Making. 2020;20(1):1–9.
Metadata
Title
Building a trustworthy AI differential diagnosis application for Crohn’s disease and intestinal tuberculosis
Authors
Keming Lu
Yuanren Tong
Si Yu
Yucong Lin
Yingyun Yang
Hui Xu
Yue Li
Sheng Yu
Publication date
01-12-2023
Publisher
BioMed Central
Published in
BMC Medical Informatics and Decision Making / Issue 1/2023
Electronic ISSN: 1472-6947
DOI
https://doi.org/10.1186/s12911-023-02257-6

Other articles of this Issue 1/2023

BMC Medical Informatics and Decision Making 1/2023 Go to the issue

Correction

Correction: The impact of data from remote measurement technology on the clinical practice of healthcare professionals in depression, epilepsy and multiple sclerosis: survey

Research

MNCLCDA: predicting circRNA-drug sensitivity associations by using mixed neighbourhood information and contrastive learning

Research

Design, development and evaluation of a mobile-based self-care application for patients with COVID-19 not requiring hospitalization; a study of Northwest of Iran

Research

Identifying factors that affect the use of health information technology in the treatment and management of hypertension

Research

Integrated personal health record (PHR) security: requirements and mechanisms

Research

Developing and testing the usability, acceptability, and future implementation of the Whole Day Matters Tool and User Guide for primary care providers using think-aloud, near-live, and interview procedures