Published online Aug 27, 2024. doi: 10.4240/wjgs.v16.i8.2745
Revised: July 6, 2024
Accepted: July 15, 2024
Published online: August 27, 2024
Processing time: 142 Days and 1 Hours
Crohn's disease (CD) is a chronic inflammatory bowel disease of unknown origin that can cause significant disability and morbidity with its progression. Due to the unique nature of CD, surgery is often necessary for many patients during their lifetime, and the incidence of postoperative complications is high, which can affect the prognosis of patients. Therefore, it is essential to identify and manage post
Core Tip: Crohn's disease (CD) is a condition characterized by chronic, recurrent inflammation, which can involve any part of the digestive tract. As the disease progresses, many patients require bowel resection and ostomy, with subsequent postoperative complications. Machine learning (ML) has emerged as a valuable tool for predicting these complications. A recent study published by Wang et al presented an ML approach for predicting major postoperative complications in CD patients undergoing intestinal resection. While acknowledging the merit of the study, we would like to express our opinions and engage in a discussion with the authors.
- Citation: Zhang LF, Chen LX, Yang WJ, Hu B. Machine learning in predicting postoperative complications in Crohn’s disease. World J Gastrointest Surg 2024; 16(8): 2745-2747
- URL: https://www.wjgnet.com/1948-9366/full/v16/i8/2745.htm
- DOI: https://dx.doi.org/10.4240/wjgs.v16.i8.2745
The prevalence of Crohn's disease (CD) is increasing, posing a growing health and economic challenge[1]. While the management of CD is primarily aimed at symptom relief and avoidance of surgery, a proportion of patients will inevitably undergo bowel resection. Consequently, the anticipation and prevention of postoperative complications have received increasing attention. Machine learning (ML) has gained prominence in medicine due to its ability to robustly navigate complex non-linear relationships. In an article, Wang et al[2] used ML techniques to predict short-term major postoperative complications in bowel resection for CD. In this article, the authors used logistic regression and random forest for predictive modeling, and random forest has a better performance than logistic regression. In particular, pre
First, the significant sample imbalance, with only 5% (13/259) of patients experiencing major surgical complications, could potentially compromise the training effectiveness and generalizability of the model[3,4]. The model may prefer to predict no complications when the area under the the receiver operating characteristic (ROC) curve (AUC) is the only evaluation metric. To address this issue, the use of oversampling, undersampling, or alternative metrics beyond AUC may be warranted[5-7].
Second, the inclusion of preoperative CDAI as a categorical variable (≥ 220 or < 220) rather than a continuous nume
Last, in the evolving landscape of ML, while prioritizing interpretability is not always mandatory[9], there is a growing emphasis on explainability[10]. In this article, the summary plots generated by SHapley Additive exPlanations (SHAP)[11] attempt to elucidate the dynamics of the random forest model. However, a more comprehensive explanation, in
In conclusion, the use of ML to predict major postoperative complications after intestinal resection for CD is innovative and requires significant effort. However, we hold different opinions on some methodological issues and would like to discuss them with the authors to enhance the robustness and credibility of future research in this area.
1. | Torres J, Mehandru S, Colombel JF, Peyrin-Biroulet L. Crohn's disease. Lancet. 2017;389:1741-1755. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 1121] [Cited by in F6Publishing: 1545] [Article Influence: 220.7] [Reference Citation Analysis (4)] |
2. | Wang FT, Lin Y, Yuan XQ, Gao RY, Wu XC, Xu WW, Wu TQ, Xia K, Jiao YR, Yin L, Chen CQ. Predicting short-term major postoperative complications in intestinal resection for Crohn's disease: A machine learning-based study. World J Gastrointest Surg. 2024;16: 717-730. [PubMed] [DOI] [Cited in This Article: ] [Reference Citation Analysis (0)] |
3. | Lu Y, Cheung YM, Tang YY. Bayes Imbalance Impact Index: A Measure of Class Imbalanced Data Set for Classification Problem. IEEE Trans Neural Netw Learn Syst. 2020;31:3525-3539. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 24] [Cited by in F6Publishing: 13] [Article Influence: 3.3] [Reference Citation Analysis (0)] |
4. | Macdonald ME, Chilibeck G, Affleck W, Cadell S. Gender imbalance in pediatric palliative care research samples. Palliat Med. 2010;24:435-444. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 37] [Cited by in F6Publishing: 36] [Article Influence: 2.6] [Reference Citation Analysis (0)] |
5. | Ji Z, Yu X, Yu Y, Pang Y, Zhang Z. Semantic-Guided Class-Imbalance Learning Model for Zero-Shot Image Classification. IEEE Trans Cybern. 2022;52:6543-6554. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 3] [Reference Citation Analysis (0)] |
6. | Gnip P, Vokorokos L, Drotár P. Selective oversampling approach for strongly imbalanced data. PeerJ Comput Sci. 2021;7:e604. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 20] [Cited by in F6Publishing: 4] [Article Influence: 1.3] [Reference Citation Analysis (0)] |
7. | Vaughan R. Oversampling in Health Surveys: Why, When, and How? Am J Public Health. 2017;107:1214-1215. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 15] [Cited by in F6Publishing: 18] [Article Influence: 2.6] [Reference Citation Analysis (0)] |
8. | Best WR, Becktel JM, Singleton JW, Kern F Jr. Development of a Crohn's disease activity index. National Cooperative Crohn's Disease Study. Gastroenterology. 1976;70:439-444. [PubMed] [Cited in This Article: ] |
9. | McCoy LG, Brenna CTA, Chen SS, Vold K, Das S. Believing in black boxes: machine learning for healthcare does not need explainability to be evidence-based. J Clin Epidemiol. 2022;142:252-257. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 8] [Cited by in F6Publishing: 33] [Article Influence: 11.0] [Reference Citation Analysis (0)] |
10. | Goodwin NL, Nilsson SRO, Choong JJ, Golden SA. Toward the explainability, transparency, and universality of machine learning for behavioral classification in neuroscience. Curr Opin Neurobiol. 2022;73:102544. [PubMed] [DOI] [Cited in This Article: ] [Cited by in Crossref: 41] [Cited by in F6Publishing: 28] [Article Influence: 14.0] [Reference Citation Analysis (0)] |
11. | Fan Y, Mao H, Li Q. A Model-Agnostic Feature Attribution Approach to Magnetoencephalography Predictions Based on Shapley Value. IEEE J Biomed Health Inform. 2023;27:2524-2535. [PubMed] [DOI] [Cited in This Article: ] [Reference Citation Analysis (0)] |