文献速递炎症性肠病消化内镜

多模态机器学习模型的开发与验证:用于肛周瘘管患者克罗恩病的诊断与风险评估

Development and Validation of a Multimodal Machine Learning Model for Diagnosing and Assessing Risk of Crohn's Disease in Patients With Perianal Fistula.
PubMed 文献 · Aliment Pharmacol Ther · 2024-12-18

本研究为回顾性多中心验证研究,纳入2016年9月至2020年12月中国三家中心接受肛周瘘管手术并术前行直肠MRI的患者,构建随机森林模型早期诊断克罗恩病。推导队列(n=550)模型AUROC为0.9425(95% CI: 0.8943-0.9906),两个外部验证队列(n=300)AUROC分别为0.9187(95% CI: 0.8620-0.9754)和0.9341(95% CI: 0.8876-0.9806),并开发了公开可访问的网页工具。

要点

  • 肛周瘘管首诊患者中,基于MRI特征的多模态机器学习模型可辅助早期识别克罗恩病。
  • 推导队列随机森林模型AUROC为0.9425(95% CI: 0.8943-0.9906)。
  • 外部验证队列AUROC分别为0.9187(95% CI: 0.8620-0.9754)和0.9341(95% CI: 0.8876-0.9806),并已开发公开网页工具。

核心结论

  • 开发了多模态机器学习模型及网页工具,可预测并呈现以肛周瘘管首诊患者的克罗恩病风险。

研究设计与样本

  • 回顾性、多中心验证研究,纳入2016年9月至2020年12月中国三家中心接受首次肛周瘘管手术并术前行直肠MRI的肛周瘘管型克罗恩病或隐腺源性瘘管患者。
  • 推导队列n=550,按7:3随机分为训练集与测试集;外部验证使用两家中心的数据(n=300)。
  • 采用随机森林分类模型,并使用Shapley加性解释(SHAP)框架进行模型解释。

主要发现

  • 推导队列SHAP分析显示直肠壁溃疡、直肠壁增厚、黏膜下瘘管和T2高信号为风险因素,年龄为保护因素。
  • 推导队列中,使用上述前5个特征构建的随机森林分类模型AUROC为0.9425(95% CI: 0.8943-0.9906)。
  • 验证队列中模型表现良好,AUROC分别为0.9187(95% CI: 0.8620-0.9754)和0.9341(95% CI: 0.8876-0.9806)。

关键数值与推荐

  • 推导队列随机森林模型AUROC为0.9425(95% CI: 0.8943-0.9906)。
  • 验证队列AUROC分别为0.9187(95% CI: 0.8620-0.9754)和0.9341(95% CI: 0.8876-0.9806)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Diagnosis of Crohn's disease (CD) can pose challenges, particularly when perianal fistula is the initial presentation. AIM: To develop and validate a predictive model, establishing a visual web tool for early diagnosis of CD in patients presenting with perianal fistula. METHODS: This retrospective, multicentre validation study involved patients diagnosed with either perianal fistulising CD or cryptoglandular fistula who underwent initial perianal fistula surgery subsequent to rectal MRI at three Chinese centres from September 2016 to December 2020. A random forest classification model was trained on the derivation cohort (n = 550), randomly split into training and test sets at a 7:3 ratio. Validation utilised data from two external centres (n = 300). Model interpretation employed the Shapley Addictive explanation (SHAP) framework. The validated model was integrated into a web tool for calculating patient-specific risk. RESULTS: In the derivation cohort, SHAP analysis highlighted rectal wall ulceration, rectal wall thickening, submucosal fistula, and T2 hyperintensity as risk factors, while age was identified as protective. A random forest classification model developed using these top 5 features achieved an AUROC of 0.9425 (95% CI: 0.8943-0.9906). In the validation cohort, the model performed well with AUROC values of 0.9187 (95% CI: 0.8620-0.9754) and 0.9341 (95% CI: 0.8876-0.9806), respectively. We developed a publicly accessible web-based application. CONCLUSION: We have developed a multimodal machine learning model and a web tool that can predict and present CD risk in patients initially presenting with perianal fistula.

来源:Aliment Pharmacol Ther,查看原文。版权归原作者所有。

引用

  1. Xiang Y, Yang F, Yuan F, et al. Development and Validation of a Multimodal Machine Learning Model for Diagnosing and Assessing Risk of Crohn's Disease in Patients With Perianal Fistula. Aliment Pharmacol Ther. 2024. PMID: 39692571. doi:10.1111/apt.18455

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。