4.7 Article

Noninvasive detection and interpretation of gastrointestinal diseases by collaborative serum metabolite and magnetically controlled capsule endoscopy

期刊

出版社

ELSEVIER
DOI: 10.1016/j.csbj.2022.10.001

关键词

Gastrointestinal diseases; Noninvasive detection; Serum metabolite; Magnetically controlled capsule endoscopy; Machine learning; Convolutional neural networks

资金

  1. National Natural Science Foundation of China [11871456, 61803360]
  2. Shanghai Municipal Science and Technology Major Project [2017SHZDZX01]
  3. Shanghai Jiao Tong University Affiliated Sixth People's Hospital Basic Scientific Research [ynms202118]
  4. Clinical Research Plan of SHDC [SHDC2022CRS044]

向作者/读者索取更多资源

Gastrointestinal diseases are complex diseases that often present challenges in diagnosis and treatment. Traditional diagnostic methods are invasive and carry risks. This study proposes a collaborative noninvasive diagnostic scheme combining serological examination and magnetically controlled capsule endoscopy. The study successfully identified key metabolite signatures and image embedding signatures with high accuracy, providing a new approach for noninvasive detection and interpretation of gastrointestinal diseases.
Gastrointestinal diseases are complex diseases that occur in the gastrointestinal tract. Common gastroin-testinal diseases include chronic gastritis, peptic ulcers, inflammatory bowel disease, and gastrointestinal tumors. These diseases may manifest a long course, difficult treatment, and repeated attacks.Gastroscopy and mucosal biopsy are the gold standard methods for diagnosing gastric and duodenal diseases, but they are invasive procedures and carry risks due to the necessity of sedation and anesthesia. Recently, several new approaches have been developed, including serological examination and magnet-ically controlled capsule endoscopy (MGCE). However, serological markers lack lesion information, while MGCE images lack molecular information. This study proposes combining these two technologies in a collaborative noninvasive diagnostic scheme as an alternative to the standard procedures. We introduce an interpretable framework for the clinical diagnosis of gastrointestinal diseases. Based on collected blood samples and MGCE records of patients with gastrointestinal diseases and comparisons with normal individuals, we selected serum metabolite signatures by bioinformatic analysis, captured image embedding signatures by convolutional neural networks, and inferred the location-specific associations between these signatures.Our study successfully identified five key metabolite signatures with functional relevance to gastroin-testinal disease. The combined signatures achieved discrimination AUC of 0.88. Meanwhile, the image embedding signatures showed different levels of validation and testing accuracy ranging from 0.7 to 0.9 according to different locations in the gastrointestinal tract as explained by their specific associations with metabolite signatures. Overall, our work provides a new collaborative noninvasive identification pipeline and candidate metabolite biomarkers for image auxiliary diagnosis. This method should be valu-able for the noninvasive detection and interpretation of gastrointestinal and other complex diseases.(c) 2022 Published by Elsevier B.V. on behalf of Research Network of Computational and Structural Bio-technology. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据