Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comment
. 2023 Oct;72(10):2004-2006.
doi: 10.1136/gutjnl-2022-328216. Epub 2022 Oct 28.

Overcoming regional limitations: transfer learning for cross-regional microbial-based diagnosis of diseases

Nan Wang  1 , Mingyue Cheng  1 , Kang Ning  2
Affiliations
Comment

Overcoming regional limitations: transfer learning for cross-regional microbial-based diagnosis of diseases

Nan Wang et al. Gut. 2023 Oct.
No abstract available

Keywords: INTESTINAL BACTERIA; INTESTINAL MICROBIOLOGY.

PubMed Disclaimer

Conflict of interest statement

Competing interests: None declared.

Figures

Figure 1
Figure 1
Data distribution, assessment workflow and framework evaluation. (A) data distribution. The number of samples of different diseases. The seven diseases marked in red were assessed, including metabolic syndrome, gastritis, kidney stones, T2D, rheumatoid arthritis, constipation and COPD. (B) The workflow of assessment. The genera abundance profiles of samples from each city were randomly divided into the training subset (80%) and the testing subset (20%). Three assessment workflows for each model were marked by three different colours. The testing subset of city B was used to test all the three models. (C) Framework evaluation: comparison of the AUROC of three models. Boxplots in the left panel show the AUROC of the three models for diagnosing seven diseases using samples in each of city, and the right panel shows these values collectively. *, p<0.05; **, p<0.01; ***, p<0.005; Mann-Whitney-Wilcoxon test. (D) The relationship between sample size and the performance of three models. Boxplots show AUROC of three models for diagnosing three diseases (COPD, rheumatoid arthritis and T2D). The lines show the change in average AUROC of three models with sample size increasing. The dashed line shows the average AUROC of cross-regional diagnosis of T2D using random forest model. For all the boxplots, boxes represent the IQR between the first and third quartiles and the line inside represents the median. Whiskers denote the lowest and highest values within the 1.5×IQR from the first and third quartiles, respectively. AUROC, area under the receiver operating characteristic; COPD, chronic obstructive pulmonary disease; T2D, type 2 diabetes.
See this image and copyright information in PMC

Comment on

References

    1. Clooney AG, Eckenberger J, Laserna-Mendieta E, et al. . Ranking microbiome variance in inflammatory bowel disease: a large longitudinal intercontinental study. Gut 2021;70:499–510. 10.1136/gutjnl-2020-321106 - DOI - PMC - PubMed
    1. Weng F, Meng Y, Lu F, et al. . Differentiation of intestinal tuberculosis and crohn's disease through an explainable machine learning method. Sci Rep 2022;12:1714. 10.1038/s41598-022-05571-7 - DOI - PMC - PubMed
    1. Gou W, Ling C-W, He Y, et al. . Interpretable machine learning framework reveals robust gut microbiome features associated with type 2 diabetes. Diabetes Care 2021;44:358–66. 10.2337/dc20-1536 - DOI - PMC - PubMed
    1. Sun Q, Liu Y, Chua T. Meta-transfer learning for few-shot learning. 2019 IEEE Conf Comput Vis Pattern Recognit, 2019:403–12.
    1. He Y, Wu W, Zheng H-M, et al. . Regional variation limits applications of healthy gut microbiome reference ranges and disease models. Nat Med 2018;24:1532–5. 10.1038/s41591-018-0164-x - DOI - PubMed