Faecal microbiome-based machine learning for multi-class disease diagnosis

Qi Su, Qin Liu, Raphaela Iris Lau, Jingwan Zhang, Zhilu Xu, Yun Kit Yeoh, Thomas W.H. Leung, Whitney Tang, Lin Zhang, Jessie Q.Y. Liang, Yuk Kam Yau, Jiaying Zheng, Chengyu Liu, Mengjing Zhang, Chun Pan Cheung, Jessica Y.L. Ching, Hein M. Tun, Jun Yu, Francis K.L. Chan, Siew C. Ng*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

38 Citations (Scopus)

Abstract

Systemic characterisation of the human faecal microbiome provides the opportunity to develop non-invasive approaches in the diagnosis of a major human disease. However, shared microbial signatures across different diseases make accurate diagnosis challenging in single-disease models. Herein, we present a machine-learning multi-class model using faecal metagenomic dataset of 2,320 individuals with nine well-characterised phenotypes, including colorectal cancer, colorectal adenomas, Crohn’s disease, ulcerative colitis, irritable bowel syndrome, obesity, cardiovascular disease, post-acute COVID-19 syndrome and healthy individuals. Our processed data covers 325 microbial species derived from 14.3 terabytes of sequence. The trained model achieves an area under the receiver operating characteristic curve (AUROC) of 0.90 to 0.99 (Interquartile range, IQR, 0.91–0.94) in predicting different diseases in the independent test set, with a sensitivity of 0.81 to 0.95 (IQR, 0.87–0.93) at a specificity of 0.76 to 0.98 (IQR 0.83–0.95). Metagenomic analysis from public datasets of 1,597 samples across different populations observes comparable predictions with AUROC of 0.69 to 0.91 (IQR 0.79–0.87). Correlation of the top 50 microbial species with disease phenotypes identifies 363 significant associations (FDR < 0.05). This microbiome-based multi-disease model has potential clinical application in disease diagnostics and treatment response monitoring and warrants further exploration.

Original languageEnglish
Article number6818
Number of pages8
JournalNature Communications
Volume13
DOIs
Publication statusPublished - 10 Nov 2022

Scopus Subject Areas

  • Chemistry(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • General
  • Physics and Astronomy(all)

Fingerprint

Dive into the research topics of 'Faecal microbiome-based machine learning for multi-class disease diagnosis'. Together they form a unique fingerprint.

Cite this