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

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. This study presents a machine-learning multi-class model using faecal metagenomic data of 2,320 individuals with nine well-characterised phenotypes. The trained model achieves high AUROC (0.90 to 0.99) in predicting different diseases in an independent test set, with good sensitivity and specificity. Metagenomic analysis from public datasets shows comparable predictions. Correlation of top microbial species with disease phenotypes identifies significant associations. This microbiome-based multi-disease model has potential clinical application in disease diagnostics and treatment response monitoring.

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