微生物群
肠道菌群
失调
人体微生物群
生物
疾病
炎症性肠病
免疫学
免疫系统
溃疡性结肠炎
人类微生物组计划
机器学习
生物信息学
医学
计算机科学
内科学
作者
Miad Boodaghidizaji,Thaisa M. Cantu-Jungles,Tingting Chen,Bin Zhang,Tianming Yao,ALAN L. LANDAY,Ali Keshavarzian,Bruce R. Hamaker,Arezoo M. Ardekani
出处
期刊:BMC Microbiology
[BioMed Central]
日期:2025-06-05
卷期号:25 (1): 353-353
被引量:16
标识
DOI:10.1186/s12866-025-04072-7
摘要
Gut microbiota has been implicated in the pathogenesis of multiple gastrointestinal (GI) and systemic metabolic and inflammatory disorders where disrupted gut microbiota composition and function (dysbiosis) has been found in multiple studies. Thus, human microbiome data holds significant potential as a source of information for diagnosing and characterizing diseases-such as phenotypes, disease course, and therapeutic response-associated with dysbiotic microbiota communities. However, multiple attempts to leverage gut microbiota taxonomic data for diagnostic and disease characterization have failed due to significant inter-individual variability of microbiota community and overlap of disrupted microbiota communities among multiple diseases. One potential approach is to look at the microbiota community pattern and response to microbiota modifiers like dietary fiber in different disease states. This approach has become feasible with the advent of machine learning, which can uncover hidden patterns in human microbiome data and enable disease prediction. Accordingly, the aim of our study was to test the hypothesis that machine learning algorithms can distinguish stool microbiota patterns-and their responses to fiber-across diseases with previously reported overlapping dysbiotic microbiota profiles. Here, we applied machine learning algorithms to distinguish between Parkinson's disease, Crohn's disease (CD), ulcerative colitis (UC), human immune deficiency virus (HIV), and healthy control (HC) subjects in the presence and absence of fiber treatments. We demonstrated that machine learning algorithms can classify diseases with accuracy as high as 95%. Furthermore, applying machine learning to microbiome data to distinguish UC from CD yielded a prediction accuracy of up to 90%.
科研通智能强力驱动
Strongly Powered by AbleSci AI