Scholarlink

<p>Hyperuricemia (HUA) and gout result from imbalances in uric acid metabolism and are closely associated with the gut microbiota. Advanced analytical methods facilitate the exploration of microbiota complexity. In this study, 16S rRNA sequencing data from stool samples of 233 patients were thoroughly collected. Machine learning (ML) and Shapley Additive exPlanations (SHAP) interpretability algorithms were applied to identify core taxa and predict the metabolic functions. The results revealed that the high-contribution core taxa identified by SHAP in each group, such as <i>Oscillospiraceae</i>_UCG-005 and <i>Rhodococcus</i> provided the basis for ML prediction. Among the five classification models, Random Forest (RF) achieved the best diagnostic performance, with prediction accuracy ranging from 82 to 96%. Metabolic function predictions indicated that the purine metabolism pathway contributes the most to distinguishing gout from other groups. In sum, ML-based 16S rRNA sequencing reveals key gut microbiome biomarkers, aiding new diagnostic strategies for HUA and gout. </p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Interpretive prediction of hyperuricemia and gout patients via machine learning analysis of human gut microbiome

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月10日

查看全文
  • Jia-Wei Tang,
  • Alfred Chin Yen Tay,
  • Liang Wang

摘要

Hyperuricemia (HUA) and gout result from imbalances in uric acid metabolism and are closely associated with the gut microbiota. Advanced analytical methods facilitate the exploration of microbiota complexity. In this study, 16S rRNA sequencing data from stool samples of 233 patients were thoroughly collected. Machine learning (ML) and Shapley Additive exPlanations (SHAP) interpretability algorithms were applied to identify core taxa and predict the metabolic functions. The results revealed that the high-contribution core taxa identified by SHAP in each group, such as Oscillospiraceae_UCG-005 and Rhodococcus provided the basis for ML prediction. Among the five classification models, Random Forest (RF) achieved the best diagnostic performance, with prediction accuracy ranging from 82 to 96%. Metabolic function predictions indicated that the purine metabolism pathway contributes the most to distinguishing gout from other groups. In sum, ML-based 16S rRNA sequencing reveals key gut microbiome biomarkers, aiding new diagnostic strategies for HUA and gout.

Graphical Abstract