2023-05-10 ニューサウスウェールズ大学(UNSW)
◆研究では、健康な人々の血液サンプルを使い、15年後にパーキンソン病を発症した39人の代謝物の組み合わせを分析した。それにより、独特な代謝物の組み合わせが見つかり、未来のパーキンソン病の早期警告となる可能性があると報告された。ただし、より多くの調査が必要である。この研究により、機械学習を活用した疾患診断とモニタリングの方法が改善されることが期待される。
<関連情報>
- https://newsroom.unsw.edu.au/news/science-tech/scientists-develop-ai-tool-predict-parkinsons-disease-onset
- https://pubs.acs.org/doi/10.1021/acscentsci.2c01468
メタボロミクスデータの解釈可能な機械学習により、パーキンソン病のバイオマーカーが明らかになる Interpretable Machine Learning on Metabolomics Data Reveals Biomarkers for Parkinson’s Disease
J. Diana Zhang, Chonghua Xue, Vijaya B. Kolachalama, and William A. Donald
ACS Central Science Published:May 9, 2023
DOI:https://doi.org/10.1021/acscentsci.2c01468
Abstract
The use of machine learning (ML) with metabolomics provides opportunities for the early diagnosis of disease. However, the accuracy of ML and extent of information obtained from metabolomics can be limited owing to challenges associated with interpreting disease prediction models and analyzing many chemical features with abundances that are correlated and “noisy”. Here, we report an interpretable neural network (NN) framework to accurately predict disease and identify significant biomarkers using whole metabolomics data sets without a priori feature selection. The performance of the NN approach for predicting Parkinson’s disease (PD) from blood plasma metabolomics data is significantly higher than other ML methods with a mean area under the curve of >0.995. PD-specific markers that predate clinical PD diagnosis and contribute significantly to early disease prediction were identified including an exogenous polyfluoroalkyl substance. It is anticipated that this accurate and interpretable NN-based approach can improve diagnostic performance for many diseases using metabolomics and other untargeted ‘omics methods.
