Related Experiment Video
Updated: Jun 4, 2025
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
Published on: July 24, 2019
Understanding Parkinson's: The microbiome and machine learning approach
David Rojas-Velazquez1, Sarah Kidwai2, Ting Chia Liu2
1Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Faculty of Science, Universiteitsweg 99, Utrecht 3508 TB, the Netherlands; Department of Data Science, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA, the Netherlands.
Objective:
Given that Parkinson's disease is a progressive disorder, with symptoms that worsen over time, our goal is to enhance the diagnosis of Parkinson's disease by utilizing machine learning techniques and microbiome analysis. The primary objective is to identify specific microbiome signatures that can reproducibly differentiate patients with Parkinson's disease from healthy controls.
Methods:
We used four Parkinson-related datasets from the NCBI repository, focusing on stool samples. Then, we applied a DADA2-based script for amplicon sequence processing and the Recursive Ensemble Feature Selection (REF) algorithm for biomarker discovery. The discovery dataset was PRJEB14674, while PRJNA742875, PRJEB27564, and PRJNA594156 served as testing datasets. The Extra Trees classifier was used to validate the selected features.
Results:
The Recursive Ensemble Feature Selection algorithm identified 84 features (Amplicon Sequence Variants) from the discovery dataset, achieving an accuracy of over 80%. The Extra Trees classifier demonstrated good diagnostic accuracy with an area under the receiver operating characteristic curve of 0.74. In the testing phase, the classifier achieved areas under the receiver operating characteristic curves of 0.64, 0.71, and 0.62 for the respective datasets, indicating sufficient to good diagnostic accuracy. The study identified several bacterial taxa associated with Parkinson's disease, such as Lactobacillus, Bifidobacterium, and Roseburia, which were increased in patients with the disease.
Conclusion:
This study successfully identified microbiome signatures that can differentiate patients with Parkinson's disease from healthy controls across different datasets. These findings highlight the potential of integrating machine learning and microbiome analysis for the diagnosis of Parkinson's disease. However, further research is needed to validate these microbiome signatures and to explore their therapeutic implications in developing targeted treatments and diagnostics for Parkinson's disease.
Insights
Machine learning and microbiome analysis identified specific bacterial signatures to differentiate Parkinson's disease patients from healthy individuals. This approach shows promise for improving Parkinson's disease diagnosis.
Area of Science:
- Microbiome research
- Computational biology
- Neuroscience
Background:
- Parkinson's disease (PD) is a progressive neurodegenerative disorder.
- Current diagnostic methods can be limited in early detection.
- The gut microbiome is increasingly recognized for its role in neurological health.
Purpose of the Study:
- To enhance Parkinson's disease diagnosis using machine learning (ML) and microbiome analysis.
- To identify reproducible microbiome signatures differentiating PD patients from healthy controls.
- To explore the potential of microbial biomarkers for PD detection.
Main Methods:
- Utilized four Parkinson's disease-related datasets from the NCBI repository (stool samples).
- Applied DADA2 for amplicon sequence processing and Recursive Ensemble Feature Selection (REF) for biomarker discovery.
- Employed the Extra Trees classifier for feature validation and diagnostic accuracy assessment.
Main Results:
- Identified 84 Amplicon Sequence Variants (ASVs) with >80% accuracy in the discovery dataset.
- Achieved an area under the receiver operating characteristic curve (AUC) of 0.74 with the Extra Trees classifier.
- Validated diagnostic accuracy across testing datasets (AUCs: 0.64, 0.71, 0.62), identifying increased abundance of Lactobacillus, Bifidobacterium, and Roseburia in PD patients.
Conclusions:
- Successfully identified microbiome signatures capable of differentiating PD patients from controls.
- Demonstrated the potential of integrating ML and microbiome analysis for PD diagnosis.
- Highlighted the need for further validation and exploration of therapeutic implications for identified microbial signatures.
Related Concept Videos
01:15Parkinson's Disease: Overview
01:24Parkinson's Disease: Treatment
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
01:37Neural Regulation