Nutritional Intake and Gut Microbiome Composition Predict Parkinson’s Disease

Abstract

BackgroundModels to predict Parkinson’s disease (PD) incorporating alterations of gut microbiome (GM) composition have been reported with varying success.ObjectiveTo assess the utility of GM compositional changes combined with macronutrient intake to develop a predictive model of PD.MethodsWe performed a cross-sectional analysis of the GM and nutritional intake in 103 PD patients and 81 household controls (HCs). GM composition was determined by 16S amplicon sequencing of the V3-V4 region of bacterial ribosomal DNA isolated from stool. To determine multivariate disease-discriminant associations, we developed two models using Random Forest and support-vector machine (SVM) methodologies.ResultsUsing updated taxonomic reference, we identified significant compositional differences in the GM profiles of PD patients in association with a variety of clinical PD characteristics. Six genera were overrepresented and eight underrepresented in PD patients relative to HCs, with the largest difference being overrepresentation of Lactobacillaceae at family taxonomic level. Correlation analyses highlighted multiple associations between clinical characteristics and select taxa, whilst constipation severity, physical activity and pharmacological therapies associated with changes in beta diversity. The random forest model of PD, incorporating taxonomic data at the genus level and carbohydrate contribution to total energy demonstrated the best predictive capacity [Area under the ROC Curve (AUC) of 0.74].ConclusionThe notable differences in GM diversity and composition when combined with clinical measures and nutritional data enabled the development of a predictive model to identify PD. These findings support the combination of GM and nutritional data as a potentially useful biomarker of PD to improve diagnosis and guide clinical management.

The Gut Microbiome in Parkinson’s Disease: A Longitudinal Study of the Impacts on Disease Progression and the Use of Device-Assisted Therapies

“…Subjects were recruited from the movement disorder and neurology clinics at Royal North Shore Hospital, Sydney, Australia, as reported in our previous studies ( Lubomski et al, 2020a , b , 2021a , b , c ; 2022 ). Inclusion criteria: being managed by a specialist neurologist, a clinical diagnosis of idiopathic PD according to the UK Parkinson’s Disease Society Brain Bank Diagnostic Criteria ( Hughes et al, 1992 ), and >18 years of age.…”

“…A combined central log transformation with support vector machine model to predict faster progressing PD patients using microbiota and clinical covariates at different taxonomic levels was built. Model performance at each taxonomic level was based on applying the concept of leave-one-out cross validation to calculate the area under the receiver operating characteristics curve (LOOCV-AUC) ( Lubomski et al, 2022 ).…”

NEMoE: a nutrition aware regularized mixture of experts model to identify heterogeneous diet-microbiome-host health interactions

“…Recent observational studies suggest that long-term diets could be associated with the microbiome [18], and this can further affect overall health. In a similar context, our recent study of the gut microbiome in PD showed that when partitioning individuals based on carbohydrate intake, the predictive performance of the microbiota profile to indicate PD was increased [19,20]. Together, these studies suggest that dietary differences can impact relationships between microbiome composition and host health/disease status.…”

The Interplay between Gut Microbiota and Parkinson’s Disease: Implications on Diagnosis and Treatment

“…More recently, Guo et al reported that the simultaneous measurement of Blautia levels in the feces, brain and blood can be used to differentiate cases from controls, as PD patients show reduced abundance of this genus [ 162 ]. Of note, improvements in predictive ability can be achieved by combining microbiome composition data with dietary information [ 163 ].…”