Prediction of Parkinson’s Disease Risk Based on Genetic Profile and Established Risk Factors

Chairta, Paraskevi; Hadjisavvas, Andreas; Georgiou, Andrea; Loizidou, Maria A.; Yiangou, Kristia; Demetriou, Christiana A.; Pantziaris, M.; Michailidou, Kyriaki; Zamba‐Papanicolaou, Eleni

doi:10.3390/genes12081278

Cited by 7 publications

(5 citation statements)

References 29 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, our prediction model built with just PRS can achieve an average AUC of 0.75 (scenario 0 in Fig. 1), which is substantially higher than that in the existing literature (e.g., the AUCs are around 0.55 and 0.61 in Chairta et al 23 , and Li et al 14 , respectively).…”

Section: Discussionmentioning

confidence: 57%

Polygenic risk score-based prediction for Parkinson’s disease

Wen,

Zhang,

et al. 2023

Preprint

View full text Add to dashboard Cite

Parkinson’s disease (PD) is a complex neurodegenerative disorder with unclear etiology and ineffective treatments. Integrating multimodal data for PD prediction remains challenging. We analyzed data obtained from the Parkinson’s Progression Markers Initiative, using polygenic risk scores (PRS) to reflect genetic susceptibility to PD. We compared the prediction accuracy of models with PRS, demographics, clinical assessment, and biomarkers progressively integrated and investigated relationships. The SDPR-based PRS exhibited the highest prediction performance with an AUC of 0.75. Models combining PRS, demographic, and clinical variables achieved an AUC of 0.91, surpassing models without PRS and matching those with biomarkers. PRS correlated with olfactory function and Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS), with its influence on PD risk dependent on gender and MDS-UPDRS. Our study illuminates PD etiology and provides a practical risk assessment framework, highlighting its omnigenic architecture, and the potential for accurate prediction using PRS and non-invasive clinical data.

show abstract

Section: Discussionmentioning

confidence: 57%

Polygenic risk score-based prediction for Parkinson’s disease

Wen,

Zhang,

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, compared to scenario III, the model's performance was substantially enhanced with the addition of PRS, indicating that ignoring the contributions of genetic factors can lead to reduced prediction performance. For example, Chairta et al combined a PRS composed of twelve SNPs with seven environmental factors to predict PD, emphasizing the potential of using genetic factors for predicting PD risk [39]. It is worth noting that with PRS incorporated (i.e., scenario IV), the prediction models built by penalized logistic regression and XGBoost methods can be quite accurate with penalized logistic regression having an AUC of 0.94 and Brier score of 0.08.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Parkinson’s Disease Using Machine Learning Methods

Zhang,

Zhou,

et al. 2023

Biomolecules

View full text Add to dashboard Cite

The detection of Parkinson’s disease (PD) in its early stages is of great importance for its treatment and management, but consensus is lacking on what information is necessary and what models should be used to best predict PD risk. In our study, we first grouped PD-associated factors based on their cost and accessibility, and then gradually incorporated them into risk predictions, which were built using eight commonly used machine learning models to allow for comprehensive assessment. Finally, the Shapley Additive Explanations (SHAP) method was used to investigate the contributions of each factor. We found that models built with demographic variables, hospital admission examinations, clinical assessment, and polygenic risk score achieved the best prediction performance, and the inclusion of invasive biomarkers could not further enhance its accuracy. Among the eight machine learning models considered, penalized logistic regression and XGBoost were the most accurate algorithms for assessing PD risk, with penalized logistic regression achieving an area under the curve of 0.94 and a Brier score of 0.08. Olfactory function and polygenic risk scores were the most important predictors for PD risk. Our research has offered a practical framework for PD risk assessment, where necessary information and efficient machine learning tools were highlighted.

show abstract

“…Affecting millions globally, the prevalence of PD increases with age 3 . Despite extensive research, the exact etiology of PD remains unclear, involving a complex interplay of genetic, environmental, and lifestyle factors 4,5 .…”

Section: Introductionmentioning

confidence: 99%

Cerebrospinal Fluid and Plasma Metabolites with Parkinson’s Disease: A Mendelian Randomization Study

Wang,

Zheng,

Fang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background and Objective: Previous studies have identified associations between metabolites and Parkinson's disease (PD), but the causal relationships remain unclear. This study aims to identify causal relationships between specific cerebrospinal fluid (CSF) and plasma metabolites and the PD risk using Mendelian Randomization (MR). Methods: We utilized data on 338 CSF metabolites from the Wisconsin Alzheimer's Disease Research Center and the Wisconsin Registry for Alzheimer's Prevention, and 1,400 plasma metabolites from the Canadian Longitudinal Study on Aging. PD outcome data were obtained from a GWAS meta-analysis by the International Parkinson's Disease Genomics Consortium. MR analysis was conducted using the TwoSampleMR package in R. Results: MR analysis identified 49 plasma metabolites with suggestive causal relationships with PD risk, including 21 positively associated metabolites, 23 negatively associated metabolites, and 5 unknown compounds. In the CSF, six metabolites showed suggestive causal relationships with PD, including positively associated dimethylglycine, gluconate, oxalate (ethanedioate), and the unknown metabolite X-12015, while (1-enyl-palmitoyl)-2-arachidonoyl-GPC (P-16:0/20:4) and the unknown metabolite X-23587 were negatively associated. Among the plasma metabolites, those with a positive association with PD risk include hydroxy-3-carboxy-4-methyl-5-propyl-2-furanpropanoic acid (hydroxy-CMPF), carnitine C14, 1-linoleoyl-GPG (18:2), glucose to maltose ratio, and cis-3,4-methyleneheptanoate. Conversely, metabolites with a negative association with PD risk include tryptophan, succinate to acetoacetate ratio, N,N,N-trimethyl-alanylproline betaine (TMAP), glucuronide of piperine metabolite C17H21NO3, and linoleoylcholine. Conclusion: Our study underscores the correlation between CSF and plasma metabolites and PD risk, highlighting specific metabolites as potential biomarkers for diagnosis and therapeutic targets.

show abstract

Prediction of Parkinson’s Disease Risk Based on Genetic Profile and Established Risk Factors

Cited by 7 publications

References 29 publications

Polygenic risk score-based prediction for Parkinson’s disease

Polygenic risk score-based prediction for Parkinson’s disease

Prediction of Parkinson’s Disease Using Machine Learning Methods

Cerebrospinal Fluid and Plasma Metabolites with Parkinson’s Disease: A Mendelian Randomization Study

Contact Info

Product

Resources

About