“…The fact that the total score of the UPDRS represents the severity of both motor and non motor symptoms could explain this result. In our study, the levodopa LEDD also resulted in rules with lift values below one, suggesting that high doses of levodopa may contribute to the development of dyskinesias as demonstrated by Eusebi et al 6 , Pandey et al 8 , Olanow et al 2013, and Dias et al 23 .…”
Dyskinesias are non preventable abnormal involuntary movements that represent the main challenge of the long term treatment of Parkinson’s disease (PD) with the gold standard dopamine precursor levodopa. Applying machine learning techniques on the data extracted from the Parkinson’s Progression Marker Initiative (PPMI, Michael J. Fox Foundation), this study was aimed to identify PD patients who are at high risk of developing dyskinesias. Data regarding clinical, behavioral and neurological features from 697 PD patients were included in our study. Our results show that the Random Forest was the classifier with the best and most consistent performance, reaching an area under the receiver operating characteristic (ROC) curve of up to 91.8% with only seven features. Information regarding the severity of the symptoms, the semantic verbal fluency, and the levodopa treatment were the most important for the prediction, and were further used to create a Decision Tree, whose rules may guide the pharmacological management of PD symptoms. Our results contribute to the identification of PD patients who are prone to develop dyskinesia, and may be considered in future clinical trials aiming at developing new therapeutic approaches for PD.
“…The fact that the total score of the UPDRS represents the severity of both motor and non motor symptoms could explain this result. In our study, the levodopa LEDD also resulted in rules with lift values below one, suggesting that high doses of levodopa may contribute to the development of dyskinesias as demonstrated by Eusebi et al 6 , Pandey et al 8 , Olanow et al 2013, and Dias et al 23 .…”
Dyskinesias are non preventable abnormal involuntary movements that represent the main challenge of the long term treatment of Parkinson’s disease (PD) with the gold standard dopamine precursor levodopa. Applying machine learning techniques on the data extracted from the Parkinson’s Progression Marker Initiative (PPMI, Michael J. Fox Foundation), this study was aimed to identify PD patients who are at high risk of developing dyskinesias. Data regarding clinical, behavioral and neurological features from 697 PD patients were included in our study. Our results show that the Random Forest was the classifier with the best and most consistent performance, reaching an area under the receiver operating characteristic (ROC) curve of up to 91.8% with only seven features. Information regarding the severity of the symptoms, the semantic verbal fluency, and the levodopa treatment were the most important for the prediction, and were further used to create a Decision Tree, whose rules may guide the pharmacological management of PD symptoms. Our results contribute to the identification of PD patients who are prone to develop dyskinesia, and may be considered in future clinical trials aiming at developing new therapeutic approaches for PD.
“…There is no cure and the mainstay (or standard) treatment is to administer L-DOPA. Generally, the problem with l-DOPA is that efficacy wanes after chronic use and that is when side effects like dyskinesia can occur (Kwon et al, 2022, Dias et al, 2023). There are only limited PD biomarkers available for screening (e.g.…”
SummaryParkinson’s disease (PD) is a devastating neurodegenerative disorder, with both genetic and environmental causes. Human genetic studies have identified ∼20 inherited familial genes that cause monogenic forms of PD. We have investigated the effects of individual familial PD mutations by developing a medium-throughput platform using genome-editing to install individual PD mutations in human pluripotent stem cells (hPSCs) that we subsequently differentiated into midbrain lineage cells including dopaminergic (DA) neurons in cell culture. Both global gene expression and pre-mRNA splicing patterns in midbrain cultures carrying inherited, pathogenic PD mutations in the PRKN and SNCA genes were analyzed. This analysis revealed that PD mutations lead to many more pre-mRNA splicing changes than changes in overall gene RNA expression levels. Importantly, we have also shown that these splicing changes overlap with changes found in PD patient postmortem brain sample RNA-seq datasets. These pre-mRNA splicing changes are in genes related to cytoskeletal and neuronal process formation, as well as splicing factors and spliceosome components. We predict that these mutation-specific pre-mRNA isoforms can be used as biomarkers for PD that are linked to the familial PD mutant genotypes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.