Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures

Nguyen, Kevin P.; Raval, Vyom; Treacher, Alex; Mellema, Cooper; Yu, Fang; Pinho, Marco C.; Subramaniam, Rathan M.; Dewey, Richard B.; Montillo, Albert

doi:10.1016/j.parkreldis.2021.02.026

Cited by 18 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Like prior studies (15,18,21,34), we nd that low baseline MDS-UPDRS subpart impairment is among the most important predictors of progression status, but unlike prior studies we demonstrate how metaprediction leads to more accurate and generalizable predictions through both the projection of long-term motor and non-motor impairment trajectories and the disentanglement of the con icting baseline conditions leading to motor vs non-motor progression. While all PD individuals eventually progress at a similar rate at longer follow-up time periods, the rate and order of short-term symptom progression differs across individuals depending upon their baseline state, leading to differing and more rapid "catch-up" effects in motor vs non-motor symptoms.…”

Section: Discussionsupporting

confidence: 58%

“…In this scenario and in contrast to progression predictions described above, higher baseline impairment is predictive of future severe disease. They achieve good predictive 1-year accuracy (PPMI AUC 0.75) but with reduced generalizability in the external validation set (PDBP 0.69) except when identifying those individuals with the most severe disease (21).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Genetically-Informed Prediction of Short-Term Parkinson’s Disease Progression

Torkamani

Sadaei

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Parkinson’s disease (PD) treatments modify disease symptoms but do not halt progression, characterized by slow and varied motor and non-motor changes overtime. Variation in PD progression hampers clinical research, resulting in long and expensive clinical trials prone to failure.Objective: Development of models for short-term PD progression prediction, which could be useful for informing individual-level disease management, and shortening the time required to detect disease-modifying drug effects in clinical studies.Methods: PD progressors were defined by an increase in MDS-UPDRS scores at 12-, 24-, and 36- months post-baseline. Using only baseline features, PD progression was separately predicted across all timepoints and MDS-UPDRS subparts in an optimized XGBoost framework. These predictions were combined into a meta-predictor for 12-month MDS UPDRS Total progression. Data from the Parkinson's Progression Markers Initiative (PPMI) were used for training with independent testing on the Parkinson's Disease Biomarkers Program (PDBP) cohort.Results: 12-month PD total progression was predicted with an F-measure 0.77, ROC AUC of 0.77, and PR AUC of 0.76 when tested on a hold-out PPMI set. When tested on PDBP we achieve a F-measure 0.75, ROC AUC of 0.74, and PR AUC of 0.73. Exclusion of genetic predictors led to the greatest loss in predictive accuracy; ROC AUC of 0.66, PR AUC of 0.66-0.68 for both PPMI and PDBP testing.Conclusions: Short-term PD progression can be predicted with a combination of survey-based, neuroimaging, physician examination, and genetic predictors. Dissection of the interplay between genetic risk, motor symptoms, non-motor symptoms, and longer-term expected rates of progression enable generalizable predictions.

show abstract

Section: Discussionsupporting

confidence: 58%

Section: Introductionmentioning

confidence: 99%

Genetically-Informed Prediction of Short-Term Parkinson’s Disease Progression

Torkamani

Sadaei

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In two recent studies, measures derived from rs‐fMRI were used to predict PD prognosis. Nguyen et al ( 2021 ) used baseline measures including regional homogeneity (ReHo) and fALFF, to predict the future on‐medication UPDRS scores for patients with PD, which focused on the total score rather than the UPDRS Part III motor score that can be more severely influenced by dopaminergic treatment. De Micco et al ( 2021 ) stratified drug‐naïve patients with PD into two subtypes (early/mild and early/severe) at baseline, explored the association between the baseline topologic metrics and clinical changes, and only observed significant correlations between the functional topological metrics and cognitive progression.…”

Section: Discussionmentioning

confidence: 99%

“…A two‐year longitudinal rs‐fMRI study found that the fALFF values in the cerebellum were positively correlated with the unified PD rating scale (UPDRS) Part III scores and changes in the scores, which suggests that the cerebellum may play an important role in the motor progression of patients with PD (Hu et al, 2015 ). Combined with machine learning (ML) and fALFF, a prediction algorithm of UPDRS scores at future timepoints could be established, and robust statistical patterns could be captured (Nguyen et al, 2021 ). Findings from one of our previous studies also showed that the ALFF values may enable the prediction of the UPDRS Part III score at baseline (Hou et al, 2016 ).…”

Section: Introductionmentioning

confidence: 99%

Motor progression marker for newly diagnosed drug‐naïve patients with Parkinson's disease: A resting‐state functional MRI study

Hou

Zhang

et al. 2022

Human Brain Mapping

View full text Add to dashboard Cite

The effective early prediction of clinical outcomes of Parkinson's disease (PD) is of great significance in the implementation of appropriate interventions. We aimed to propose a method based on the use of baseline resting‐state functional characteristics (i.e., fractional amplitude of low‐frequency fluctuations, fALFF) to predict motor progression in PD patients. Resting‐state functional magnetic resonance imaging was performed on 48 newly‐diagnosed drug‐naïve PD patients and 27 age‐ and sex‐ matched healthy controls (HCs). Two PD subgroups were defined with different annual increase of Unified PD Rating Scale Part III motor scores. Least absolute shrinkage and selection operator regression analysis was performed to explore the baseline region‐functional indicators for PD discrimination as well as the predictors for future motor deficits. Two significant models composed of baseline fALFF values from cerebral subregions were proposed. The classification model that distinguished PD patients from HCs (area under the curve [AUC] = 0.897) showed the most significant imaging characteristics in the putamen and precentral gyrus. The other prediction model that evaluated the degree of future deterioration of motor symptoms in PD patients (AUC = 0.916) showed the most significant imaging characteristics in the superior occipital gyrus and caudate nucleus. Furthermore, the increased regional function in bilateral caudate nuclei was correlated with the lower annual increase in motor deficits in all PD patients. The caudate nucleus might be the core region responsible for future motor deficits in newly‐diagnosed PD patients, which may aid the development of disease progression preventive strategies in clinical practice.

show abstract

“…They reached an accuracy of 96.88%. In [18], the authors established a model that uses fractional amplitude of low frequency fluctuations (fALFF) and regional homogeneity (ReHo) in the purpose of predicting current and future individual's severity. They utilized the Unified Parkinson's Disease Rating Scale (UPDRS) to calculate scores.…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Parkinson’s Disease Detection Based on Voice Classification and Features Selection Techniques

et al. 2021

View full text Add to dashboard Cite

Parkinson’s disease (PD) is one of the most widespread diseases that, primarily, affects the motor system of the neural central system. In fact, PD is characterized by tremors, stiffness of the muscles, imprecise gait movements, and vocal impairment. An accurate diagnosis of Parkinson’s disease is usually based on many neurological, psychological, and physical investigations despite the fact that its main symptoms cannot be easily decorrelated from other diseases. As such, many automatic diagnostic support systems based on Machine Learning approaches have been recently employed to assist the PD patients' assessment. In the current paper, a comparative analysis was performed on machine learning (ML) techniques for PD identification based on voice disorders analysis. These ML methods included the Support Vector Machine (SVM), K-Nearest-Neighbors (KNN), and Decision Tree (DT) algorithms. In addition, two feature selection techniques; mRMR and ReliefF; are used to further improve the performance of the proposed classifiers. The efficiency of the developed model has been evaluated based on accuracy, sensitivity, specificity and AUC metrics, and it is higher than existing approaches. The simulation results show that the KNN algorithm yielded the best classifier performance in term of accuracy and reached an AUC of 98.26%.

show abstract

Predicting Parkinson's disease trajectory using clinical and neuroimaging baseline measures

Cited by 18 publications

References 23 publications

Genetically-Informed Prediction of Short-Term Parkinson’s Disease Progression

Genetically-Informed Prediction of Short-Term Parkinson’s Disease Progression

Motor progression marker for newly diagnosed drug‐naïve patients with Parkinson's disease: A resting‐state functional MRI study

A Novel Approach for Parkinson’s Disease Detection Based on Voice Classification and Features Selection Techniques

Contact Info

Product

Resources

About