Parkinson's disease prognostic scores for progression of cognitive decline

Machine learning for predicting cognitive decline within five years in Parkinson's disease: Comparing cognitive assessment scales with DAT SPECT and clinical biomarkers

OBJECTIVE

Parkinson's disease (PD) is an age-related neurodegenerative condition characterized mostly by motor symptoms. Although a wide range of non-motor symptoms (NMS) are frequently experienced by PD patients. One of the important and common NMS is cognitive impairment, which is measured using different cognitive scales. Monitoring cognitive impairment and its decline in PD is essential for patient care and management. In this study, our goal is to identify the most effective cognitive scale in predicting cognitive decline over a 5-year timeframe initializing clinical biomarkers and DAT SPECT.

METHODS

Machine Learning has previously shown superior performance in image and clinical data classification and detection. In this study, we propose to use machine learning with different types of data, such as DAT SPECT and clinical biomarkers, to predict PD-CD based on various cognitive scales. We collected 330 DAT SPECT images and their clinical data in baseline, years 2,3,4, and 5 from Parkinson's Progression Markers Initiative (PPMI). We then designed a 3D Autoencoder to extract deep radiomic features (DF) from DAT SPECT images, and we then concatenated it with 17 clinical features (CF) to predict cognitive decline based on Montreal Cognitive Assessment (MoCA) and The Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS-I).

RESULTS

The utilization of MoCA as a cognitive decline scale yielded better performance in various years compared to MDS-UPDRS-I. In year 4, the application of the deep radiomic feature resulted in the highest achievement, with a cross-validation AUC of 89.28, utilizing the gradient boosting classifier. For the MDS-UPDRS-I scale, the highest achievement was obtained by utilizing the deep radiomic feature, resulting in a cross-validation AUC of 81.34 with the random forest classifier.

CONCLUSIONS

The study findings indicate that the MoCA scale may be a more effective predictor of cognitive decline within 5 years compared to MDS-UPDRS-I. Furthermore, deep radiomic features had better performance compared to sole clinical biomarkers or clinical and deep radiomic combined. These results suggest that using the MoCA score and deep radiomic features extracted from DAT SPECT could be a promising approach for identifying individuals at risk for cognitive decline in four years. Future research is needed to validate these findings and explore their utility in clinical practice.

Original research: initial development of a pragmatic tool to estimate cognitive decline risk focusing on potentially modifiable factors in Parkinson's disease

Introduction

Cognitive decline is common in Parkinson's disease (PD). Calculating personalized risk of cognitive decline in PD would allow for appropriate counseling, early intervention with available treatments, and inclusion in disease-modifying trials.

Methods

Data were from the Parkinson's Progression Markers Initiative de novo cohort. Baseline scores were calculated for Lifestyle for Brain Health (LIBRA) and the Montreal Parkinson Risk of Dementia Scale (MoPaRDS) per prior literature and preliminary Parkinson's disease Risk Estimator for Decline In Cognition Tool (pPREDICT) by attributing a point for fourteen posited risk factors. Baseline and 5-year follow-up composite cognitive scores (CCSs) were calculated from a neuropsychological battery and used to define cognitive decliners (PD-decline) versus maintainers (PD-maintain).

Results

The PD-decline group (n = 44) had higher LIBRA (6.76 ± 0.57, p < 0.05), MoPaRDS (2.45 ± 1.41, p < 0.05) and pPREDICT (4.52 ± 1.66, p < 0.05) scores compared to the PD-maintain group (n = 263; LIBRA 4.98 ± 0.20, MoPaRDS 1.68 ± 1.16, pPREDICT 3.38 ± 1.69). Area-under-the-curve (AUC) for LIBRA was 0.64 (95% confidence interval [CI], 0.55-0.73), MoPaRDS was 0.66 (95% CI, 0.58-0.75) and for pPREDICT was 0.68 (95% CI, 0.61-0.76). In linear regression analyses, LIBRA (p < 0.05), MoPaRDS (p < 0.05) and pPREDICT (p < 0.05) predicted change in CCS. Only age stratified by sex (p < 0.05) contributed significantly to the model for LIBRA. Age and presence of hallucinations (p < 0.05) contributed significantly to the model for MoPaRDS. Male sex, older age, excessive daytime sleepiness, and moderate-severe motor symptoms (all p < 0.05) contributed significantly to the model for pPREDICT.

Conclusion

Although MoPaRDS is a PD-specific tool for predicting cognitive decline relying on only clinical features, it does not focus on potentially modifiable risk factors. LIBRA does focus on potentially modifiable risk factors and is associated with prediction of all-cause dementia in some populations, but pPREDICT potentially demonstrates improved performance in cognitive decline risk calculation in individuals with PD and may identify actionable risk factors. As pPREDICT incorporates multiple potentially modifiable risk factors that can be obtained easily in the clinical setting, it is a first step in developing an easily assessable tool for a personalized approach to reduce dementia risk in people with PD.

Aging, Parkinson's Disease, and Models: What Are the Challenges?

Parkinson's disease (PD) is a chronic, neurodegenerative condition characterized by motor symptoms such as bradykinesia, rigidity, and tremor, alongside multiple nonmotor symptoms. The appearance of motor symptoms is linked to progressive dopaminergic neuron loss within the substantia nigra. PD incidence increases sharply with age, suggesting a strong association between mechanisms driving biological aging and the development and progression of PD. However, the role of aging in the pathogenesis of PD remains understudied. Numerous models of PD, including cell models, toxin-induced models, and genetic models in rodents and nonhuman primates (NHPs), reproduce different aspects of PD, but preclinical studies of PD rarely incorporate age as a factor. Studies using patient neurons derived from stem cells via reprogramming methods retain some aging features, but their characterization, particularly of aging markers and reproducibility of neuron type, is suboptimal. Investigation of age-related changes in PD using animal models indicates an association, but this is likely in conjunction with other disease drivers. The biggest barrier to drawing firm conclusions is that each model lacks full characterization and appropriate time-course assessments. There is a need to systematically investigate whether aging increases the susceptibility of mouse, rat, and NHP models to develop PD and understand the role of cell models. We propose that a significant investment in time and resources, together with the coordination and sharing of resources, knowledge, and data, is required to accelerate progress in understanding the role of biological aging in PD development and improve the reliability of models to test interventions.

A progression analysis of motor features in Parkinson's disease based on the mapper algorithm

Background

Parkinson's disease (PD) is a neurodegenerative disease with a broad spectrum of motor and non-motor symptoms. The great heterogeneity of clinical symptoms, biomarkers, and neuroimaging and lack of reliable progression markers present a significant challenge in predicting disease progression and prognoses.

Methods

We propose a new approach to disease progression analysis based on the mapper algorithm, a tool from topological data analysis. In this paper, we apply this method to the data from the Parkinson's Progression Markers Initiative (PPMI). We then construct a Markov chain on the mapper output graphs.

Results

The resulting progression model yields a quantitative comparison of patients' disease progression under different usage of medications. We also obtain an algorithm to predict patients' UPDRS III scores.

Conclusions

By using mapper algorithm and routinely gathered clinical assessments, we developed a new dynamic models to predict the following year's motor progression in the early stage of PD. The use of this model can predict motor evaluations at the individual level, assisting clinicians to adjust intervention strategy for each patient and identifying at-risk patients for future disease-modifying therapy clinical trials.

Path analysis of biomarkers for cognitive decline in early Parkinson’s disease

Clinical and biochemical diversity of Parkinson’s disease (PD) and numerous demographic, clinical, and pathological measures influencing cognitive function and its decline in PD create problems with the determination of effects of individual measures on cognition in PD. This is particularly the case where these measures significantly interrelate with each other producing intricate networks of direct and indirect effects on cognition. Here, we use generalized structural equation modelling (GSEM) to identify and characterize significant paths for direct and indirect effects of 14 baseline measures on global cognition in PD at baseline and at 4 years later. We consider 269 drug-naïve participants from the Parkinson’s Progression Marker Initiative database, diagnosed with idiopathic PD and observed for at least 4 years after baseline. Two GSEM networks are derived, highlighting the possibility of at least two different molecular pathways or two different PD sub-types, with either CSF p-tau181 or amyloid beta (1–42) being the primary protein variables potentially driving progression of cognitive decline. The models provide insights into the interrelations between the 14 baseline variables, and determined their total effects on cognition in early PD. High CSF amyloid concentrations (> 500 pg/ml) are associated with nearly full protection against cognitive decline in early PD in the whole range of baseline age between 40 and 80 years, and irrespectively of whether p-tau181 or amyloid beta (1–42) are considered as the primary protein variables. The total effect of depression on cognition is shown to be strongly amplified by PD, but not at the time of diagnosis or at prodromal stages. CSF p-tau181 protein could not be a reliable indicator of cognitive decline because of its significantly heterogeneous effects on cognition. The outcomes will enable better understanding of the roles of the clinical and pathological measures and their mutual effects on cognition in early PD.

Motor Progression in Early-Stage Parkinson's Disease: A Clinical Prediction Model and the Role of Cerebrospinal Fluid Biomarkers

Background: The substantial heterogeneity of clinical symptoms and lack of reliable progression markers in Parkinson's disease (PD) present a major challenge in predicting accurate progression and prognoses. Increasing evidence indicates that each component of the neurovascular unit (NVU) and blood-brain barrier (BBB) disruption may take part in many neurodegenerative diseases. Since some portions of CSF are eliminated along the neurovascular unit and across the BBB, disturbing the pathways may result in changes of these substances.

Methods: Four hundred seventy-four participants from the Parkinson's Progression Markers Initiative (PPMI) study (NCT01141023) were included in the study. Thirty-six initial features, including general information, brief clinical characteristics and the current year's classical scale scores, were used to build five regression models to predict PD motor progression represented by the coming year's Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III score after redundancy removal and recursive feature elimination (RFE)-based feature selection. Then, a threshold range was added to the predicted value for more convenient model application. Finally, we evaluated the CSF and blood biomarkers' influence on the disease progression model.

Results: Eight hundred forty-nine cases were included in the study. The adjusted R² values of three different categories of regression model, linear, Bayesian and ensemble, all reached 0.75. Models of the same category shared similar feature combinations. The common features selected among the categories were the MDS-UPDRS Part III score, Montreal Cognitive Assessment (MOCA) and Rapid Eye Movement Sleep Behavior Disorder Questionnaire (RBDSQ) score. It can be seen more intuitively that the model can achieve certain prediction effect through threshold range. Biomarkers had no significant impact on the progression model within the data in the study.

Conclusions: By using machine learning and routinely gathered assessments from the current year, we developed multiple dynamic models to predict the following year's motor progression in the early stage of PD. These methods will allow clinicians to tailor medical management to the individual and identify at-risk patients for future clinical trials examining disease-modifying therapies.