Progression Markers Initiative Research Articles

Medication recommendation for Parkinson’s disease based on dynamics of symptom progression

Parkinson’s Disease (PD) is a chronic condition, with extensive research on initial medication selection for treatment, but limited guidance on long-term medication management. This study aims to identify optimal medication adjustment strategies based on patient clusters, focusing on either maximizing time spent in favorable health states or minimizing time spent in unfavorable ones while avoiding adverse effects. To guide treatment, we developed decision models using prescription dosages converted into standardized units for various medications. Using data from the Parkinson’s Progression Markers Initiative, we employed a multivariate time-series clustering approach to capture symptom progression dynamics. This analysis identified four distinct clusters: two representing desirable and undesirable states, and two highlighting motor-focused and non-motor-focused failures across multiple domains. We developed two separate Markov Decision Process (MDP) models to address these dual objectives, which were then integrated into a comprehensive framework that suggests optimal actions and cautions against risky ones for each patient state. This model provides valuable insights for clinical decision-making by offering flexible guidance on adjusting medication intensity rather than prescribing specific medication types, enhancing its applicability in clinical practice.

Temporal ordering of cognitive impairment in Parkinson's disease patients based on disease progression models

IntroductionIdentifying Parkinson's disease (PD) patients at risk of cognitive decline is crucial for enhancing clinical interventions. While several models predicting cognitive decline in PD exist, a new machine learning framework called disease progression models (DPMs) offers a data-driven approach to understand disease evolution. MethodsWe enrolled 423 PD patients and 196 healthy controls from the Parkinson's Progression Markers Initiative (PPMI). Our study encompassed a range of biomarkers, including motor, neurocognitive, and neuroimaging evaluations at baseline and annually. A methodology was employed to select optimal combinations of biomarkers for constructing DPMs with superior predictive capabilities for both diagnosing and estimating conversion times toward cognitive decline. ResultsAt baseline, the approach showed excellent performance in identifying individuals at high risk of cognitive decline within the first five years. Furthermore, the proposed timeline from cognitive impairment to dementia was also used to explore clinical events such as the onset of cognitive impairment, the development of dementia or amyloid pathology. The presence of amyloid pathology did not alter the progression of cognitive impairment among PD patients. ConclusionsNeuropsychological measures and certain biomarkers, including cerebrospinal fluid (CSF) amyloid beta 42 (Aβ42) and dopamine transporter deficits, can be used to predict cognitive decline and estimate a timeline from cognitive impairment to dementia, with amyloid pathology preceding the onset of dementia in many cases. Our DPMs suggested that the profiles of CSF Aβ42 and phosphorylated tau in PD patients may differ from those in aging patients and those with Alzheimer's disease.

A prediction model for the walking and balance milestone in Parkinson's disease

BackgroundWalking and balance impairments, represented by freezing of gait and falls, are significant contributors to disability in advanced Parkinson's disease (PD) patients. However, the composite measure of the Walking and Balance Milestone (WBMS) has not been thoroughly investigated. MethodsThis study included 606 early-stage PD patients from the Parkinson's Progression Markers Initiative (PPMI) database, with a disease duration of less than 2 years and no WBMS at baseline. Patients were divided into a model development cohort (70 %) and a validation cohort (30 %) according to the enrollment site. Longitudinal follow-up data over a period of 12 years were analyzed. ResultsAmong all 606 patients, the estimated probability of being WBMS-free at the 5th and 10th year was 88 % and 60 %, respectively. Five clinical variables (Age, Symbol Digit Modalities Test (SDMT), postural instability and gait difficulty (PIGD) score, Movement Disorder Society-Unified Parkinson's Disease Rating Scale Part I (MDS-UPDRS-I) score, and REM Sleep Behavior Disorder (RBD) were used to construct the Cox predictive model. The C-index of the model was 0.75 in the development cohort and 0.76 in the validation cohort. By optimizing the PIGD and MDS-UPDRS-I variables, an easy-to-use model was achieved with comparable predictive performance. ConclusionA predictive model based on five baseline clinical measures (Age, SDMT, PIGD score, MDS-UPDRS-I score, RBD) could effectively estimate the risk of the WBMS in early PD patients. This model is valuable for prognostic counseling and clinical intervention trials for gait and balance impairment.

Eleven Years of Change: Disease Progression in Biomarker-Defined Sporadic Parkinson's Disease.

Long-term longitudinal data on outcomes in sporadic Parkinson's Disease are limited, especially from cohorts with extensive biological characterization. Recent advances in biomarkers characterization of Parkinson's Disease necessitate an updated examination of long-term progression within contemporary cohorts like the Parkinson's Progression Markers Initiative, which enrolled individuals within 2 years of clinical diagnosis of Parkinson's Disease. Our study leverages the Neuronal Synuclein Disease framework, which defines the disease based on biomarker assessed presence of neuronal alpha-synuclein and dopamine deficit, rather than based on conventional clinical diagnostic criteria. In this study we aimed to provide a comprehensive long-term description of disease progression using the integrated biological and clinical staging system framework. We analyzed data from 344 participants from the sporadic Parkinson's Disease cohort in the Parkinson's Progression Markers Initiative, who met Neuronal Synuclein Disease criteria. We assessed 11-year progression in a spectrum of clinical measures. We used Cox proportional hazards models to assess the association between baseline stage and time to key outcomes, including survival, postural instability (Hoehn & Yahr ≥ 3), loss of independence (Schwab & England < 80%), cognitive decline, and domain-based milestones such as walking and balance, motor complications, autonomic dysfunction, and activities of daily living. Additional analyses were completed to account for death and participant dropout. Biomarker analysis included dopamine transporter binding measures, as well as serum urate, neurofilament light chain and CSF amyloid-beta, phosphorylated tau and total tau. At baseline, despite the cohort consisting of individuals within 2 years of clinical diagnosis, there was clear separation of participants in Neuronal Synuclein Disease Stages (23% Stage 2b, 67% Stage 3, 10% Stage 4). At 11 years, data were available for 153 participants; 35 participants had died over the follow up period. Of retained participants, 59% presented normal cognition, 24% had evidence of postural instability and mean Schwab & England score was 78.5. Serum neurofilament light chain consistently increased over time. No other biofluids had a consistent change in trajectory. Of importance, baseline Neuronal Synuclein Disease Stage predicted progression to clinically meaningful milestones. This study provides data on longitudinal, 11-year progression in Neuronal Synuclein Disease participants within 2 years of clinical diagnosis. We observed better long-term outcomes in this contemporary observational study cohort. It highlights the heterogeneity in the early Parkinson's Disease population as defined by clinical diagnostic criteria and underscores the importance of shifting from clinical to biologically and functionally based inclusion criteria in the design of new clinical trials.

Unraveling the interplay of β-amyloid pathology and Parkinson's disease progression: Insights from autopsy-confirmed patients

BackgroundParkinson's disease (PD) is a prevalent neurodegenerative disorder that manifests with both motor and non-motor symptoms, with α-synuclein misfolding recognized as a key contributor. Cognitive decline in advanced PD stages prompts interest in amyloid deposition, a hallmark of Alzheimer's disease (AD), as a potential factor. This study explores the impact of β-amyloid (Aβ) pathology in PD patients on disease progression, aiming to elucidate the role of Aβ in PD development and progression. MethodsThis study included autopsy-confirmed PD patients with post-mortem analyses from the Parkinson's Progression Markers Initiative. Comprehensive clinical assessments, including demographic data, clinical features, CSF markers, and neuroimaging, were conducted. Statistical analyses assessed differences between groups based on the severity of AD neuropathological changes. ResultsAll 16 PD participants exhibited severe Lewy body pathology, with 75 % displaying AD neuropathological changes. At baseline, PD patients with severe or moderate AD neuropathological changes had a lower Aβ42 levels (p = 0.022) and Aβ42/tau ratio (p = 0.001). Longitudinal follow-up data indicated that individuals with severe or moderate AD neuropathological changes exhibited a more rapid decline in MOCA score and BJLOT score, along with a quicker increase in MDS-UPDRS Ⅲ score. ConclusionsThe study underscores the presence of severe Aβ pathology in PD, suggesting a role in accelerated disease progression. Cross-seeding between Aβ and α-synuclein may contribute to rapid clinical symptom progression. Further research is needed for a comprehensive understanding of neurodegenerative disease complexities and exploring potential therapeutic interventions targeting protein aggregation.

Sustained effect of prasinezumab on Parkinson's disease motor progression in the open-label extension of the PASADENA trial.

The Phase II trial of Anti-alpha-Synuclein Antibody in Early Parkinson's Disease (PASADENA) is an ongoing double-blind, placebo-controlled trial evaluating the safety and efficacy of prasinezumab in early-stage Parkinson's disease (PD). During the double-blind period, prasinezumab-treated individuals showed less progression of motor signs (Movement Disorders Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III) than placebo-treated individuals. We evaluated whether the effect of prasinezumab on motor progression, assessed as a change in MDS-UPDRS Part III score in the OFF and ON states, and MDS-UPDRS Part II score, was sustained for 4 years from the start of the trial. We compared participants enrolled in the PASADENA open-label extension study with those enrolled in an external comparator arm derived from the Parkinson's Progression Markers Initiative observational study. The PASADENA delayed-start (n = 94) and early-start (n = 177) groups showed a slower decline (a smaller increase in score) in MDS-UPDRS Part III scores in the OFF state (delayed start, -51%; early start, -65%), ON state (delayed start, -94%; early start, -118%) and MDS-UPDRS Part II (delayed start, -48%; early start, -40%) than did the Parkinson's Progression Markers Initiative external comparator (n = 303). This exploratory analysis, which requires confirmation in future studies, suggested that the effect of prasinezumab in slowing motor progression in PD may be sustained long term. PASADENA ClinicalTrials.gov no. NCT03100149 .

A brain-network operator for modeling disease: a first data-based application for Parkinson’s disease

AbstractThe complexity of our brains can be described as a multi-layer network: neurons, neural agglomerates, and lobes. Neurological diseases are often related to malfunctions in this network. We propose a conceptual model of the brain, describing the disease as the result of an operator affecting and disrupting the network organization. We adopt the formalism of operators, matrices, and tensor products adapted from theoretical physics. This novel approach can be tested and instantiated for different diseases, balancing mathematical formalism and data-driven findings, including pathologies where aging is included as a risk factor. We quantitatively model the K-operator from real data of Parkinson’s Disease, from the Parkinson’s Progression Markers Initiative (PPMI) upon concession by the University of Southern California. The networks are reconstructed from fMRI analysis, resulting in a matrix acting on the healthy brain and giving as output the diseased brain. We finally decompose the K-operator into the tensor product of its submatrices and we are able to assess its action on each region of interest (ROI) characterizing the brain for the specific considered samples. We also approximate the time-dependent K-operator from the fMRI of the same patient at the baseline and at the first follow-up. Our results confirm the findings of the literature on the topic. Also, these applications confirm the feasibility of the proposed analytic technique. Further research developments can compare operators for different patients and for different diseases, looking for commonalities and aiming to develop a comprehensive theoretical approach.

Exploratory Analysis of the Association Between Plasma Ceramide Alterations and Cognitive Dysfunction in Parkinson's Disease.

Prior research has underscored the importance of sphingolipid metabolism in Parkinson's disease (PD) pathogenesis. Our objective was to explore the associations between plasma ceramide levels and PD patients with cognitive dysfunction (PD-CD). We enrolled two study populations from Eastern China and the Parkinson's Progression Markers Initiative (PPMI), comprising 290 (100 HCs, 160 PDs, and 30 MSAs) and 429 (125 HCs and 304 PDs) participants, respectively. The plasma levels of ceramides (Cer 16:0, Cer 18:0, Cer 24:0, and Cer 24:1) were tested via HPLC-MS/MS analysis. Compared with those in the HC group, the plasma levels of Cer 18:0, Cer 24:1, Cer 16:0/Cer 24:0, Cer 18:0/Cer 24:0, and Cer 24:1/Cer 24:0 were higher in both the PD and MSA groups. Significant differences in the plasma levels of Cer 16:0/Cer 24:0, Cer 18:0/Cer 24:0, and Cer 24:1/Cer 24:0 were observed among the PD-NC (PD with normal cognition), PD-MCI (PD with mild cognitive impairment), and PDD (PD dementia) groups, with the PDD group exhibiting the highest levels. PD patients with higher baseline levels of plasma ceramides (specifically, Cer 18:0, Cer 16:0/Cer 24:0, Cer 18:0/Cer 24:0, and Cer 24:1/Cer 24:0) demonstrated accelerated cognitive decline compared with individuals who had lower baseline plasma ceramide levels during the 5-year follow-up period. A biomarker panel including Cer 18:0/Cer 24:0 and Cer 24:1/Cer 24:0 could effectively differentiate PD-CD from PD-NC with notable diagnostic accuracy. Our results indicate that plasma ceramide levels could potentially be used as diagnostic biomarkers for PD-CD.

CISL-PD: A deep learning framework of clinical intervention strategies for Parkinson’s disease based on directional counterfactual Dual GANs

Parkinson’s disease (PD) is a prevalent chronic neurodegenerative disorder characterized by both motor and non-motor symptoms. The significant heterogeneity among PD patients poses a major challenge for treatment interventions. Current clinical interventions for PD primarily target motor symptoms, often neglecting non-motor symptoms, which can lead to unnecessary complications in non-motor symptoms while treating motor symptoms. Therefore, it is crucial to provide comprehensive and precise intervention strategies that encompass both symptom types. To address this issue, we develop a deep learning framework of clinical intervention strategies for PD (CISL-PD) based on counterfactual thinking. This framework introduces Directional Counterfactual Dual Generative Adversarial Networks (DCD-GANs), which apply various counterfactual constraints to longitudinal data to generate practical and plausible counterfactual instances aligned with clinical reality. By analyzing these counterfactual instances and their differences from the original instances, we explore PD intervention strategies with duration-specific fine regulation of multidimensional features. Experiments conducted on 374 PD patients from the Parkinson’s Progression Markers Initiative (PPMI) demonstrate that the counterfactual instances generated by DCD-GANs surpass other state-of-the-art models in terms of similarity (0.307 ± 0.246), sparsity (0.513 ± 0.161), smoothness (0.238 ± 0.135), and trend consistency (0.100 ± 0.089). From these generated counterfactual instances, we develop three clinically feasible intervention strategies that address both motor and non-motor symptoms and identify corresponding patterns of PD with distinct progression differences. Validation on an independent cohort of 351 patients from the National Institute of Neurological Disorders and Stroke Parkinson’s Disease Biomarkers Program (PDBP) confirmed the framework’s robustness and generalizability. By offering precise, multidimensional intervention strategies that can address both motor and non-motor symptoms, the CISL-PD framework has the potential to enhance patient outcomes, reduce complications, improve overall quality of life, and guide clinical decision-making.

APOE contributes to longitudinal impulse control disorders progression in Parkinson’s disease

BackgroundImpulse control disorders (ICDs) are an increasingly recognized complication in Parkinson disease (PD). The pathogenesis of ICDs is currently unclear. Few genetic studies have been conducted in this area.ObjectiveWe aimed to ascertain the correlation between APOE and ICDs, and identify clinical predictors of ICDs in PD.MethodsThis study included 287 PD patients from the Parkinson’s Progression Markers Initiative. They were followed up to investigate the progression of ICDs over a period of 5 years. The cumulative incidence of ICDs and potential risk factors were evaluated using Kaplan-Meier and Cox regression analyses.Results44.3% (31/70) patients with APOE ɛ4 and 32.3% (70/217) patients without APOE ɛ4 developed ICDs during the five-year follow up period. There were significant differences between the PD with and without ICDs development group in age, MSEADLG score, ESS score, GDS score, and STAI score at baseline. In multivariable Cox regression analysis, APOE ε4 (HR = 1.450, p = 0.048) and STAI score (HR = 1.017, p = 0.001) were predictors of the development of ICDs. Patients with APOE ɛ4 group showed significantly lower CSF Aβ42 and CSF α-syn level than patients without APOE ɛ4 group at baseline. In patients with APOE ɛ4 group, the “low α-syn level” group and the “low ptau/tau ratio” group had a significantly higher incidence of ICDs, respectively.ConclusionsThis study provides important insights into the potential role of the APOE gene in the development of ICDs in PD. Further studies are needed to confirm our findings and to investigate the underlying mechanisms in more detail.

Machine learning based Parkinson’s disease detection and progression evaluation using gray and white matter segmentation from 3D MRI

Parkinson’s disease (PD) is a movement-related neurological condition caused by the death of brain nerve cells that produce dopamine. T1 MR images were obtained from the Parkinson’s Progression Markers Initiative (PPMI) database. Data was collected at baseline, and at 48 months duration. SPM12 software was used to segment gray matter (GM) and white matter (WM) from the MR images. For the classification of PD, CNN and machine learning (ML) classifiers were used to train on the segmented GM and WM. The findings demonstrated that utilizing the segmented GM and WM obtained from MR images at 48 months had a better predictive ability than the data obtainment at the baseline. CNNs did not perform as well as the conventional ML algorithms, especially for the baseline data. This result is most likely due to the smaller dataset available for training the CNNs, as CNNs normally require more data for best performance. Overall, machine learning algorithms were able to distinguish between people with Parkinson’s disease and healthy controls by analyzing GM and WM in brain scans. The classifiers trained at different stages demonstrated varying degrees of accuracy, with the predictive accuracy for the 48-month dataset surpassing that of the baseline data by a significant margin. The accuracy rate for GM was 65.78% at baseline and improved significantly to 92.59% at 48 months. Similarly, the accuracy rate for WM was 60.52% at baseline and improved to 88.89% at 48 months.

Impact of excessive daytime sleepiness on the progression of freezing of gait in de novo Parkinson's disease: a cohort study.

Excessive daytime sleepiness (EDS) and freezing of gait (FOG) are prevalent non-motor and motor symptoms in patients with Parkinson's disease (PD), significantly impacting their quality of life. However, the correlation between EDS and FOG progression inde novoPD patients remains controversial. A total of 328 participants from the Parkinson's Progression Markers Initiative (PPMI) were divided into two groups: 43 with EDS (EDS group) and 285 without EDS (nEDS group). The cumulative incidence of FOG was assessed at the 5-year follow-up using Kaplan-Meier and log-rank tests. Multivariate Cox proportional hazards models were used to assess the impact of EDS on FOG progression in PD patients, with validation for robustness through sensitivity and subgroup analyses. The EDS group experienced a higher incidence of FOG throughout the 5-year follow-up than did the nEDS group. Multivariate Cox proportional hazards models showed significantly association between EDS severity and enhanced risk of developing FOG (HR = 1.076, 95% CI:1.007 ~ 1.149, P = 0.031). For sensitivity analysis, parallel analyseswere performedby substituting the independent variable with categorical variables, which yielded analogous outcomes (HR = 1.837, 95% CI:1.063 ~ 3.174,P = 0.029). Furthermore, subgroup analyses based on sex, age, TD/PIGD classification, depressive symptoms, cognitive impairment, mean caudate nucleus uptake level, mean putamen nucleus uptake level and CSF Aβ-42 level revealed no significant interactions between subgroups (allPvalues for interaction were > 0.05). EDS is a potential prognosis factor for the progression of FOG in patients with PD.

Long-Term Dementia Risk in Parkinson Disease.

It is widely cited that dementia occurs in up to 80% of patients with Parkinson disease (PD), but studies reporting such high rates were published over two decades ago, had relatively small samples, and had other limitations. We aimed to determine long-term dementia risk in PD using data from two large, ongoing, prospective, observational studies. Participants from the Parkinson's Progression Markers Initiative (PPMI), a multisite international study, and a long-standing PD research cohort at the University of Pennsylvania (Penn), a single site study at a tertiary movement disorders center, were recruited. PPMI enrolled de novo, untreated PD participants and Penn a convenience cohort from a large clinical center. For PPMI, a cognitive battery is administered annually, and a site investigator makes a cognitive diagnosis. At Penn, a comprehensive cognitive battery is administered either annually or biennially, and a cognitive diagnosis is made by expert consensus. Interval-censored survival curves were fit for time from PD diagnosis to stable dementia diagnosis for each cohort, using cognitive diagnosis of dementia as the primary end point and Montreal Cognitive Assessment (MoCA) score <21 and Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part I cognition score ≥3 as secondary end points for PPMI. In addition, estimated dementia probability by PD disease duration was tabulated for each study and end point. For the PPMI cohort, 417 participants with PD (mean age 61.6 years, 65% male) were followed, with an estimated probability of dementia at year 10 disease duration of 9% (site investigator diagnosis), 15% (MoCA), or 12% (MDS-UPDRS Part I cognition). For the Penn cohort, 389 participants with PD (mean age 69.3 years, 67% male) were followed, with 184 participants (47% of cohort) eventually diagnosed with dementia. The interval-censored curve for the Penn cohort had a median time to dementia of 15 years (95% CI 13-15); the estimated probability of dementia was 27% at 10 years of disease duration, 50% at 15 years, and 74% at 20 years. Results from two large, prospective studies suggest that dementia in PD occurs less frequently, or later in the disease course, than previous research studies have reported.

SVA Regulation of Transposable Element Clustered Transcription within the Major Histocompatibility Complex Genomic Class II Region of the Parkinson's Progression Markers Initiative.

SINE-VNTR-Alu (SVA) retrotransposons can regulate expression quantitative trait loci (eQTL) of coding and noncoding genes including transposable elements (TEs) distributed throughout the human genome. Previously, we reported that expressed SVAs and human leucocyte antigen (HLA) class II genotypes on chromosome 6 were associated significantly with Parkinson's disease (PD). Here, our aim was to follow-up our previous study and evaluate the SVA associations and their regulatory effects on the transcription of TEs within the HLA class II genomic region. We reanalyzed the transcriptome data of peripheral blood cells from the Parkinson's Progression Markers Initiative (PPMI) for 1530 subjects for TE and gene RNAs with publicly available computing packages. Four structurally polymorphic SVAs regulate the transcription of 20 distinct clusters of 235 TE loci represented by LINES (37%), SINES (28%), LTR/ERVs (23%), and ancient transposon DNA elements (12%) that are located in close proximity to HLA genes. The transcribed TEs were mostly short length, with an average size of 389 nucleotides. The numbers, types and profiles of positive and negative regulation of TE transcription varied markedly between the four regulatory SVAs. The expressed SVA and TE RNAs in blood cells appear to be enhancer-like elements that are coordinated differentially in the regulation of HLA class II genes. Future work on the mechanisms underlying their regulation and potential impact is essential for elucidating their roles in normal cellular processes and disease pathogenesis.

Enhancing early Parkinson’s disease detection through multimodal deep learning and explainable AI: insights from the PPMI database

Parkinson’s is the second most common neurodegenerative disease, affecting nearly 8.5M people and steadily increasing. In this research, Multimodal Deep Learning is investigated for the Prodromal stage detection of Parkinson's Disease (PD), combining different 3D architectures with the novel Excitation Network (EN) and supported by Explainable Artificial Intelligence (XAI) techniques. Utilizing data from the Parkinson’s Progression Markers Initiative, this study introduces a joint co-learning approach for multimodal fusion, enabling end-to-end training of deep neural networks and facilitating the learning of complementary information from both imaging and clinical modalities. DenseNet with EN outperformed other models, showing a substantial increase in accuracy when supplemented with clinical data. XAI methods, such as Integrated Gradients for ResNet and DenseNet, and Attention Heatmaps for Vision Transformer (ViT), revealed that DenseNet focused on brain regions believed to be critical to prodromal pathophysiology, including the right temporal and left pre-frontal areas. Similarly, ViT highlighted the lateral ventricles associated with cognitive decline, indicating their potential in the Prodromal stage. These findings underscore the potential of these regions as early-stage PD biomarkers and showcase the proposed framework's efficacy in predicting subtypes of PD and aiding in early diagnosis, paving the way for innovative diagnostic tools and precision medicine.

An efficient ranking-based ensembled multiclassifier for neurodegenerative diseases classification using deep learning.

Neurodegenerative diseases are group of debilitating and progressive disorders that primarily affect the structure and functions of nervous system, leading to gradual loss of neurons and subsequent decline in cognitive, and behavioral activities. The two frequent diseases affecting the world's significant population falling in the above category are Alzheimer's disease (AD) and Parkinson's disease (PD). These disorders substantially impact the quality of life and burden healthcare systems and society. The demographic characteristics, and machine learning approaches have now been employed to diagnose these illnesses; however, they possess accuracy limitations. Therefore, the authors have developed ranking-based ensemble approach based on the weighted strategy of deep learning classifiers. The whole modeling procedure of the proposed approach incorporates three phases. In phase I, preprocessing techniques are applied to clean the noise in datasets to make it standardized according to deep learning models as it significantly impacts their performance. In phase II, five deep learning models are selected for classification and calculation of prediction results. In phase III, a ranking-based ensemble approach is proposed to ensemble the results of the five models after calculating the ranks and weights of them. In addition, the Magnetic Resonance Imaging (MRI) datasets named Alzheimer's Disease Neuroimaging Initiative (ADNI) for AD classification and Parkinson's Progressive Marker Initiative (PPMI) for PD classification are selected to validate the proposed approach. Furthermore, the proposed method achieved the classification accuracy on AD- Cognitive Normals (CN) at 97.89%, AD- Mild Cognitive Impairment (MCI) at 99.33% and CN-MCI at 99.44% and on PD-CN at 99.22%, PD- Scans Without Evidence of Dopaminergic Effect (SWEDD) at 97.56% and CN-SWEDD at 98.22% respectively. Also, the multi-class classification shows the promising accuracy of 97.18% for AD and 97.85% for PD for the proposed framework. The findings of the study show that the proposed deep learning-based ensemble technique is competitive for AD and PD prediction in both multiclass and binary class classification. Furthermore, the proposed approach enhances generalization performance in diagnosing neurodegenerative diseases and performs better than existing approaches.

Socioenvironmental Factors are Associated With Dopamine Transporter Availability in Healthy Individuals but not in Parkinson's Disease.

Social factors can influence the brain's dopaminergic function. This study investigated the relationship between socioenvironmental factors and dopamine transporter (DaT) availability in healthy individuals (n = 74) and those with Parkinson's disease (PD) (n = 240). All single photon emission computed tomography (SPECT) DaT data and clinical data used in this study were obtained from the Parkinson's Progression Markers Initiative (PPMI) dataset. Socioenvironmental data was obtained from Social Explorer analyses of the American Community Survey (2014-2018) using the residential ZIP codes of the subjects available in the PPMI dataset. Participants resided in 302 ZIP code tabulation areas across 38 U.S. states. In healthy individuals, DaT signals were significant and negatively correlated in the caudate with median household income (r = -0.27, P = 0.02) and educational level of the living area (r = -0.23, P = 0.04), but not significant in the putamen (r = -0.21, P = 0.08; r = -0.11, P = 0.37 respectively). Also, there was a significant positive correlation between DaT signals in caudate and poverty rates (r = 0.29, P = 0.01), but not in the putamen (r = 0.16, P = 0.19) in healthy subjects. No significant associations were observed in the PD group for any variables. The study findings suggest that socioenvironmental factors, such as median household income, education level, and poverty rate, are significantly associated with DaT availability in the caudate of healthy individuals but not in those with PD. This indicates that PD might disrupt the connection between the social environment and dopaminergic function. These results underscore the importance of considering socioenvironmental variables when studying dopaminergic function in the human brain.

Multi-modality radiomics of conventional T1 weighted and diffusion tensor imaging for differentiating Parkinson’s disease motor subtypes in early-stages

This study aimed to develop and validate a multi-modality radiomics approach using T1-weighted and diffusion tensor imaging (DTI) to differentiate Parkinson's disease (PD) motor subtypes, specifically tremor-dominant (TD) and postural instability gait difficulty (PIGD), in early disease stages. We analyzed T1-weighted and DTI scans from 140 early-stage PD patients (70 TD, 70 PIGD) and 70 healthy controls from the Parkinson's Progression Markers Initiative database. Radiomics features were extracted from 16 brain regions of interest. After harmonization and feature selection, four machine learning classifiers were trained and evaluated for both three-class (HC vs TD vs PIGD) and binary (TD vs PIGD) classification tasks. The light gradient boosting machine (LGBM) classifier demonstrated the best overall performance. For the three-class classification, LGBM achieved an accuracy of 85% and an area under the receiver operating characteristic curve (AUC) of 0.94 using combined T1 and DTI features. In the binary classification task, LGBM reached an accuracy of 95% and AUC of 0.95. Key discriminative features were identified in the Thalamus, Amygdala, Hippocampus, and Substantia Nigra for the three-group classification, and in the Pallidum, Amygdala, Hippocampus, and Accumbens for binary classification. The combined T1 + DTI approach consistently outperformed single-modality classifications, with DTI alone showing particularly low performance (AUC 0.55–0.62) in binary classification. The high accuracy and AUC values suggest that this approach could significantly improve early diagnosis and subtyping of PD. These findings have important implications for clinical management, potentially enabling more personalized treatment strategies based on early, accurate subtype identification.

Modeling of Parkinson's Disease Progression and Implications for Detection of Disease Modification in Treatment Trials.

Objectively measuring Parkinson's disease (PD) signs and symptoms over time is critical for the successful development of treatments aimed at halting the disease progression of people with PD. To create a clinical trial simulation tool that characterizes the natural history of PD progression and enables a data-driven design of randomized controlled studies testing potential disease-modifying treatments (DMT) in early-stage PD. Data from the Parkinson's Progression Markers Initiative (PPMI) were analyzed with nonlinear mixed-effect modeling techniques to characterize the progression of MDS-UPDRS part I (non-motor aspects of experiences of daily living), part II (motor aspects of experiences of daily living), and part III (motor signs). A clinical trial simulation tool was built from these disease models and used to predict probability of success as a function of trial design. MDS-UPDRS part III progresses approximately 3 times faster than MDS-UPDRS part II and I, with an increase of 3 versus 1 points/year. Higher amounts of symptomatic therapy is associated with slower progression of MDS-UPDRS part II and III. The modeling framework predicts that a DMT effect on MDS-UPDRS part III could precede effect on part II by approximately 2 to 3 years. Our clinical trial simulation tool predicted that in a two-year randomized controlled trial, MDS-UPDRS part III could be used to evaluate a potential novel DMT, while part II would require longer trials of a minimum duration of 3 to 5 years underscoring the need for innovative trial design approaches including novel patient-centric measures.

Rest Tremor in Parkinson's Disease Is Associated with Ipsilateral Striatal Dopamine Transporter Binding.

The cardinal motor symptoms of Parkinson's disease (PD) include rigidity, bradykinesia, and rest tremor. Rigidity and bradykinesia correlate with contralateral nigrostriatal degeneration and striatal dopamine deficit, but association between striatal dopamine function and rest tremor has remained unclear. The aim of this study was to investigate the possible link between dopamine function and rest tremor using Parkinson's Progression Markers Initiative dataset, the largest prospective neuroimaging cohort of patients with PD. Clinical, [123I]N-ω-fluoropropyl-2β-carbomethoxy-3β-(4-iodophenyl)nortropane ([123I]FP-CIT) single photon emission computed tomography (SPECT), and structural magnetic resonance imaging data from 354 early PD patients and 166 healthy controls were included in this study. We employed a novel approach allowing nonlinear registration of individual scans accurately to a standard space and voxelwise analyses of the association between motor symptoms and striatal dopamine transporter (DAT) binding. Severity of both rigidity and bradykinesia was negatively associated with contralateral striatal DAT binding (PFWE < 0.05 [FWE, family-wise error corrected]). However, rest tremor amplitude was positively associated with increased ipsilateral DAT binding (PFWE < 0.05). The association between rest tremor and binding remained the same controlling for Hoehn & Yahr stage, Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS) part III score, bradykinesia-rigidity score, or motor phenotype. The association between rest tremor and binding was independent of bradykinesia-rigidity and replicated using 2-year follow-up data (PFWE < 0.05). In agreement with the existing literature, we did not find a consistent association between rest tremor and contralateral dopamine defect. However, our results demonstrate a link between rest tremor and increased or less decreased ipsilateral DAT binding. Our findings provide novel information about the association between dopaminergic function and parkinsonian rest tremor. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.