Parkinson's Progression Markers Research Articles

Combining convolution neural networks with long‐short term memory layers to predict Parkinson's disease progression

AbstractParkinson's disease (PD) is a neurological condition that occurs in nearly 1% of the world's population. The disease is manifested by a sharp drop in dopamine production, resulting from the death of the related producing cells in an area of the midbrain called the substantia nigra. Early diagnosis and accurate staging of the disease are essential to apply the appropriate therapeutic approaches to slow cognitive and motor decline. At present, there is not a singular blood test or biomarker accessible for diagnosing PD or monitoring the progression of its symptoms. Clinical professionals identify the disease by assessing the symptoms, which, however, may vary from case to case, as well as their progression speed. Magnetic resonance imaging (MRIs) have been used for the past three decades to diagnose and distinguish between PD and other neurological conditions.However, to the best of our knowledge, no neural network models have been designed to identify the disease stage. This paper aims to fill this gap. Using the “Parkinson's Progression Markers Initiative” dataset, which reports the patient's MRI and an indication of the disease stage, we developed a model to identify the level of progression. The images and the associated scores were used for training and assessing different deep learning models. Our analysis distinguished four distinct disease progression levels based on a standard scale (Hoehn and Yah scale). The final architecture consists of the cascading of a 3D‐CNN network, adopted to reduce and extract the spatial characteristics of the MRI for efficient training of the successive LSTM layers, aiming at modeling the temporal dependencies among the data. Before training the model, the patient's MRI is preprocessed to correct acquisition errors by applying image registration techniques, to extract irrelevant content from the image, such as nonbrain tissue (e.g., skull, neck, fat). We also adopted template‐based data augmentation techniques to obtain a balanced dataset about progression classes. Our results show that the proposed 3D‐CNN + LSTM model achieves state‐of‐the‐art results by classifying the elements with 91.90 as macro averaged OVR AUC on four classes.

Novel Variants Linked to the Prodromal Stage of Parkinson's Disease (PD) Patients.

The symptoms of most neurodegenerative diseases, including Parkinson's disease (PD), usually do not occur until substantial neuronal loss occurs. This makes the process of early diagnosis very challenging. Hence, this research used variant call format (VCF) analysis to detect variants and novel genes that could be used as prognostic indicators in the early diagnosis of prodromal PD. Data were obtained from the Parkinson's Progression Markers Initiative (PPMI), and we analyzed prodromal patients with gVCF data collected in the 2021 cohort. A total of 304 participants were included, including 100 healthy controls, 146 prodromal genetic individuals, 21 prodromal hyposmia individuals, and 37 prodromal individuals with RBD. A pipeline was developed to process the samples from gVCF to reach variant annotation and pathway and disease association analysis. Novel variant percentages were detected in the analyzed prodromal subgroups. The prodromal subgroup analysis revealed novel variations of 1.0%, 1.2%, 0.6%, 0.3%, 0.5%, and 0.4% for the genetic male, genetic female, hyposmia male, hyposmia female, RBD male, and RBD female groups, respectively. Interestingly, 12 potentially novel loci (MTF2, PIK3CA, ADD1, SYBU, IRS2, USP8, PIGL, FASN, MYLK2, USP25, EP300, and PPP6R2) that were recently detected in PD patients were detected in the prodromal stage of PD. Genetic biomarkers are crucial for the early detection of Parkinson's disease and its prodromal stage. The novel PD genes detected in prodromal patients could aid in the use of gene biomarkers for early diagnosis of the prodromal stage without relying only on phenotypic traits.

Feature engineering-based analysis of DaTSCAN-SPECT imaging-derived features in the detection of SWEDD and Parkinson's disease

Scans without evidence of dopamine deficit (SWEDD) refer to patients with a normal dopamine transporter scan who have been clinically considered to have Parkinson's disease (PD). To prevent misdiagnosis between SWEDD and PD, it is imperative to identify the manifestations of SWEDD in the early stages. In this experiment, imaging-based striatum binding ratio (SBR) features of four striatum regions are utilized and obtained from the Parkinson's Progression Marker Initiative (PPMI). After that, by implementing feature engineering, six combinational pairs are created by taking two SBR features at a time using a mathematical-based combination (nCr)technique. Then, by evaluating the maximum and minimum values of features of each pair, the six new features are obtained from each combinational pair based on arithmetic operations. Finally, a total of thirty-six new features have been derived by using these existing four SBR features. These derived 36 features are further applied to various supervised and ensemble classifiers of machine learning for three binary classifications (PD vs SWEDD, PD vs healthy, and healthy vs SWEDD). From the consequences, it has been observed that the Naive Bayes classifier performed well across all classification probabilities and among other classifiers. To differentiate SWEDD from PD, the classifier achieved 98.03 % accuracy, 98.85 % recall, 96.29 % precision, 92.96 % Jaccard_score, 96.29 % F1-score, & 99.34 % AUC. Moreover, the comparison has been made between with and without implementing the feature engineering technique for all three classification probabilities for better interpretation. Thus, it is reasonable to hypothesize that the suggested method, which is based on feature engineering, may not only improve performance but also help medical professionals diagnose diseases at early stages.

Comparison between morphometry and radiomics: detecting normal brain aging based on grey matter.

Voxel-based morphometry (VBM), surface-based morphometry (SBM), and radiomics are widely used in the field of neuroimage analysis, while it is still unclear that the performance comparison between traditional morphometry and emerging radiomics methods in diagnosing brain aging. In this study, we aimed to develop a VBM-SBM model and a radiomics model for brain aging based on cognitively normal (CN) individuals and compare their performance to explore both methods' strengths, weaknesses, and relationships. 967 CN participants were included in this study. Subjects were classified into the middle-aged group (n = 302) and the old-aged group (n = 665) according to the age of 66. The data of 360 subjects from the Alzheimer's Disease Neuroimaging Initiative were used for training and internal test of the VBM-SBM and radiomics models, and the data of 607 subjects from the Australian Imaging, Biomarker and Lifestyle, the National Alzheimer's Coordinating Center, and the Parkinson's Progression Markers Initiative databases were used for the external tests. Logistics regression participated in the construction of both models. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were used to evaluate the two model performances. The DeLong test was used to compare the differences in AUCs between models. The Spearman correlation analysis was used to observe the correlations between age, VBM-SBM parameters, and radiomics features. The AUCs of the VBM-SBM model and radiomics model were 0.697 and 0.778 in the training set (p = 0.018), 0.640 and 0.789 in the internal test set (p = 0.007), 0.736 and 0.737 in the AIBL test set (p = 0.972), 0.746 and 0.838 in the NACC test set (p < 0.001), and 0.701 and 0.830 in the PPMI test set (p = 0.036). Weak correlations were observed between VBM-SBM parameters and radiomics features (p < 0.05). The radiomics model achieved better performance than the VBM-SBM model. Radiomics provides a good option for researchers who prioritize performance and generalization, whereas VBM-SBM is more suitable for those who emphasize interpretability and clinical practice.

A decision support system based on recurrent neural networks to predict medication dosage for patients with Parkinson's disease

Using deep learning has demonstrated significant potential in making informed decisions based on clinical evidence. In this study, we deal with optimizing medication and quantitatively present the role of deep learning in predicting the medication dosage for patients with Parkinson's disease (PD). The proposed method is based on recurrent neural networks (RNNs) and tries to predict the dosage of five critical medication types for PD, including levodopa, dopamine agonists, monoamine oxidase-B inhibitors, catechol-O-methyltransferase inhibitors, and amantadine. Recurrent neural networks have memory blocks that retain crucial information from previous patient visits. This feature is helpful for patients with PD, as the neurologist can refer to the patient's previous state and the prescribed medication to make informed decisions. We employed data from the Parkinson's Progression Markers Initiative. The dataset included information on the Unified Parkinson's Disease Rating Scale, Activities of Daily Living, Hoehn and Yahr scale, demographic details, and medication use logs for each patient. We evaluated several models, such as multi-layer perceptron (MLP), Simple-RNN, long short-term memory (LSTM), and gated recurrent units (GRU). Our analysis found that recurrent neural networks (LSTM and GRU) performed the best. More specifically, when using LSTM, we were able to predict levodopa and dopamine agonist dosage with a mean squared error of 0.009 and 0.003, mean absolute error of 0.062 and 0.030, root mean square error of 0.099 and 0.053, and R-squared of 0.514 and 0.711, respectively.

Alterations in Blood Methylome as Potential Epigenetic Biomarker in Sporadic Parkinson's Disease.

To characterize DNA methylation (DNAm) differences between sporadic Parkinson's disease (PD) and healthy control (HC) individuals enrolled in the Parkinson's Progression Markers Initiative (PPMI). Using whole blood, we characterized longitudinal differences in DNAm between sporadic PD patients (n = 196) and HCs (n = 86) enrolled in PPMI. RNA sequencing (RNAseq) was used to conduct gene expression analyses for genes mapped to differentially methylated cytosine-guanine sites (CpGs). At the time of patient enrollment, 5,178 CpGs were differentially methylated (2,683 hypermethylated and 2,495 hypomethylated) in PD compared to HC. Of these, 579 CpGs underwent significant methylation changes over 3 years. Several differentially methylated CpGs were found near the cytochrome P450 family 2 subfamily E member 1 (CYP2E1) gene. Additionally, multiple hypermethylated CpGs were associated with the N-myc downregulated gene family member 4 (NDRG4) gene. RNA-Seq analyses showed 75 differentially expressed genes in PD patients compared to controls. An integrative analysis of both differentially methylated sites and differentially expressed genes revealed 20 genes that exhibited hypomethylation concomitant with overexpression. Additionally, 1 gene, cathepsin H (CTSH), displayed hypermethylation that was associated with its decreased expression. We provide initial evidence of alterations in DNAm in blood of PD patients that may serve as potential epigenetic biomarker of disease. To evaluate the significance of these changes throughout the progression of PD, additional profiling at longer intervals and during the prodromal stages of disease will be necessary. ANN NEUROL 2024;95:1162-1172.

White matter biomarker for predicting de novo Parkinson's disease using tract-based spatial statistics: a machine learning-based model.

Parkinson's disease (PD) is an irreversible, chronic degenerative disease of the central nervous system, potentially associated with cerebral white matter (WM) lesions. Investigating the microstructural alterations within the WM in the early stages of PD can help to identify the disease early and enable intervention to reduce the associated serious threats to health. This study selected 227 cases from the Parkinson's Progression Markers Initiative (PPMI) database, including 152 de novo PD patients and 75 normal controls (NC). Whole-brain voxel analysis of the WM was performed using the tract-based spatial statistics (TBSS) method. The WM regions with statistically significant differences (P<0.05) between the PD and NC groups were identified and used as masks. The mask was applied to each case's fractional anisotropy (FA) image to extract voxel values as feature vectors. Geometric dimensionality reduction was then applied to eliminate redundant values in the feature vectors. Subsequently, the cases were randomly divided into a training group (158 cases, including 103 PD patients and 55 NC) and a test group (69 cases, including 49 PD patients and 20 NC). The least absolute shrinkage and selection operator (LASSO) regression algorithm was employed to extract the minimal set of relevant features, then the random forest (RF) algorithm was utilized for classification using 5-fold cross validation. The resulting model was further integrated with clinical factors to create a comprehensive prediction model. In comparison to the NC group, the FA values in PD patients exhibited a statistically significant decrease (P<0.05), indicating the presence of widespread WM lesions across multiple brain regions. Moreover, the PD prediction model, constructed based on these WM lesion regions, yielded prediction accuracy (ACC) and area under the receiver operating characteristic (ROC) curve (AUC) values of 0.778 and 0.865 in the validation set, and 0.783 and 0.831 in the test set, respectively. Furthermore, the performance of the integrated model showed some improvement, with ACC and AUC values in the test set reaching 0.804 and 0.844, respectively. The quantitative calculation of WM lesion area on FA images using the TBSS method can serve as a neuroimaging biomarker for diagnosing and predicting early PD at the individual level. When integrated with clinical variables, the predictive performance improves.

Regulatory SVA retrotransposons and classical HLA genotyped-transcripts associated with Parkinson's disease.

Parkinson's disease (PD) is a neurodegenerative and polygenic disorder characterised by the progressive loss of neural dopamine and onset of movement disorders. We previously described eight SINE-VNTR-Alu (SVA) retrotransposon-insertion-polymorphisms (RIPs) located and expressed within the Human Leucocyte Antigen (HLA) genomic region of chromosome 6 that modulate the differential co-expression of 71 different genes including the HLA classical class I and class II genes in a Parkinson's Progression Markers Initiative (PPMI) cohort. In the present study, we (1) reanalysed the PPMI genomic and transcriptomic sequencing data obtained from whole blood of 1521 individuals (867 cases and 654 controls) to infer the genotypes of the transcripts expressed by eight classical HLA class I and class II genes as well as DRA and the DRB3/4/5 haplotypes, and (2) examined the statistical differences between three different PD subgroups (cases) and healthy controls (HC) for the HLA and SVA transcribed genotypes and inferred haplotypes. Significant differences for 57 expressed HLA alleles (21 HLA class I and 36 HLA class II alleles) up to the three-field resolution and four of eight expressed SVA were detected at p<0.05 by the Fisher's exact test within one or other of three different PD subgroups (750 individuals with PD, 57 prodromes, 60 individuals who had scans without evidence of dopamine deficits [SWEDD]), when compared against a group of 654 HCs within the PPMI cohort and when not corrected by the Bonferroni test for multiple comparisons. Fourteen of 20 significant alleles were unique to the PD-HC comparison, whereas 31 of the 57 alleles overlapped between two or more different subgroup comparisons. Only the expressed HLA-DRA*01:01:01 and -DQA1*03:01:01 protective alleles (PD v HC), the -DQA1*03:03:01 risk (HC v Prodrome) or protective allele (PD v Prodrome), the -DRA*01:01:02 and -DRB4*01:03:02 risk alleles (SWEDD v HC), and the NR_SVA_381 present genotype (PD v HC) at a 5% homozygous insertion frequency near HLA-DPA1, were significant (Pc<0.1) after Bonferroni corrections. The homologous NR_SVA_381 insertion significantly decreased the transcription levels of HLA-DPA1 and HLA-DPB1 in the PPMI cohort and its presence as a homozygous genotype is a risk factor (Pc=0.012) for PD. The most frequent NR_SVA_381 insertion haplotype in the PPMI cohort was NR_SVA_381/DPA1*02/DPB1*01 (3.7%). Although HLA C*07/B*07/DRB5*01/DRB1*15/DQB1*06 was the most frequent HLA 5-loci phased-haplotype (n, 76) in the PPMI cohort, the NR_SVA_381 insertion was present in only six of them (8%). These data suggest that expressed SVA and HLA gene alleles in circulating white blood cells are coordinated differentially in the regulation of immune responses and the long-term onset and progression of PD, the mechanisms of which have yet to be elucidated.

Interpretable discriminant analysis for functional data supported on random nonlinear domains with an application to Alzheimer's disease.

We introduce a novel framework for the classification of functional data supported on nonlinear, and possibly random, manifold domains. The motivating application is the identification of subjects with Alzheimer's disease from their cortical surface geometry and associated cortical thickness map. The proposed model is based upon a reformulation of the classification problem as a regularized multivariate functional linear regression model. This allows us to adopt a direct approach to the estimation of the most discriminant direction while controlling for its complexity with appropriate differential regularization. Our approach does not require prior estimation of the covariance structure of the functional predictors, which is computationally prohibitive in our application setting. We provide a theoretical analysis of the out-of-sample prediction error of the proposed model and explore the finite sample performance in a simulation setting. We apply the proposed method to a pooled dataset from Alzheimer's Disease Neuroimaging Initiative and Parkinson's Progression Markers Initiative. Through this application, we identify discriminant directions that capture both cortical geometric and thickness predictive features of Alzheimer's disease that are consistent with the existing neuroscience literature.

Optimizing Parkinson's Disease Diagnosis with Multimodal Data Fusion Techniques

Parkinson's disease (PD) is a central nervous system neurodegenerative illness. Its symptoms include poor motor skills, speech, cognition, and memory. The condition is incurable, although evidence shows that early identification and therapy reduce symptoms. A lack of medical facilities and personnel hinders PD identification. PD is a common chronic degenerative neurological dyskinesia that threatens the elderly. Multi-modal data fusion may reveal more about PD pathophysiology. This study aims to contribute to the evaluation of PD by introducing a novel multimodal deep-learning technique for distinguishing individuals with PD from those without PD. This study utilizes resting functional magnetic resonance imaging (rfMRI) and gene data obtained from the Parkinson's Progression Markers Initiative (PPMI) and Alzheimer's Disease Neuroimaging Initiative (ADNI) databases. The primary objective is to predict the specific pathological brain regions and identify the risk genes associated with PD. The authors want to learn more about the genetic components and underlying procedures by analyzing these datasets. Contributing to the development and progression of PD. In this study, we present our findings that demonstrate the superior recital of our proposed multimodal method compared to both unimodal approaches and other existing multimodal methods. Our evaluation is based on an extensive dataset consisting of real patients. Specifically, our proposed method stacked deep learning classifiers (SDLC) achieves an impressive F1-score of 0.99 and an accuracy of 99.4%, surpassing the performance of both unimodal approaches and other multimodal methods. These results highlight the efficiency and potential of our method in enhancing the accuracy and reliability of patient data analysis. In this study, we demonstrate that our proposed method consistently surpasses alternative approaches in terms of performance, as indicated by a higher average increase in F1-score. This finding highlights the advantage of training on multiple modalities, even when a particular modality is absent during inference.

Corpus callosum and cerebellum participate in semantic dysfunction of Parkinson's disease: a diffusion tensor imaging-based cross-sectional study.

Language dysfunction is common in Parkinson's disease (PD) patients, among which, the decline of semantic fluency is usually observed. This study aims to explore the relationship between white matter (WM) alterations and semantic fluency changes in PD patients. 127 PD patients from the Parkinson's Progression Markers Initiative cohort who received diffusion tensor imaging scanning, clinical assessment and semantic fluency test (SFT) were included. Tract-based special statistics, automated fiber quantification, graph-theoretical and network-based analyses were performed to analyze the correlation between WM structural changes, brain network features and semantic fluency in PD patients. Fractional anisotropy of corpus callosum, anterior thalamic radiation, inferior front-occipital fasciculus, and uncinate fasciculus, were positively correlated with SFT scores, while a negative correlation was identified between radial diffusion of the corpus callosum, inferior longitudinal fasciculus, and SFT scores. Automatic fiber quantification identified similar alterations with more details in these WM tracts. Brain network analysis positively correlated SFT scores with nodal efficiency of cerebellar lobule VIII, and nodal local efficiency of cerebellar lobule X. WM integrity and myelin integrity in the corpus callosum and several other language-related WM tracts may influence the semantic function in PD patients. Damage to the cerebellum lobule VIII and lobule X may also be involved in semantic dysfunction in PD patients.

An Examination of Cognitive Heterogeneity in Parkinson Disease: The Dual-Syndrome Hypothesis.

Cognitive impairment is one of the most debilitating nonmotor symptoms in Parkinson disease (PD), and its presentation is heterogeneous. One proposed model to explain cognitive variability in PD is the dual-syndrome hypothesis. This hypothesis delineates two cognitive profiles, a "fronto-striatal" profile and a "posterior cortical" profile according to symptom presentation, associated motor phenotype, and risk for dementia. The current study examined the dual-syndrome hypothesis in individuals with idiopathic PD to evaluate the existence of these profiles, determine the association with the motor phenotype (tremor dominant vs. postural instability/gait disorder), and assess the relative risk for dementia. A retrospective examination was conducted using data from the Parkinson's Progression Markers Initiative database at baseline (within 2 years of diagnosis) and 5 years after baseline. Descriptive categorizations, cluster analyses, generalized linear mixed models, and logistic regressions were used to address the research questions. There was emerging evidence of cognitive profiles; however, these were not fully supported by cluster analyses. Baseline cognitive profile was associated with later motor phenotype, and as predicted, dementia risk was greatest in persons with baseline posterior cortical impairments. The current results provide mixed support for the dual-syndrome hypothesis, with some evidence that the posterior cortical cognitive profile is associated with postural instability and gait disorder as well as greater dementia risk.

Predictors for early-onset psychotic symptoms in patients newly diagnosed with Parkinson's disease without psychosis at baseline: A 5-year cohort study.

To investigate the risk factors for early-onset psychosis in Parkinson's disease (PD) in a cohort of patients from the Parkinson's Progression Markers Initiative. Longitudinal data on motor and non-motor features, dopamine transporter (DAT) imaging, and cerebrospinal fluid (CSF) measurements were collected. The survival probability of psychotic symptoms, potential risk factors for psychosis development over a 5-year follow-up period, and the performance of the prediction model were evaluated. Among the 338 newly diagnosed patients with PD, 83 developed psychotic symptoms. Gastrointestinal autonomic dysfunction, presence of probable rapid-eye-movement sleep behavior disorder, and the ratio Aβ42: total-tau could independently predict onset of psychosis in PD (hazard ratio (HR) = 1.157, 95% confidence interval (CI) 1.022-1.309, p = 0.021, HR = 2.596, 95% CI 1.287-5.237, p = 0.008, and HR = 0.842, 95% CI 0.723-0.980, p = 0.027, respectively). The combined model integrating baseline clinical predictors, DAT imaging, and CSF measurements achieved better sensitivity than the clinical predictors alone (area under the curve = 0.770 [95% CI 0.672-0.868] vs. 0.714 [95% CI 0.625-0.802], p = 0.098). We identified clinical and CSF predictors of early-onset psychosis in patients with PD. Our study provides evidence and implications for prognostic stratification and therapeutic approaches for PD psychosis.

Association between body mass index and glymphatic function using diffusion tensor image-along the perivascular space (DTI-ALPS) in patients with Parkinson's disease.

Obesity is considered a risk factor for the development of several neurodegenerative diseases, including Parkinson's disease (PD). Recent studies have revealed that glymphatic function is compromised in PD patients. This study aims to investigate the impact of different body mass index (BMI) statuses on glymphatic system function in PD patients using the diffusion tensor image analysis along the perivascular space (DTI-ALPS) method. This study used a cross-sectional study design. A total of 145 PD patients were retrospectively enrolled in Parkinson's Progression Markers Initiative (PPMI) from 2010-2013. Eligibility criteria included diagnosis of PD based on PPMI criteria. Diffusion tensor image (DTI) scans (diffusion gradient =64, b-value =1,000 s/mm2, slice thickness =2 mm) were acquired, and the analysis along the perivascular space (ALPS) index of each subject was calculated. The patient cohort was categorized into three groups based on BMI: normal weight (N=49), overweight (N=69), and obese (N=27). The difference in ALPS index among groups was performed by one-way analysis of variance (ANOVA). Partial correlation analysis was used to observe the relationship between ALPS index, BMI status, and demographics. Spearman's rank correlation coefficient and multivariable linear regression analyses were used to identify factors associated with ALPS index. PD patients with higher BMI exhibited a reduced ALPS index (normal weight > overweight > obese), and the ALPS index for patients with obesity was statistically significantly lower than that for patients with normal weight (P<0.001). After adjusting for age, sex, years of education, handedness, and disease duration, a significant negative correlation between the ALPS index and BMI was observed in the PD patients (R=-0.275, P<0.001). Furthermore, a negative correlation between the ALPS index and the severity of motor symptoms was identified in the subgroup of overweight (R=-0.318, P=0.01), rather than in the normal weight and obese groups. High BMI has a negative impact on the glymphatic function in PD patients, suggesting that weight control may have clinical relevance in the management of PD patients.

Associations of Multimorbidity with Cerebrospinal Fluid Biomarkers for Neurodegenerative Disorders in Early Parkinson's Disease: A Crosssectional and Longitudinal Study.

The study aims to determine whether multimorbidity status is associated with cerebrospinal fluid (CSF) biomarkers for neurodegenerative disorders. A total of 827 patients were enrolled from the Parkinson's Progression Markers Initiative (PPMI) database, including 638 patients with early-stage Parkinson's disease (PD) and 189 healthy controls (HCs). Multimorbidity status was evaluated based on the count of long-term conditions (LTCs) and the multimorbidity pattern. Using linear regression models, cross-sectional and longitudinal analyses were conducted to assess the associations of multimorbidity status with CSF biomarkers for neurodegenerative disorders, including α-synuclein (αSyn), amyloid-β42 (Aβ42), total tau (t-tau), phosphorylated tau (p-tau), glial fibrillary acidic protein (GFAP), and neurofilament light chain protein (NfL). At baseline, the CSF t-tau (p = 0.010), p-tau (p = 0.034), and NfL (p = 0.049) levels showed significant differences across the three categories of LTC counts. In the longitudinal analysis, the presence of LTCs was associated with lower Aβ42 (β < -0.001, p = 0.020), and higher t-tau (β = 0.007, p = 0.026), GFAP (β = 0.013, p = 0.022) and NfL (β = 0.020, p = 0.012); Participants with tumor/musculoskeletal/mental disorders showed higher CSF levels of t-tau (β = 0.016, p = 0.011) and p-tau (β = 0.032, p = 0.044) than those without multimorbidity. Multimorbidity, especially severe multimorbidity and the pattern of mental/musculoskeletal/ tumor disorders, was associated with CSF biomarkers for neurodegenerative disorders in early-stage PD patients, suggesting that multimorbidity might play a crucial role in aggravating neuronal damage in neurodegenerative diseases.

Evaluation of ATNPD Framework and Biofluid Markers to Predict Cognitive Decline in Early Parkinson Disease.

In Parkinson disease (PD), Alzheimer disease (AD) copathology is common and clinically relevant. However, the longitudinal progression of AD CSF biomarkers-β-amyloid 1-42 (Aβ42), phosphorylated tau 181 (p-tau181), and total tau (t-tau)-in PD is poorly understood and may be distinct from clinical AD. Moreover, it is unclear whether CSF p-tau181 and serum neurofilament light (NfL) have added prognostic utility in PD, when combined with CSF Aβ42. First, we describe longitudinal trajectories of biofluid markers in PD. Second, we modified the AD β-amyloid/tau/neurodegeneration (ATN) framework for application in PD (ATNPD) using CSF Aβ42 (A), p-tau181 (T), and serum NfL (N) and tested ATNPD prediction of longitudinal cognitive decline in PD. Participants were selected from the Parkinson's Progression Markers Initiative cohort, clinically diagnosed with sporadic PD or as controls, and followed up annually for 5 years. Linear mixed-effects models (LMEMs) tested the interaction of diagnosis with longitudinal trajectories of analytes (log transformed, false discovery rate [FDR] corrected). In patients with PD, LMEMs tested how baseline ATNPD status (AD [A+T+N±] vs not) predicted clinical outcomes, including Montreal Cognitive Assessment (MoCA; rank transformed, FDR corrected). Participants were 364 patients with PD and 168 controls, with comparable baseline mean (±SD) age (patients with PD = 62 ± 10 years; controls = 61 ± 11 years]; Mann-Whitney Wilcoxon: p = 0.4) and sex distribution (patients with PD = 231 male individuals [63%]; controls = 107 male individuals [64%]; χ2: p = 1). Patients with PD had overall lower CSF p-tau181 (β = -0.16, 95% CI -0.23 to -0.092, p = 2.2e-05) and t-tau than controls (β = -0.13, 95% CI -0.19 to -0.065, p = 4e-04), but not Aβ42 (p = 0.061) or NfL (p = 0.32). Over time, patients with PD had greater increases in serum NfL than controls (β = 0.035, 95% CI 0.022 to 0.048, p = 9.8e-07); slopes of patients with PD did not differ from those of controls for CSF Aβ42 (p = 0.18), p-tau181 (p = 1), or t-tau (p = 0.96). Using ATNPD, PD classified as A+T+N± (n = 32; 9%) had worse cognitive decline on global MoCA (β = -73, 95% CI -110 to -37, p = 0.00077) than all other ATNPD statuses including A+ alone (A+T-N-; n = 75; 21%). In patients with early PD, CSF p-tau181 and t-tau were low compared with those in controls and did not increase over 5 years of follow-up. Our study shows that classification using modified ATNPD (incorporating CSF Aβ42, CSF p-tau181, and serum NfL) can identify biologically relevant subgroups of PD to improve prediction of cognitive decline in early PD.

Data-driven disease progression model of Parkinson's disease and effect of sex and genetic variants.

As Parkinson's disease (PD) progresses, there are multiple biomarker changes, and sex and genetic variants may influence the rate of progression. Data-driven, long-term disease progression model analysis may provide precise knowledge of the relationships between these risk factors and progression and would allow for the selection of appropriate diagnosis and treatment according to disease progression. To construct a long-term disease progression model of PD based on multiple biomarkers and evaluate the effects of sex and leucine-rich repeat kinase 2 (LRRK2) mutations, a technique derived from the nonlinear mixed-effects model (Statistical Restoration of Fragmented Time course [SReFT]) was applied to datasets of patients provided by the Parkinson's Progression Markers Initiative. Four biomarkers, including the Unified PD Rating Scale, were used, and a covariate analysis was performed to investigate the effects of sex and LRRK2-related mutations. A model of disease progression over ~30 years was successfully developed using patient data with a median of 6 years. Covariate analysis suggested that female sex and LRRK2 G2019S mutations were associated with 21.6% and 25.4% significantly slower progression, respectively. LRRK2 rs76904798 mutation also tended to delay disease progression by 10.4% but the difference was not significant. In conclusion, a long-term PD progression model was successfully constructed using SReFT from relatively short-term individual patient observations and depicted nonlinear changes in relevant biomarkers and their covariates, including sex and genetic variants.

Association of Family History and Polygenic Risk Score With Longitudinal Prognosis in Parkinson Disease.

Evidence suggests that either family history or polygenic risk score (PRS) is associated with developing Parkinson disease (PD). However, little is known about the longitudinal prognosis of PD according to family history and higher PRS. From the Parkinson's Progression Markers Initiative database, 395 patients with PD who followed up for more than 2 years were grouped into those with family history within first-degree, second-degree, and third-degree relatives (N = 127 [32.2%]) vs those without (N = 268 [67.8%]). The PRS of 386 patients was computed using whole-genome sequencing data. Longitudinal assessment of motor, cognition, and imaging based on dopaminergic degeneration was conducted during the regular follow-up period. Effects of family history, PRS, or both on longitudinal changes of cognition, motor severity, and nigrostriatal degeneration were tested using a linear mixed model. The risk of freezing of gait (FOG) according to family history was assessed using the Kaplan-Meier analysis and Cox regression models. During a median follow-up of 9.1 years, PD with positive family history showed a slower decline of caudate dopamine transporter uptake (β estimate of family history × time = 0.02, 95% CI = 0.002-0.036, p = 0.027). Family history of PD and higher PRS were independently associated with a slower decline of Montreal Cognitive Assessment (β estimate of family history × time = 0.12, 95% CI = 0.02-0.22, p = 0.017; β estimate of PRS × time = 0.09, 95% CI = 0.03-0.16, p = 0.006). In those 364 patients without FOG at baseline, PD with positive family history had a lower risk of FOG (hazard ratio of family history = 0.57, 95% CI = 0.38-0.84, p = 0.005). Having a family history of PD predicts slower progression of cognitive decline and caudate dopaminergic degeneration, and less FOG compared with those without a family history independent of PRS. Taken together, information on family history could be used as a proxy for the clinical heterogeneity of PD. The study was registered at clinicaltrials.gov (NCT01141023), and the enrollment began June 1, 2010.

Longitudinal brain structure changes in Parkinson's disease: A replication study.

An existing major challenge in Parkinson's disease (PD) research is the identification of biomarkers of disease progression. While magnetic resonance imaging is a potential source of PD biomarkers, none of the magnetic resonance imaging measures of PD are robust enough to warrant their adoption in clinical research. This study is part of a project that aims to replicate 11 PD studies reviewed in a recent survey (JAMA neurology, 78(10) 2021) to investigate the robustness of PD neuroimaging findings to data and analytical variations. This study attempts to replicate the results in Hanganu et al. (Brain, 137(4) 2014) using data from the Parkinson's Progression Markers Initiative (PPMI). Using 25 PD subjects and 18 healthy controls, we analyzed the rate of change of cortical thickness and of the volume of subcortical structures, and we measured the relationship between structural changes and cognitive decline. We compared our findings to the results in the original study. (1) Similarly to the original study, PD patients with mild cognitive impairment (MCI) exhibited increased cortical thinning over time compared to patients without MCI in the right middle temporal gyrus, insula, and precuneus. (2) The rate of cortical thinning in the left inferior temporal and precentral gyri in PD patients correlated with the change in cognitive performance. (3) There were no group differences in the change of subcortical volumes. (4) We did not find a relationship between the change in subcortical volumes and the change in cognitive performance. Despite important differences in the dataset used in this replication study, and despite differences in sample size, we were able to partially replicate the original results. We produced a publicly available reproducible notebook allowing researchers to further investigate the reproducibility of the results in Hanganu et al. (2014) when more data is added to PPMI.

Personalized Prediction of Parkinson's Disease Progression Based on Deep Gaussian Processes.

Parkinson's disease is a chronic progressive neurodegenerative disease with highly heterogeneous symptoms and progression. It is helpful for patient management to establish a personalized model that integrates heterogeneous interpretation methods to predict disease progression. In the study, we propose a novel approach based on a multi-task learning framework to divide Parkinson's disease progression modeling into an unsupervised clustering task and a disease progression prediction task. On the one hand, the method can cluster patients with different progression trajectories and discover new progression patterns of Parkinson's disease. On the other hand, the discovery of new progression patterns helps to predict the future progression of Parkinson's disease markers more accurately through parameter sharing among multiple tasks. We discovered three different Parkinson's disease progression patterns and achieved better prediction performance (MAE=5.015, RMSE=7.284, r2=0.727) than previously proposed methods on Parkinson's Progression Markers Initiative datasets, which is a longitudinal cohort study with newly diagnosed Parkinson's disease.