Machine learning-based prediction of cognitive outcomes in de novo Parkinson's disease.
Ontology highlight
ABSTRACT:
SUBMITTER: Harvey J
PROVIDER: S-EPMC9640625 | biostudies-literature | 2022 Nov
REPOSITORIES: biostudies-literature
Publications
Machine learning-based prediction of cognitive outcomes in de novo Parkinson's disease.
Harvey Joshua J Reijnders Rick A RA Cavill Rachel R Duits Annelien A Köhler Sebastian S Eijssen Lars L Rutten Bart P F BPF Shireby Gemma G Torkamani Ali A Creese Byron B Leentjens Albert F G AFG Lunnon Katie K Pishva Ehsan E
NPJ Parkinson's disease 20221107 1
Cognitive impairment is a debilitating symptom in Parkinson's disease (PD). We aimed to establish an accurate multivariate machine learning (ML) model to predict cognitive outcome in newly diagnosed PD cases from the Parkinson's Progression Markers Initiative (PPMI). Annual cognitive assessments over an 8-year time span were used to define two cognitive outcomes of (i) cognitive impairment, and (ii) dementia conversion. Selected baseline variables were organized into three subsets of clinical, b ...[more]
Similar Datasets
Project description:BackgroundParkinson'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.MethodsThis 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.ResultsIn 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.ConclusionsThe 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.
| S-EPMC11007501 | biostudies-literature
Project description:Patients with Parkinson's Disease (PD) often suffer from cognitive decline. Accurate prediction of cognitive decline is essential for early treatment of at-risk patients. The aim of this study was to develop and evaluate a multimodal machine learning model for the prediction of continuous cognitive decline in patients with early PD. We included 213 PD patients from the Parkinson's Progression Markers Initiative (PPMI) database. Machine learning was used to predict change in Montreal Cognitive Assessment (MoCA) score using the difference between baseline and 4-years follow-up data as outcome. Input features were categorized into four sets: clinical test scores, cerebrospinal fluid (CSF) biomarkers, brain volumes, and genetic variants. All combinations of input feature sets were added to a basic model, which consisted of demographics and baseline cognition. An iterative scheme using RReliefF-based feature ranking and support vector regression in combination with tenfold cross validation was used to determine the optimal number of predictive features and to evaluate model performance for each combination of input feature sets. Our best performing model consisted of a combination of the basic model, clinical test scores and CSF-based biomarkers. This model had 12 features, which included baseline cognition, CSF phosphorylated tau, CSF total tau, CSF amyloid-beta1-42, geriatric depression scale (GDS) scores, and anxiety scores. Interestingly, many of the predictive features in our model have previously been associated with Alzheimer's disease, showing the importance of assessing Alzheimer's disease pathology in patients with Parkinson's disease.
| S-EPMC10425414 | biostudies-literature
Project description:ObjectiveTo evaluate the sex differences in cognitive course over 4 years in Parkinson's disease (PD) patients with and without mild cognitive impairment (MCI) compared to controls.MethodsFour-year longitudinal cognitive scores of 257 cognitively intact PD, 167 PD-MCI, and 140 controls from the Parkinson's Progression Markers Initiative were included. Longitudinal scores of men and women, and PD with and without MCI were compared.ResultsWomen had better verbal memory, men had better visuospatial function. There was no interaction between sex, diagnostic group, and/or time (4-year follow-up period).ConclusionsSex differences in cognitive course in de novo PD are similar to healthy aging. Cognitive decline rates in PD with and without MCI are similar for the first 4 years of PD.
| S-EPMC7282562 | biostudies-literature
Project description:The detection of Parkinson's disease (PD) in its early stages is of great importance for its treatment and management, but consensus is lacking on what information is necessary and what models should be used to best predict PD risk. In our study, we first grouped PD-associated factors based on their cost and accessibility, and then gradually incorporated them into risk predictions, which were built using eight commonly used machine learning models to allow for comprehensive assessment. Finally, the Shapley Additive Explanations (SHAP) method was used to investigate the contributions of each factor. We found that models built with demographic variables, hospital admission examinations, clinical assessment, and polygenic risk score achieved the best prediction performance, and the inclusion of invasive biomarkers could not further enhance its accuracy. Among the eight machine learning models considered, penalized logistic regression and XGBoost were the most accurate algorithms for assessing PD risk, with penalized logistic regression achieving an area under the curve of 0.94 and a Brier score of 0.08. Olfactory function and polygenic risk scores were the most important predictors for PD risk. Our research has offered a practical framework for PD risk assessment, where necessary information and efficient machine learning tools were highlighted.
| S-EPMC10741603 | biostudies-literature
Project description:Although many studies have been conducted on machine learning (ML) models for Parkinson's disease (PD) prediction using neuroimaging and movement analyses, studies with large population-based datasets are limited. We aimed to propose PD prediction models using ML algorithms based on the National Health Insurance Service-Health Screening datasets. We selected individuals who participated in national health-screening programs > 5 times between 2002 and 2015. PD was defined based on the ICD-code (G20), and a matched cohort of individuals without PD was selected using a 1:1 random sampling method. Various ML algorithms were applied for PD prediction, and the performance of the prediction models was compared. Neural networks, gradient boosting machines, and random forest algorithms exhibited the best average prediction accuracy (average area under the receiver operating characteristic curve (AUC): 0.779, 0.766, and 0.731, respectively) among the algorithms validated in this study. The overall model performance metrics were higher in men than in women (AUC: 0.742 and 0.729, respectively). The most important factor for predicting PD occurrence was body mass index, followed by total cholesterol, glucose, hemoglobin, and blood pressure levels. Smoking and alcohol consumption (in men) and socioeconomic status, physical activity, and diabetes mellitus (in women) were highly correlated with the occurrence of PD. The proposed health-screening dataset-based PD prediction model using ML algorithms is readily applicable, produces validated results, and could be a useful option for PD prediction models.
| S-EPMC9663430 | biostudies-literature
Project description:In this study, we apply a multidisciplinary approach to investigate falls in PD patients using clinical, demographic and neuroimaging data from two independent initiatives (University of Michigan and Tel Aviv Sourasky Medical Center). Using machine learning techniques, we construct predictive models to discriminate fallers and non-fallers. Through controlled feature selection, we identified the most salient predictors of patient falls including gait speed, Hoehn and Yahr stage, postural instability and gait difficulty-related measurements. The model-based and model-free analytical methods we employed included logistic regression, random forests, support vector machines, and XGboost. The reliability of the forecasts was assessed by internal statistical (5-fold) cross validation as well as by external out-of-bag validation. Four specific challenges were addressed in the study: Challenge 1, develop a protocol for harmonizing and aggregating complex, multisource, and multi-site Parkinson's disease data; Challenge 2, identify salient predictive features associated with specific clinical traits, e.g., patient falls; Challenge 3, forecast patient falls and evaluate the classification performance; and Challenge 4, predict tremor dominance (TD) vs. posture instability and gait difficulty (PIGD). Our findings suggest that, compared to other approaches, model-free machine learning based techniques provide a more reliable clinical outcome forecasting of falls in Parkinson's patients, for example, with a classification accuracy of about 70-80%.
| S-EPMC5940671 | biostudies-literature
Project description:BackgroundAltered cholinergic innervation plays a putative role in cognitive impairment in Parkinson's disease (PD) at least in advanced stages. Identification of the relationship between cognitive impairment and cholinergic innervation early in the disease will provide better insight into disease prognosis and possible early intervention.ObjectiveThe aim was to assess regional cholinergic innervation status in de novo patients with PD, with and without cognitive impairment.MethodsFifty-seven newly diagnosed, treatment-naive, PD patients (32 men, mean age 64.6 ± 8.2 years) and 10 healthy controls (5 men, mean age 54.6 ± 6.0 years) were included. All participants underwent cholinergic [18 F]fluoroethoxybenzovesamicol positron emission tomography and detailed neuropsychological assessment. PD patients were classified as either cognitively normal (PD-NC) or mild cognitive impairment (PD-MCI). Whole brain voxel-based group comparisons were performed.ResultsResults show bidirectional cholinergic innervation changes in PD. Both PD-NC and PD-MCI groups showed significant cortical cholinergic denervation compared to controls (P < 0.05, false discovery rate corrected), primarily in the posterior cortical regions. Higher-than-normal binding was most prominent in PD-NC in both cortical and subcortical regions, including the cerebellum, cingulate cortex, putamen, gyrus rectus, hippocampus, and amygdala.ConclusionAltered cholinergic innervation is already present in de novo patients with PD. Posterior cortical cholinergic losses were present in all patients independent of cognitive status. Higher-than-normal binding in cerebellar, frontal, and subcortical regions in cognitively intact patients may reflect compensatory cholinergic upregulation in early-stage PD. Limited or failing cholinergic upregulation may play an important role in early, clinically evident cognitive impairment in PD. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
| S-EPMC9306739 | biostudies-literature
Project description:BackgroundClinical markers of cognitive decline in Parkinson's disease (PD) encompass several mental non-motor symptoms such as hallucinations, apathy, anxiety, and depression. Furthermore, freezing of gait (FOG) and specific gait alterations have been associated with cognitive dysfunction in PD. Finally, although low cerebrospinal fluid levels of amyloid-β42 have been found to predict cognitive decline in PD, hitherto PET imaging of amyloid-β (Aβ) failed to consistently demonstrate the association between Aβ plaques deposition and mild cognitive impairment in PD (PD-MCI).AimFinding significant features associated with PD-MCI through a machine learning approach.Patients and methodsPatients were assessed with an extensive clinical and neuropsychological examination. Clinical evaluation included the assessment of mental non-motor symptoms and FOG using the specific items of the MDS-UPDRS I and II. Based on the neuropsychological examination, patients were classified as subjects without and with MCI (noPD-MCI, PD-MCI). All patients were evaluated using a motion analysis system. A subgroup of PD patients also underwent amyloid PET imaging. PD-MCI and noPD-MCI subjects were compared with a univariate statistical analysis on demographic data, clinical features, gait analysis variables, and amyloid PET data. Then, machine learning analysis was performed two times: Model 1 was implemented with age, clinical variables (hallucinations/psychosis, depression, anxiety, apathy, sleep problems, FOG), and gait features, while Model 2, including only the subgroup performing PET, was implemented with PET variables combined with the top five features of the former model.ResultsSeventy-five PD patients were enrolled (33 PD-MCI and 42 noPD-MCI). PD-MCI vs. noPD-MCI resulted in older and showed worse gait patterns, mainly characterized by increased dynamic instability and reduced step length; when comparing amyloid PET data, the two groups did not differ. Regarding the machine learning analyses, evaluation metrics were satisfactory for Model 1 overcoming 80% for accuracy and specificity, whereas they were disappointing for Model 2.ConclusionsThis study demonstrates that machine learning implemented with specific clinical features and gait variables exhibits high accuracy in predicting PD-MCI, whereas amyloid PET imaging is not able to increase prediction. Additionally, our results prompt that a data mining approach on certain gait parameters might represent a reliable surrogate biomarker of PD-MCI.
| S-EPMC9714435 | biostudies-literature
Project description:BackgroundThe role of the lipidome as a biomarker for Parkinson's disease (PD) is a relatively new field that currently only focuses on PD diagnosis.ObjectiveTo identify a relevant lipidome signature for PD severity markers.MethodsDisease severity of 149 PD patients was assessed by the Unified Parkinson's Disease Rating Scale (UPDRS) and the Montreal Cognitive Assessment (MoCA). The lipid composition of whole blood samples was analyzed, consisting of 517 lipid species from 37 classes; these included all major classes of glycerophospholipids, sphingolipids, glycerolipids, and sterols. To handle the high number of lipids, the selection of lipid species and classes was consolidated via analysis of interrelations between lipidomics and disease severity prediction using the random forest machine-learning algorithm aided by conventional statistical methods.ResultsSpecific lipid classes dihydrosphingomyelin (dhSM), plasmalogen phosphatidylethanolamine (PEp), glucosylceramide (GlcCer), dihydro globotriaosylceramide (dhGB3), and to a lesser degree dihydro GM3 ganglioside (dhGM3), as well as species dhSM(20:0), PEp(38:6), PEp(42:7), GlcCer(16:0), GlcCer(24:1), dhGM3(22:0), dhGM3(16:0), and dhGB3(16:0) contribute to PD severity prediction of UPDRS III score. These, together with age, age at onset, and disease duration, also contribute to prediction of UPDRS total score. We demonstrate that certain lipid classes and species interrelate differently with the degree of severity of motor symptoms between men and women, and that predicting intermediate disease stages is more accurate than predicting less or more severe stages.ConclusionUsing machine-learning algorithms and methodologies, we identified lipid signatures that enable prediction of motor severity in PD. Future studies should focus on identifying the biological mechanisms linking GlcCer, dhGB3, dhSM, and PEp with PD severity.
| S-EPMC8355022 | biostudies-literature
Project description:Previous research investigating motor sequence learning (MSL) and consolidation in patients with Parkinson's disease (PD) has predominantly included heterogeneous participant samples with early and advanced disease stages; thus, little is known about the onset of potential behavioral impairments. We employed a multisession MSL paradigm to investigate whether behavioral deficits in learning and consolidation appear immediately after or prior to the detection of clinical symptoms in the tested (left) hand. Specifically, our patient sample was limited to recently diagnosed patients with pure unilateral PD. The left hand symptomatic (LH-S) patients provided an assessment of performance following the onset of clinical symptoms in the tested hand. Conversely, right hand affected (left hand asymptomatic, LH-A) patients served to investigate whether MSL impairments appear before symptoms in the tested hand. LH-S patients demonstrated impaired learning during the initial training session and both LH-S and LH-A patients demonstrated decreased performance compared to controls during the next-day retest. Critically, the impairments in later learning stages in the LH-A patients were evident even before the appearance of traditional clinical symptoms in the tested hand. Results may be explained by the progression of disease-related alterations in relevant corticostriatal networks.
| S-EPMC4519305 | biostudies-literature