Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease

Abstract 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 predicti...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chao Gao, Hanbo Sun, Tuo Wang, Ming Tang, Nicolaas I. Bohnen, Martijn L. T. M. Müller, Talia Herman, Nir Giladi, Alexandr Kalinin, Cathie Spino, William Dauer, Jeffrey M. Hausdorff, Ivo D. Dinov
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f3f7a8e86fd34267bf9c85a913def857
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f3f7a8e86fd34267bf9c85a913def857
record_format	dspace
spelling	oai:doaj.org-article:f3f7a8e86fd34267bf9c85a913def8572021-12-02T12:32:47ZModel-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease10.1038/s41598-018-24783-42045-2322https://doaj.org/article/f3f7a8e86fd34267bf9c85a913def8572018-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-24783-4https://doaj.org/toc/2045-2322Abstract 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%.Chao GaoHanbo SunTuo WangMing TangNicolaas I. BohnenMartijn L. T. M. MüllerTalia HermanNir GiladiAlexandr KalininCathie SpinoWilliam DauerJeffrey M. HausdorffIvo D. DinovNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-21 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Chao Gao Hanbo Sun Tuo Wang Ming Tang Nicolaas I. Bohnen Martijn L. T. M. Müller Talia Herman Nir Giladi Alexandr Kalinin Cathie Spino William Dauer Jeffrey M. Hausdorff Ivo D. Dinov Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease
description	Abstract 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%.
format	article
author	Chao Gao Hanbo Sun Tuo Wang Ming Tang Nicolaas I. Bohnen Martijn L. T. M. Müller Talia Herman Nir Giladi Alexandr Kalinin Cathie Spino William Dauer Jeffrey M. Hausdorff Ivo D. Dinov
author_facet	Chao Gao Hanbo Sun Tuo Wang Ming Tang Nicolaas I. Bohnen Martijn L. T. M. Müller Talia Herman Nir Giladi Alexandr Kalinin Cathie Spino William Dauer Jeffrey M. Hausdorff Ivo D. Dinov
author_sort	Chao Gao
title	Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease
title_short	Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease
title_full	Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease
title_fullStr	Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease
title_full_unstemmed	Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease
title_sort	model-based and model-free machine learning techniques for diagnostic prediction and classification of clinical outcomes in parkinson’s disease
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/f3f7a8e86fd34267bf9c85a913def857
work_keys_str_mv	AT chaogao modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT hanbosun modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT tuowang modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT mingtang modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT nicolaasibohnen modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT martijnltmmuller modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT taliaherman modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT nirgiladi modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT alexandrkalinin modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT cathiespino modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT williamdauer modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT jeffreymhausdorff modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease AT ivoddinov modelbasedandmodelfreemachinelearningtechniquesfordiagnosticpredictionandclassificationofclinicaloutcomesinparkinsonsdisease
_version_	1718394014869225472

Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease

Ejemplares similares