[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126447-en":3,"doc-seo-126447-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126447,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Predicting Parkinson’s Disease Progression - Analyzing Prodromal Stages Through Machine Learning","The study investigates prodromal Parkinson’s Disease (PD) using data from the Parkinson’s Progression Markers Initiative (PPMI), aiming to distinguish prodromals who phenoconverted to PD within 7 years from those who did not. Feature selection identifies key predictors from first-visit information spanning demographic, clinical, and structural MRI measures. Seven machine learning models are evaluated; Support Vector Machine (balanced) works best for demographic and clinical data, while Logistic Regression (balanced) improves performance when MRI thicknesses and volumes are included (AUC ROC 0.84). Predictors include olfactory dysfunction, motor symptoms, psychomotor speed, and third ventricle dilation.","Martinez-Eguiluz, M. et al. (2024). Predicting Parkinson’s Disease Progression: Analyzing Prodromal Stages Through Machine Learning. In: Alonso-Betanzos, A., et al. Advances in Artificial Intelligence. CAEPIA 2024. Lecture Notes in Computer Science, vol 14640. Springer, Cham. This version of the paper has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: [https://doi.org/10.1007/978-3-031-62799-6_7](https://doi.org/10.1007/978-3-031-62799-6_7)  \nPredicting Parkinson’s Disease Progression: Analyzing Prodromal Stages through Machine  \nLearning  \nMaitane Martinez-Eguiluz 1[0000−0001−8608−9170], Javier  \nMuguerza 1[0000−0002−7026−7371], Olatz Arbelaitz 1[0000−0001−7371−2971], Ibai  \nGurrutxaga 1[0000−0003−1830−1058], Juan Carlos  \nGomez-Esteban2 ,3 ,4[0000−0002−4697−3890], Ane  \nMurueta-Goyena2 ,3[0000−0002−9808−6943], and I˜nigo  \nGabilondo3 ,4 ,5[0000−0001−6045−2840]  \n1 Department of Computer Architecture and Technology, University of the Basque  \nCountry, UPV/EHU, Donostia, Spain  \n{maitane.martineze,j.muguerza,olatz.arbelaitz,[i.gurrutxaga](i.gurrutxaga}@ehu.eus)[}](i.gurrutxaga}@ehu.eus)[@ehu.eus](i.gurrutxaga}@ehu.eus)  \n2 Department of Neurosciences, University of the Basque Country, UPV/EHU, Leioa,  \nSpain [ane.muruetagoyena@ehu.eus](ane.muruetagoyena@ehu.eus)  \n3 Neurodegenerative Diseases group, Biobizkaia Health Research Institute,  \nBarakaldo, Spain  \n4 Department of Neurology, Cruces University Hospital, Barakaldo, Spain  \n{juancarlos.gomezesteban, i~[nigo.gabilondocuellar](nigo.gabilondocuellar}@osakidetza.eus)[}](nigo.gabilondocuellar}@osakidetza.eus)[@osakidetza.eus](nigo.gabilondocuellar}@osakidetza.eus)  \n5 Ikerbasque Basque Foundation of Science, Bilbao, Spain  \nAbstract. This study explores prodromal Parkinson’s Disease (PD)  \nby leveraging data from the Parkinson’s Progression Markers Initiative  \n(PPMI) . The main goal was to discriminate between prodromals that  \nphenoconverted to PD in 7 years to those that did not. Through feature  \nselection, the system identified key first visit predictors of PD pheno  \nconversion, encompassing demographic, clinical, and structural magnetic  \nresonance imaging (MRI) data. Employing seven machine learning algo  \nrithms in standard and balanced forms, we find Support Vector Machine  \n(balanced) as most effective for demographic and clinical data, and Logis  \ntic Regression (balanced) when adding thicknesses and volumes of MRI  \ndata. The metrics were improve in the second case (AUC ROC of 0.84) .  \nSignificant predictors include olfactory dysfunction, motor symptoms,  \npsychomotor speed, and third ventricle dilation.  \nKeywords: Prodromal Parkinson’s disease · Machine Learning · MRI  \ndata.  \n1 Introduction  \nParkinson’s Disease (PD) is the second most common neurodegenerative disorder  \n[11], primarily affecting the elderly, with age being a significant risk factor. Diag  \nnosis relies on clinical criteria such as bradykinesia and other motor symptoms,  \n2 Authors Suppressed Due to Excessive Length  \nwith a strong link to dopaminergic cell loss in the substantia nigra [5] . Recent insights challenge this traditional view, highlighting that significant neuropathological changes and nonmotor manifestations can occur well before classic motor symptoms [14], indicating a ‘preclinical’ (symptom-free) or ‘prodromal’ (exhibit various nonmotor symptoms and/or minor motor signs) phase of PD. This early phase is crucial for diagnosis and offers a potential window for intervention to slow disease progression [15] . It is important to highlight that prodromal PD encompasses a broad spectrum of phenotypes, including individuals with genetic risk factors or clinical characteristics predating PD onset, such as hyposmia (a reduced sense of smell) or REM sleep behavior di","cbCairoFTL98cyX6","https://ap.wps.com/l/cbCairoFTL98cyX6","pdf",445908,9,1,10,"English","en",105,"# Abstract\n# Introduction\n## Parkinson’s Disease and prodromal phase\n## Role of neuroimaging and machine learning\n## Study objective and paper structure","[{\"question\":\"What is the primary goal of the study on prodromal Parkinson’s disease?\",\"answer\":\"To discriminate between prodromal individuals who phenoconverted to PD within 7 years and those who did not.\"},{\"question\":\"Which data types were integrated to build the predictive models?\",\"answer\":\"Demographic information, clinical measures, and structural MRI data collected at the first visit are combined.\"},{\"question\":\"How did the best-performing models differ across feature sets?\",\"answer\":\"Support Vector Machine (balanced) was most effective for demographic and clinical data, while Logistic Regression (balanced) performed best when adding MRI thicknesses and volumes.\"}]","Predicting Parkinson’s Disease Progression - Analyzing Prodromal Stages Through Machine Learning | PDF",1785905118,25,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"predicting-parkinsons-disease-progression-analyzing-prodromal-stages-through-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/predicting-parkinsons-disease-progression-analyzing-prodromal-stages-through-machine-learning/126447/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the primary goal of the study on prodromal Parkinson’s disease?","Question",{"text":77,"@type":78},"To discriminate between prodromal individuals who phenoconverted to PD within 7 years and those who did not.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which data types were integrated to build the predictive models?",{"text":82,"@type":78},"Demographic information, clinical measures, and structural MRI data collected at the first visit are combined.",{"name":84,"@type":75,"acceptedAnswer":85},"How did the best-performing models differ across feature sets?",{"text":86,"@type":78},"Support Vector Machine (balanced) was most effective for demographic and clinical data, while Logistic Regression (balanced) performed best when adding MRI thicknesses and volumes.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,122,125,129,132,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":118,"doc_module":4,"doc_module_name":47,"category_name":119,"show_sort_weight":120,"slug":121},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":123,"slug":124},30,"research-report",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":22,"slug":134},"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]