[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128180-en":3,"doc-seo-128180-105":31,"detail-sidebar-cat-0-en-105":92},{"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},128180,549768702563,"Sage","https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083",8,"Research & Report","Personalising Deep Brain Stimulation Therapy for Parkinson's Disease with Imaging Biomarkers and Machine Learning - PhD Thesis","This PhD thesis investigates clinical applications of imaging biomarkers extracted from magnetic resonance imaging (MRI) in patients with Parkinson’s disease who have undergone deep brain stimulation (DBS). It aims to develop a proof-of-principle machine learning framework that uses these biomarkers to predict DBS outcomes. Two experimental sections are presented: motor outcome prediction via radiomics-based models using 120 patient scans, and non-motor symptom improvement prediction using radiomics-based features with a random forest approach. The work addresses interpretability versus performance and emphasizes the role of future larger clinical trials for broader clinical adoption.","Personalising Deep Brain Stimulation Therapy for Parkinson’s Disease with Imaging Biomarkers and Machine  \nLearning  \nΒελτιστοποίηση της θεραπείας της εν τωβάθυ εγκεφαλικής διέγερσηςγιαασθενείς με νόσο Πάρκινσον με τηβοήθεια απεικονιστικών βιοδεικτών και  \nγλώσσας μηχανής  \nDr Nikolaos Haliasos  \nThesis submitted for the degree of PhD in Neurosurgery  \nFaculty of Medicine, University of Crete  \n2024  \nI, Dr Nikolaos Haliasos confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been  \nindicated in the thesis.  \nThis thesis and its contents are licenced under the Creative Commons BY-NC-SA  \nlicence agreement. More information can be found in [https://creativecommons.org/licenses/by-nc-sa/4.0/](https://creativecommons.org/licenses/by-nc-sa/4.0/)  \n[PhD Programme in Neurosurgery:](PhD Programme in Neurosurgery:)  \nFaculty of Medicine, University of Crete  \nPrimary supervisor: Professor Antonios Vakis, UoC  \nSecondary supervisor: Professor Kleanthi Spanaki, UoC  \nSecondary supervisor: Professor Vangelis Sakkalis, Foundation for Research and Technology  \nAuthor:  \nDr Nikolaos Haliasos, MD Fellow of the Royal College of Surgeons of England  \nQueens Hospital, Redbridge Barking Havering NHS Trust, Romford, RM7 0AG  \nTel: +44 1708 435 000 Mob: +44 7743 978068  \nEmail: [nhaliasos@gmail.com](nhaliasos@gmail.com)  \nTo my loving wife Angie  \nand my little one, Michail  \nAs long as our brain is a mystery, the universe, the reflection of the structure of the brain will also be a mystery.  \nSantiago Ramon y Cajal (1852 – 1934)  \nABSTRACT  \nThis thesis examines potential clinical applications of imaging biomarkers derived from Magnetic Resonance Imaging (MRI) of patients affected by Parkinson’s disease (PD) . These patients have undergone Deep Brain Stimulation therapy (DBS) . The aim of the thesis is to develop a proof of principle machine learning model incorporating these biomarkers in order to predict outcomes of the DBS therapy. Several new analysis methodologies are employed with the use of Radiomics and Machine learning (ML) techniques to: (1) build predictive models of DBS surgery outcome; (2) improve our understanding between imaging and pathophysiology of Parkinson’s disease  \nThe experimental component is divided in two parts:  \nSection I: in these experiments, the MRI Scans of 120 PD patients who underwent DBS are analysed to find radiological biomarkers predictive of Unified Parkinon’s Disease Rating Scale III (UPDRSIII) improvement 1 year after the surgery. A set of 7 Radiomics biomarkers (glcm_Maximal Correlation Coefficient, shape_LeastAxisLength,firstorder_Skewness, firstorder_ 90Percentile, glcm_ClusterShade,  \nglcm_Informational Measure of Correlation2, firstorder_Mean) are used to construct advanced machine learning models which were able to predict the motor outcome of  \nParkinson’s patients after DBS with an accuracy of Accuracy of 0.95, Sensitivity of 0.93 and Specificity of 0.97.  \nSection II: The Non-Motor Symptoms of Parkinson’s disease (NMS) are equally devasting for patients but have always been regarded as a lesser priority when dealing with Parkinson’s patients. DBS therapy, was initially focused on motor symptom  \nimprovement however there are studies suggesting the therapy has benefits also for the NMS. The experiments of this section attempt to find imaging biomarkers on the MRI dataset of 120 PD patients to predict Non-Motor Symptoms improvement after DBS therapy. A set of 7 Radiomics biomarkers are selected (Shape Maximum 2D Diameter Slice, Glcm Idn, Firstorder Minimum, Glcm Correlation, Shape_Mesh Volume, Glcm MCC, Firstorder Root Mean Squared, Firstorder 10 Percentile) are used to create an advanced Random Forest model which has an Accuracy of 0.91, Sensitivity of 0.94 and Specificity of 0.88 in predicting patients NMS outcomes.  \nAs this thesis attempts to bridge the use of machine learning techniques in patient care, a dilemma emerges ","cbCaiinP8wCifOTx","https://ap.wps.com/l/cbCaiinP8wCifOTx","pdf",5233008,4,1,175,"English","en",105,"# Abstract\n## Aims and proof-of-principle machine learning approach\n## Section I: Motor outcome prediction using radiomics\n## Section II: Non-motor symptom improvement prediction\n## Clinical translation: interpretability and future trials","[{\"question\":\"What is the primary goal of the thesis?\",\"answer\":\"To develop a proof-of-principle machine learning model that uses MRI-derived imaging biomarkers to predict outcomes of DBS therapy in Parkinson’s disease patients.\"},{\"question\":\"How is the experimental work structured?\",\"answer\":\"The thesis contains two sections: motor outcome prediction and non-motor symptom improvement prediction, both based on MRI radiomics from 120 DBS-treated patients.\"},{\"question\":\"Which machine learning and feature approach is used for motor and non-motor outcomes?\",\"answer\":\"Motor outcomes use advanced machine learning models built from seven radiomics biomarkers, while non-motor outcomes use a random forest model based on selected radiomics biomarkers.\"}]","Personalising Deep Brain Stimulation Therapy for Parkinson's Disease with Imaging Biomarkers and Machine Learning - PhD Thesis | PDF",1785945315,441,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"personalising-deep-brain-stimulation-therapy-for-parkinsons-disease-with-imaging-biomarkers-and-machine-learning-phd-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@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":20},"https://docshare.wps.com/document/personalising-deep-brain-stimulation-therapy-for-parkinsons-disease-with-imaging-biomarkers-and-machine-learning-phd-thesis/128180/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the primary goal of the thesis?","Question",{"text":76,"@type":77},"To develop a proof-of-principle machine learning model that uses MRI-derived imaging biomarkers to predict outcomes of DBS therapy in Parkinson’s disease patients.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is the experimental work structured?",{"text":81,"@type":77},"The thesis contains two sections: motor outcome prediction and non-motor symptom improvement prediction, both based on MRI radiomics from 120 DBS-treated patients.",{"name":83,"@type":74,"acceptedAnswer":84},"Which machine learning and feature approach is used for motor and non-motor outcomes?",{"text":85,"@type":77},"Motor outcomes use advanced machine learning models built from seven radiomics biomarkers, while non-motor outcomes use a random forest model based on selected radiomics biomarkers.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"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":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]