[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117847-en":3,"doc-seo-117847-105":30,"detail-sidebar-cat-0-en-105":95},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117847,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Implement Machine Learning Approaches in Cancer Clinical Trials","Clinical trials are prospective biomedical investigations used in clinical drug development to assess efficacy and safety of drug candidates, treatment regimens, or new technologies. Despite progress, trials still fail mainly due to drug ineffectiveness and treatment-related toxicity, driven by cohort selection weaknesses and inadequate patient monitoring. Because outcomes are often reported as average treatment effects across heterogeneous populations, results may not translate well to day-to-day clinical decision-making. This thesis integrates machine learning algorithms to identify clinically meaningful data patterns and build classification models that modernize drug development processes by improving prediction of toxicity and enabling decision support.","UNIVERSIT`A DEGLI STUDI DI TRIESTE  \ne  \nUNIVERSIT`A CA’FOSCARI DI VENEZIA  \nXXXV CICLO DEL DOTTORATO DI RICERCA IN CHIMICA  \nImplement Machine Learning Approaches in Cancer Clinical  \nTrials  \nSettore scientifico-disciplinare: CHIM/06  \nPh.D. STUDENT  \nLUCA BEDON  \nPh.D. PROGRAM COORDINATOR  \nPROF. ENZO ALESSIO  \nTHESIS SUPERVISORS  \nPROF. FEDERICO BERTI  \nGIUSEPPE TOFFOLI, M.D.  \nACADEMIC YEAR 2021/2022  \nThis thesis project was carried out as part of the  \nJoint Doctoral Program in Chemistry between the University of Trieste and Ca’ Foscari University of Venice, coordinated by Prof. Enzo Alessio  \nand with the support of the Experimental and Clinical Pharmacology Unit of the Centro di Riferimento Oncologico (CRO) IRCCS in Aviano, under the direction of Giuseppe Toffoli, M.D.  \nQuesto progetto di tesi `e stato svolto nell’ambito della Scuola di Dottorato in Chimica in convenzione fra  \nl’Universit`a degli Studi di Trieste e l’Universit`a Ca’ Foscari di Venezia, coordinata dal Prof. Enzo Alessio,  \ne con il supporto della Struttura Operativa Complessa di Farmacologia Sperimentale e Clinica  \ndel Centro di Riferimento Oncologico (CRO) IRCCS di Aviano, sotto la direzione del Dott. Giuseppe Toffoli.  \nAbstract  \nClinical trials are prospective biomedical investigations that are part of clinical drug development to evaluate the efficacy and safety of drug candidates, treatment regimens, or novel technologies on progressively larger groups of individuals.  \nDespite improvements, there are still two main reasons why clinical trials fail. These are drug ineffectiveness and drug-induced toxicity, which are primarily the result of poor cohort selection and patient monitoring. In truth, clinical drug development strategies have largely remained unchanged over the years. Because present therapies often only work for a small proportion of prescribed patients, new approaches must be developed to assess potential biomedical treatments for safety and efficacy. Furthermore, treatment results are provided as average treatment effects measured across a heterogeneous patient cohort, which may not translate easily into accurate treatment recommendations at the normal point of care.  \nMachine learning is an area of artificial intelligence that allows computers to learn without being explicitly programmed by analysing and drawing conclusions from data patterns. The use of machine learning on data from cutting-edge digital technologies can increase understanding of disease causes in a larger patient population and pave the way for the development of better treatment techniques. Intriguingly, machine learning has the potential to restructure crucial steps in clinical trials in order to improve their efficacy.  \nThis thesis investigated innovative strategies for modernising the process of drug clinical development by incorporating machine learning-based algorithms to uncover clinically significant patterns from various sources of data, culminating in classification models. This thesis work focused on three primary research issues.  \nThe first research issue concerns the use of a machine learning approach to identify known and novel predictors of dose limiting toxicity by analysing clinical, baseline blood biochemistry (i.e., prior to starting the phase I), and genetic data derived from a previously conducted phase Ib clinical trial in metastatic colorectal cancer patients treated with the FOLFIRI (folinic acid, 5-fluorouracil, irinotecan) plus bevacizumab regimen. The analysis pipeline used includes a step for selecting the best predictors based on importance rankings; the optimal subset was then used to train models. The performance of five machine learning classification models was evaluated in order to select the best classifier. The Random Forest model performed best during cross-validation, with a mean Matthews correlation  \ncoefficient of 0.549 and a mean accuracy of 80.4%; at baseline, the top predictors of dose-limiting toxicity were haemoglo","cbCairkAQw3rqlmp","https://ap.wps.com/l/cbCairkAQw3rqlmp","pdf",15339612,1,242,"English","en",105,"# Abstract\n## Rationale for clinical trial failure and need for new approaches\n## Role of machine learning in modernising clinical trial steps\n## Research issue 1: predictors of dose limiting toxicity\n## Research issue 2: genotype-therapy toxicity associations in ovarian cancer\n## Methods: feature selection and classification modelling","[{\"question\":\"Why do clinical trials often fail despite improvements in development?\",\"answer\":\"Clinical trials mainly fail due to drug ineffectiveness and drug-induced toxicity. These issues are linked to poor cohort selection and insufficient patient monitoring.\"},{\"question\":\"How does this thesis use machine learning to improve cancer clinical trial outcomes?\",\"answer\":\"It incorporates machine learning algorithms to uncover clinically significant patterns across multiple data sources and build classification models, with a focus on better toxicity prediction and decision support.\"},{\"question\":\"What data and modelling approach are used for identifying predictors of dose limiting toxicity?\",\"answer\":\"The study analyzes clinical, baseline blood biochemistry, and genetic data from a prior phase Ib metastatic colorectal cancer trial. Feature selection based on importance rankings trains and evaluates multiple classification models, with Random Forest performing best in cross-validation and validation.\"},{\"question\":\"How are genetic variants linked to drug-induced toxicities in the ovarian cancer research part?\",\"answer\":\"The thesis retrospectively analyzes DNA sequencing data for 171 patients from the MITO-16A/MaNGO-OV2A study. Using machine learning with the Boruta algorithm and XGBoost classifiers, it prioritizes germline variants associated with toxicities such as hypertension, hematological toxicity, non-hematological toxicity, and proteinuria.\"}]","Implement Machine Learning Approaches in Cancer Clinical Trials | PDF",1785679982,610,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"implement-machine-learning-approaches-in-cancer-clinical-trials","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/implement-machine-learning-approaches-in-cancer-clinical-trials/117847/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"Why do clinical trials often fail despite improvements in development?","Question",{"text":75,"@type":76},"Clinical trials mainly fail due to drug ineffectiveness and drug-induced toxicity. These issues are linked to poor cohort selection and insufficient patient monitoring.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does this thesis use machine learning to improve cancer clinical trial outcomes?",{"text":80,"@type":76},"It incorporates machine learning algorithms to uncover clinically significant patterns across multiple data sources and build classification models, with a focus on better toxicity prediction and decision support.",{"name":82,"@type":73,"acceptedAnswer":83},"What data and modelling approach are used for identifying predictors of dose limiting toxicity?",{"text":84,"@type":76},"The study analyzes clinical, baseline blood biochemistry, and genetic data from a prior phase Ib metastatic colorectal cancer trial. Feature selection based on importance rankings trains and evaluates multiple classification models, with Random Forest performing best in cross-validation and validation.",{"name":86,"@type":73,"acceptedAnswer":87},"How are genetic variants linked to drug-induced toxicities in the ovarian cancer research part?",{"text":88,"@type":76},"The thesis retrospectively analyzes DNA sequencing data for 171 patients from the MITO-16A/MaNGO-OV2A study. Using machine learning with the Boruta algorithm and XGBoost classifiers, it prioritizes germline variants associated with toxicities such as hypertension, hematological toxicity, non-hematological toxicity, and proteinuria.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]