{"651867":{"#nid":"651867","#data":{"type":"news","title":"Multi-Algorithm Approach Helps Deliver Personalized Medicine for Cancer Patients","body":[{"value":"\u003Cp\u003EToday, machine learning, artificial intelligence, and algorithmic advancements made by research scientists and engineers are driving more targeted medical therapies through the power of prediction. The ability to rapidly analyze large amounts of complex data has clinicians closer to providing individualized treatments for patients, with an aim to create better outcomes through more proactive, personalized medicine and care.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;In medicine, we need to be able to make predictions,\u0026rdquo; said\u0026nbsp;\u003Ca href=\u0022https:\/\/biosciences.gatech.edu\/people\/john-mcdonald\u0022\u003EJohn F. McDonald\u003C\/a\u003E, professor in the\u0026nbsp;\u003Ca href=\u0022https:\/\/biosciences.gatech.edu\/\u0022\u003ESchool of Biological Sciences\u003C\/a\u003E\u0026nbsp;and director of the\u0026nbsp;\u003Ca href=\u0022https:\/\/icrc.gatech.edu\/\u0022\u003EIntegrated Cancer Research Center\u003C\/a\u003E\u0026nbsp;in the\u0026nbsp;\u003Ca href=\u0022https:\/\/research.gatech.edu\/bio\u0022\u003EPetit Institute for Bioengineering and Bioscience\u003C\/a\u003E\u0026nbsp;at the Georgia Institute of Technology. One way is through understanding cause and reflect relationships, like a cancer patient\u0026rsquo;s response to drugs, he explained. The other way is through correlation.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;In analyzing complex datasets in cancer biology, we can use machine learning, which is simply a sophisticated way to look for correlations. The advantage is that computers can look for these correlations in extremely large and complex data sets.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003ENow, McDonald\u0026rsquo;s team and the\u0026nbsp;\u003Ca href=\u0022https:\/\/ovariancancerinstitute.org\/\u0022\u003EOvarian Cancer Institute\u003C\/a\u003E\u0026nbsp;are using ensemble-based machine learning algorithms to predict how patients will respond to cancer-fighting drugs with high accuracy rates. The \u003Ca href=\u0022https:\/\/escires.com\/articles\/JOR-4-111.pdf\u0022\u003Eresults\u003C\/a\u003E of their most recent work have been published in the \u003Ca href=\u0022https:\/\/escires.com\/JOURNAL-OF-ONCOLOGY-RESEARCH\/articles\/volume-4-issue-1\u0022\u003E\u003Cem\u003EJournal of Oncology Research\u003C\/em\u003E\u003C\/a\u003E \u003Cem\u003E.\u003C\/em\u003E \u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EFor the study, McDonald and his colleagues developed predictive machine learning-based models for 15 distinct cancer types, using data from 499 independent cell lines provided by the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cancer.gov\/\u0022\u003ENational Cancer Institute\u003C\/a\u003E. Those models were then validated against a clinical dataset containing seven chemotherapeutic drugs, administered either singularly or in combination, to 23 ovarian cancer patients. The researchers found an overall predictive accuracy of 91%.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;While additional validation will need to be carried out using larger numbers of patients with multiple types of cancer,\u0026rdquo; McDonald noted, \u0026ldquo;our preliminary finding of 90% accuracy in the prediction of drug responses in ovarian cancer patients is extremely promising and gives me hope that the days of being able to accurately predict optimal cancer drug therapies for individual patients is in sight.\u0026quot;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe study was conducted in collaboration with the Ovarian Cancer Institute (OCI) in Atlanta, where McDonald serves as chief research officer. Other authors are\u0026nbsp;\u003Ca href=\u0022https:\/\/ovariancancerinstitute.org\/leadership\/\u0022\u003EBenedict Benigno\u003C\/a\u003E, MD (OCI founder and chief executive officer, as well as an obstetrician-gynecologist, surgeon, and oncologist);\u0026nbsp;\u003Ca href=\u0022https:\/\/mcdonaldlab.biology.gatech.edu\/nick-housley\/\u0022\u003ENick Housley\u003C\/a\u003E, a postdoctoral researcher in McDonald\u0026rsquo;s Georgia Tech lab; and the paper\u0026rsquo;s lead author, Jai Lanka, an intern with OCI.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EThe challenges in predicting cancer treatments\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe complex nature of cancer makes it a challenging problem when it comes to predicting drug responses, McDonald said. Patients with the same type of cancer will often respond differently to the same therapeutic treatment.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Part of the problem is that the cancer cell is a highly integrated network of pathways and patient tumors that display the same characteristics clinically may be quite different on the molecular level,\u0026rdquo; he explained.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EA major goal of personalized cancer medicine is to accurately predict likely responses to drug treatments based upon genomic profiles of individual patient tumors.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;In our approach, we utilize an ensemble of machine learning methods to build predictive algorithms \u0026mdash; based on correlations between gene expression profiles of cancer cell lines or patient tumors with previously observed responses \u0026mdash; to a variety of cancer drugs. The future goal is that gene expression profiles of tumor biopsies can be fed into the algorithms, and likely patient responses to different drug therapies can be predicted with high accuracy,\u0026rdquo; said McDonald.\u0026nbsp;\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMachine learning is already being applied to the data coming from the genomic profiles of tumor biopsies, but prior to the researchers\u0026rsquo; work, these methods have typically involved a single algorithmic approach.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMcDonald and his team decided to combine several algorithm approaches that use multiple ways to analyze complex data; one even uses a three-dimensional approach. They found using this ensemble-based approach significantly boosted predictive accuracy.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe algorithms the team used have names like Support Vector Machines (SVM), Random Forest classifier (RF), K-Nearest Neighbor classifier (KNN), and Logistic Regression classifier (LR).\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;They\u0026rsquo;re all fairly technical, and they\u0026rsquo;re all different computational mathematical approaches, and all of them are looking for correlations,\u0026rdquo; said McDonald. \u0026ldquo;It\u0026rsquo;s just a question of which one to use, and for different data sets, we find that one model might work better than another.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EHowever, more patient datasets that combine genomic profiles with responses to cancer drugs are needed to advance the research.\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;If we want to have a clinical impact, we must validate our models using data from a large number of patients,\u0026rdquo; said McDonald, who added that many datasets are held by pharmaceutical companies who use them in drug development. That data is typically considered proprietary, private information. And although a significant amount of genomic data of cancer patients is generally available, it\u0026rsquo;s not typically correlated with patient responses to drugs.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMcDonald is currently talking with medical insurance companies about access to relevant datasets, as well. \u0026ldquo;It costs insurance companies a significant amount of money to pay for drug treatments that don\u0026rsquo;t work,\u0026rdquo; he noted. Time, medical fees, and ultimately, many lives could be saved by providing researchers with these types of information.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Right now, a percentage of patients will not respond to a drug, but we don\u0026rsquo;t know that until after six weeks of chemotherapy,\u0026rdquo; said McDonald. \u0026ldquo;What we hope is that we will soon have tools that can accurately predict the probability of a patient responding to first line therapies \u0026mdash; and if they don\u0026rsquo;t respond, to be able to make accurate predictions as to the next drug to be tried.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003ECitation: Lanka J, Housley SN, Benigno BB, McDonald JF. \u0026ldquo;ELAFT: An Ensemble-based Machine-learning Algorithm that Predicts Anti-cancer Drug Responses with High Accuracy.\u0026rdquo;\u0026nbsp;Journal of Oncology Research.\u0026nbsp;ISSN: 2637-6148.\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EFunding for this research provided by the Ovarian Cancer Institute, Atlanta, Georgia; Northside Hospital (Atlanta); and The Deborah Nash Endowment Fund. John F. McDonald serves as chief research officer of the Ovarian Cancer Institute (OCI) in Atlanta.\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003E\u003Cstrong\u003EAbout Georgia Tech\u003C\/strong\u003E\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EThe Georgia Institute of Technology, or Georgia Tech, is a top 10 public research university developing leaders who advance technology and improve the human condition. The Institute offers business, computing, design, engineering, liberal arts, and sciences degrees. Its nearly 40,000 students, representing 50 states and 149 countries, study at the main campus in Atlanta, at campuses in France and China, and through distance and online learning.\u0026nbsp;As a leading technological university, Georgia Tech is an engine\u0026nbsp;of economic development for Georgia, the Southeast, and the nation, conducting more than $1 billion in research annually for government, industry, and society.\u003C\/em\u003E\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":[{"value":"John F. McDonald and his research team have created a \u2018multi-algorithm\u2019 machine learning approach to boost accuracy in predicting drug responses for ovarian cancer patients"}],"field_summary":[{"value":"\u003Cp\u003EJohn F. McDonald and his research team have created a \u0026lsquo;multi-algorithm\u0026rsquo; machine learning approach to boost accuracy in predicting drug responses for ovarian cancer patients.\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"John F. McDonald and his research team have created a \u2018multi-algorithm\u2019 machine learning approach to boost accuracy in predicting drug responses for ovarian cancer patients."}],"uid":"34434","created_gmt":"2021-10-20 18:58:26","changed_gmt":"2021-10-27 12:28:55","author":"Renay San Miguel","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2021-10-26T00:00:00-04:00","iso_date":"2021-10-26T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"652005":{"id":"652005","type":"image","title":"Ovarian cancer cells (Photo Nephron via Wikimedia Commons)","body":null,"created":"1635171998","gmt_created":"2021-10-25 14:26:38","changed":"1635171998","gmt_changed":"2021-10-25 14:26:38","alt":"","file":{"fid":"247368","name":"Ovarian cancer cells (Wikimedia Commons).jpg","image_path":"\/sites\/default\/files\/images\/Ovarian%20cancer%20cells%20%28Wikimedia%20Commons%29_0.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/Ovarian%20cancer%20cells%20%28Wikimedia%20Commons%29_0.jpg","mime":"image\/jpeg","size":826673,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/Ovarian%20cancer%20cells%20%28Wikimedia%20Commons%29_0.jpg?itok=lEWEMnaI"}},"651872":{"id":"651872","type":"image","title":"John F. McDonald","body":null,"created":"1634756909","gmt_created":"2021-10-20 19:08:29","changed":"1634756909","gmt_changed":"2021-10-20 19:08:29","alt":"","file":{"fid":"247318","name":"John F. McDonald.png","image_path":"\/sites\/default\/files\/images\/John%20F.%20McDonald.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/John%20F.%20McDonald.png","mime":"image\/png","size":513574,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/John%20F.%20McDonald.png?itok=6vqc2TLb"}}},"media_ids":["652005","651872"],"related_links":[{"url":"https:\/\/cos.gatech.edu\/news\/new-grant-award-supports-research-early-detection-ovarian-cancer","title":"New Grant Award Supports Research on Early Detection of Ovarian Cancer"},{"url":"https:\/\/cos.gatech.edu\/news\/open-source-machine-learning-tool-could-help-choose-cancer-drugs","title":"Open Source Machine Learning Tool Could Help Choose Cancer Drugs"},{"url":"https:\/\/cos.gatech.edu\/news\/genetics-and-cancer-research-offers-new-insights-risks-onset-progression","title":"Genetics and Cancer: Research Offers New Insights On Risks, Onset, Progression"},{"url":"https:\/\/cos.gatech.edu\/news\/detecting-ovarian-cancer-mice","title":"Detecting Ovarian Cancer in Mice"},{"url":"https:\/\/saportareport.com\/atlantas-ovarian-cancer-institute-breaking-new-ground-on-early-detection-treatment\/columnists\/maria_saporta\/","title":"Atlanta\u2019s Ovarian Cancer Institute breaking new ground on early detection, treatment"},{"url":"https:\/\/rh.gatech.edu\/news\/636060\/chemotherapy-and-cancer-gang-cause-neurological-side-effect-study-says","title":"Chemotherapy and Cancer Gang up to Cause a Neurological Side Effect, Study Says"}],"groups":[{"id":"1278","name":"College of Sciences"},{"id":"1275","name":"School of Biological Sciences"},{"id":"1188","name":"Research Horizons"}],"categories":[{"id":"135","name":"Research"},{"id":"138","name":"Biotechnology, Health, Bioengineering, Genetics"},{"id":"140","name":"Cancer Research"},{"id":"146","name":"Life Sciences and Biology"}],"keywords":[{"id":"4896","name":"College of Sciences"},{"id":"166882","name":"School of Biological Sciences"},{"id":"188855","name":"John F. McDonald"},{"id":"2373","name":"Ovarian Cancer Institute"},{"id":"189113","name":"marine learning"},{"id":"189114","name":"cancer-fighting drugs"},{"id":"5660","name":"algorithms"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"39441","name":"Bioengineering and Bioscience"},{"id":"39501","name":"People and Technology"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003ERenay San Miguel\u003Cbr \/\u003E\r\nCommunications Officer II\/Science Writer\u003Cbr \/\u003E\r\nCollege of Sciences\u003Cbr \/\u003E\r\n404-894-5209\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMedia Contacts:\u003Cbr \/\u003E\r\nGeorgia Parmelee | georgia.parmelee@gatech.edu | 404-281-7818\u003Cbr \/\u003E\r\nJess Hunt-Ralston | jess@cos.gatech.edu | 404-385-5207\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["renay.san@cos.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}