{"id":109412,"date":"2020-02-20T00:14:15","date_gmt":"2020-02-20T00:14:15","guid":{"rendered":"https:\/\/news.microsoft.com\/?p=436277"},"modified":"2020-02-20T00:14:15","modified_gmt":"2020-02-20T00:14:15","slug":"cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine","status":"publish","type":"post","link":"https:\/\/sickgaming.net\/blog\/2020\/02\/20\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine\/","title":{"rendered":"Cancer researchers embrace AI to accelerate development of precision medicine"},"content":{"rendered":"<div class=\"video-container responsive-youtube oembed-container\">\n<p id=\"ariaLabel_5e4e507fe808d\" class=\"screen-reader-text\">YouTube Video<\/p>\n<p><button class=\"cookie-consent-btn\">Click here to load media<\/button><\/p>\n<\/div>\n<p>Biomedical researchers are embracing artificial intelligence to accelerate the implementation of cancer treatments that target patients\u2019 specific genomic profiles, a type of precision medicine that in some cases is more effective than traditional chemotherapy and has fewer side effects.<\/p>\n<p>The potential for this new era of cancer treatment stems from advances in genome sequencing technology that enables researchers to more efficiently discover the specific genomic mutations that drive cancer, and an explosion of research on the development of new drugs that target those mutations.<\/p>\n<p>To harness this potential, researchers at <a href=\"https:\/\/www.jax.org\/\">The Jackson Laboratory<\/a>, an independent, nonprofit biomedical research institution also known as JAX and headquartered in Bar Harbor, Maine, developed a tool to help the global medical and scientific communities stay on top of the continuously growing volume of data generated by advances in genomic research.<\/p>\n<p>The tool, called the Clinical Knowledgebase, or CKB, is a searchable database where subject matter experts store, sort and interpret complex genomic data to improve patient outcomes and share information about clinical trials and treatment options.<\/p>\n<p>The challenge is to find the most relevant cancer-related information from the 4,000 or so biomedical research papers published each day, according to Susan Mockus, the associate director of clinical genomic market development with JAX\u2019s genomic medicine institute in Farmington, Connecticut.<\/p>\n<p>\u201cBecause there is so much data and so many complexities, without embracing and incorporating artificial intelligence and machine learning to help in the interpretation of the data, progress will be slow,\u201d she said.<\/p>\n<p>That\u2019s why Mockus and her colleagues at JAX are collaborating with computer scientists working on Microsoft\u2019s <a href=\"http:\/\/aka.ms\/hanover\">Project Hanover<\/a> who are developing AI technology that enables machines to read complex medical and research documents and highlight the important information they contain.<\/p>\n<p>While this machine reading technology is in the early stages of development, researchers have found they can make progress by narrowing the focus to specific areas such as clinical oncology, explained <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/petelee\/\">Peter Lee<\/a>, corporate vice president of Microsoft Healthcare in Redmond, Washington.<\/p>\n<p>\u201cFor something that really matters like cancer treatment where there are thousands of new research papers being published every day, we actually have a shot at having the machine read them all and help a board of cancer specialists answer questions about the latest research,\u201d he said.<\/p>\n<figure id=\"attachment_81955\" aria-describedby=\"caption-attachment-81955\" class=\"wp-caption alignright\"><a href=\"https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-81955 size-full\" src=\"https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine.jpg\" alt=\"Peter Lee stands with arms crossed behind some plants\" width=\"1920\" height=\"1080\" srcset=\"https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine.jpg 1920w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-2.jpg 300w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-3.jpg 768w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-4.jpg 1024w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-5.jpg 1333w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-6.jpg 924w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-7.jpg 793w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-8.jpg 960w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-9.jpg 480w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-10.jpg 1600w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\"><\/a><figcaption id=\"caption-attachment-81955\" class=\"wp-caption-text\">Peter Lee, corporate vice president of Microsoft Healthcare. Photo by Dan DeLong.<\/figcaption><\/figure>\n<h2><strong>Curating CKB<\/strong><\/h2>\n<p>Mockus and her colleagues are using Microsoft\u2019s machine reading technology to curate CKB, which stores structured information about genomic mutations that drive cancer, drugs that target cancer genes and the response of patients to those drugs.<\/p>\n<p>One application of this knowledgebase allows oncologists to discover what, if any, matches exist between a patient\u2019s known cancer-related genomic mutations and drugs that target them as they explore and weigh options for treatment, including enrollment in clinical trials for drugs in development.<\/p>\n<p>This information is also useful to translational and clinical researchers, Mockus noted.<\/p>\n<p>The bottleneck is filtering through the more than 4,000 papers published every day in biomedical journals to find the subset of about 200 related to cancer, read them and update CKB with the relevant information on the mutation, drug and patient response.<\/p>\n<p>\u201cWhat you want is some degree of intelligence incorporated into the system that can go out and not just be efficient, but also be effective and relevant in terms of how it can filter information. That is what Hanover has done,\u201d said <a href=\"https:\/\/www.jax.org\/people\/auro-nair\">Auro Nair<\/a>, executive vice president of JAX.<\/p>\n<p>The core of Microsoft\u2019s Project Hanover is the capability to comb through the thousands of documents published each day in the biomedical literature and flag and rank all that are potentially relevant to cancer researchers, highlighting, for example, information on gene, mutation, drug and patient response.<\/p>\n<p>Human curators working on CKB are then free to focus on the flagged research papers, validating the accuracy of the highlighted information.<\/p>\n<p>\u201cOur goal is to make the human curators superpowered,\u201d said <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/people\/hoifung\/\">Hoifung Poon<\/a>, director of precision health natural language processing with Microsoft\u2019s research organization in Redmond and the lead researcher on Project Hanover.<\/p>\n<p>\u201cWith the machine reader, we are able to suggest that this might be a case where a paper is talking about a drug-gene mutation relation that you care about,\u201d Poon explained. \u201cThe curator can look at this in context and, in a couple of minutes, say, \u2018This is exactly what I want,\u2019 or \u2018This is incorrect.\u2019\u201d<\/p>\n<figure id=\"attachment_81956\" aria-describedby=\"caption-attachment-81956\" class=\"wp-caption alignright\"><a href=\"https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-1.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-81956 size-full\" src=\"https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-1.jpg\" alt=\"Hoifung Poon sits on a yellow chair\" width=\"1920\" height=\"1080\" srcset=\"https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-1.jpg 1920w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-11.jpg 300w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-12.jpg 768w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-13.jpg 1024w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-14.jpg 1333w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-15.jpg 924w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-16.jpg 793w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-17.jpg 960w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-18.jpg 480w, https:\/\/www.sickgaming.net\/blog\/wp-content\/uploads\/2020\/02\/cancer-researchers-embrace-ai-to-accelerate-development-of-precision-medicine-19.jpg 1600w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\"><\/a><figcaption id=\"caption-attachment-81956\" class=\"wp-caption-text\">Hoifung Poon , director of precision health natural language processing with Microsoft\u2019s research organization, is leading the development of Project Hanover, a machine reading technology. Photo by Jonathan Banks.<\/figcaption><\/figure>\n<h2><strong>Self supervision<\/strong><\/h2>\n<p>To be successful, Poon and his team need to train machine learning models in such a way that they catch all the potentially relevant information \u2013 ensure there are no gaps in content \u2013 and, at the same time, weed out irrelevant information sufficiently to make the curation process more efficient.<\/p>\n<p>In traditional machine reading tasks such as finding information about celebrities in news stories, researchers tend to focus on relationships contained within a single sentence, such as a celebrity name and a new movie.<\/p>\n<p>Since this type of information is widespread across news stories, researchers can skip instances that are more challenging such as when the name of the celebrity and movie are mentioned in separate paragraphs, or when the relationship involves more than two pieces of information.<\/p>\n<p>\u201cIn biomedicine, you can\u2019t do that because your latest finding may only appear in this single paper and if you skip it, it could be life or death for this patient,\u201d explained Poon. \u201cIn this case, you have to tackle some of the hard linguistic challenges head on.\u201d<\/p>\n<p>Poon and his team are taking what they call a self-supervision approach to machine learning in which the model automatically annotates training examples from unlabeled text by leveraging prior knowledge in existing databases and ontologies.<\/p>\n<p>For example, a National Cancer Institute initiative manually compiled information from the biomedical literature on how genes regulate each other but was unable to sustain the effort beyond two years. Poon\u2019s team used the compiled knowledge to automatically label documents and train a machine reader to find new instances of gene regulation.<\/p>\n<p>They took the same approach with public datasets on approved cancer drugs and drugs in clinical trials, among other sources.<\/p>\n<p>This connect-the-dots approach creates a machine learned model that \u201crarely misses anything\u201d and is precise enough \u201cwhere we can potentially improve the curation efficiency by a lot,\u201d said Poon.<\/p>\n<h2><strong>Collaboration with JAX<\/strong><\/h2>\n<p>The collaboration with JAX allows Poon and his team to validate the effectiveness of Microsoft\u2019s machine reading technology while increasing the efficiency of Mockus and her team as they curate CKB.<\/p>\n<p>\u201cLeveraging the machine reader, we can say here is what we are interested in and it will help to triage and actually rank papers for us that have high clinical significance,\u201d Mockus said. \u201cAnd then a human goes in to really tease apart the data.\u201d<\/p>\n<p>Over time, feedback from the curators will be used to help train the machine reading technology, making the models more precise and, in turn, making the curators more efficient and allowing the scope of CKB to expand.<\/p>\n<p>\u201cWe feel really, really good about this relationship,\u201d said Nair. \u201cParticularly from the standpoint of the impact it can have in providing a very powerful tool to clinicians.\u201d<\/p>\n<h3>Related:<\/h3>\n<p><em>John Roach writes about Microsoft research and innovation. Follow him on <\/em><a href=\"https:\/\/twitter.com\/byjohnroach\"><em>Twitter<\/em><\/a><em>.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>YouTube Video Click here to load media Biomedical researchers are embracing artificial intelligence to accelerate the implementation of cancer treatments that target patients\u2019 specific genomic profiles, a type of precision medicine that in some cases is more effective than traditional chemotherapy and has fewer side effects. The potential for this new era of cancer treatment [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":109413,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[49],"tags":[917,50],"class_list":["post-109412","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-microsoft-news","tag-health","tag-recent-news"],"_links":{"self":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts\/109412","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/comments?post=109412"}],"version-history":[{"count":0,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/posts\/109412\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/media\/109413"}],"wp:attachment":[{"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/media?parent=109412"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/categories?post=109412"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sickgaming.net\/blog\/wp-json\/wp\/v2\/tags?post=109412"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}