{"id":25815,"date":"2024-12-27T19:44:17","date_gmt":"2024-12-27T11:44:17","guid":{"rendered":"https:\/\/www.1ai.net\/?p=25815"},"modified":"2024-12-27T19:44:17","modified_gmt":"2024-12-27T11:44:17","slug":"%e5%85%a8%e7%90%83%e9%a6%96%e4%b8%aa%e9%87%8d%e7%97%87%e5%8c%bb%e7%96%97%e5%a4%a7%e6%a8%a1%e5%9e%8b%ef%bc%9a%e8%85%be%e8%ae%af-x-%e8%bf%88%e7%91%9e%e5%8f%91%e5%b8%83%e5%90%af%e5%85%83","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/25815.html","title":{"rendered":"World's First Critical Care Model: Tencent X Myriad Releases \"Qiyuan Critical Care Model\", Already Used in ICU Wards"},"content":{"rendered":"<p>December 27th.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%85%be%e8%ae%af\" title=\"[View articles tagged with [Tencent]]\" target=\"_blank\" >Tencent<\/a>today announced a joint<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%bf%88%e7%91%9e%e5%8c%bb%e7%96%97\" title=\"&quot;Look at the article that contains the label&quot;\" target=\"_blank\" >Myriad Healthcare (company name)<\/a>, released the world's first critical care<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%8c%bb%e7%96%97%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"Look at the article that contains the label\" target=\"_blank\" >Medical Model<\/a> -- \"--\"<strong>Qiyuan Critical Mass Model<\/strong>&quot;.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-25816\" title=\"281a0d2aj00sp5hwk00cod000u000jyp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/12\/281a0d2aj00sp5hwk00cod000u000jyp.jpg\" alt=\"281a0d2aj00sp5hwk00cod000u000jyp\" width=\"1080\" height=\"718\" \/><\/p>\n<p>According to reports, as an \"AI teammate\" with \"critical thinking\", Qiyuan can process disease data and take over the paperwork, allowing doctors to focus on treating diseases and saving lives.<\/p>\n<p>It has a workflow that is roughly divided into 'two steps':<strong>First, the massive data of patients are integrated to generate digital portraits; subsequently, the portraits are analyzed in depth with critical care thinking to predict the progression of the disease and suggest interventions<\/strong>.<\/p>\n<p>Based on these two steps, four major functions are finally realized:<\/p>\n<ul>\n<li><strong>Sickness Q&amp;A:<\/strong>exist\u00a0<strong>Within 5 seconds<\/strong>Sorting out the patient's disease history, extracting key indicators, generating digital portraits, predicting disease trends, and providing treatment recommendations to help doctors make quick decisions.<\/li>\n<li><strong>Medical Record Writing:<\/strong>After integrating diagnosis and treatment data, Qiyuan can also efficiently generate well-organized and standardized medical records.<strong>Within 1 minute<\/strong>Complete the entire writing process with increased efficiency\u00a0<strong>30 times<\/strong>.<\/li>\n<li><strong>Knowledge Queries:<\/strong>Based on the nine subgroups of the Critical Care Medicine Knowledge Graph, Qiyuan can pinpoint key knowledge and analyze it with an accuracy rate as high as\u00a0<strong>95%<\/strong>, providing efficient and authoritative decision support for physicians.<\/li>\n<li><strong>Diagnostic and treatment recommendations:<\/strong>Combining patient data and critical thinking training, Qiyuan provides personalized treatment plans to help doctors quickly develop accurate treatment plans.<\/li>\n<\/ul>\n<p>As a technological base, Tencent provides Qiyuan with a big model of hybridization through the<strong>Trillions of Parameters and 7 Trillion Tokens<\/strong>; and using a large amount of medical data - covering\u00a0<strong>2.85 million medical entities<\/strong>,<strong>12.5 million medical relations<\/strong>,as well as\u00a0<strong>Medical Knowledge and Literature for 98%<\/strong>, training a medical macromodel.<\/p>\n<p>At the same time, based on the RAG capability of the big model knowledge engine, Tencent helps Myriad build a search application for doctors to assist them in<strong>Retrieve the latest critical care knowledge and literature<\/strong>. For example, information on the basics of critical illnesses including respiratory, cardiovascular, neurological, digestive, endocrine and metabolic, urological, and infectious diseases, prevention, diagnosis, contraindications to medication, and nutritional support, saving time for physicians.<\/p>\n<p>Tencent has further joined forces with Myriad Healthcare to encourage the output of healthcare assessment and feedback models through a \"learning-by-use\" feedback mechanism to continuously<strong>Calibrating the logic and filling in the gaps<\/strong>The 'Critical Care Thinking' that is tailored to the clinical needs is gradually being developed.<\/p>\n<p>In addition, through model quantization, distillation and compression techniques, Tencent has \"slimmed down\" Qiyuan, the<strong>Make it work on the hospital's existing computing resources.<\/strong>; support localized deployments, lowering the threshold of use.<\/p>\n<p>1AI has learned from an official announcement that the Qiyuan Critical Illness Mega Model has been in the<strong>Pilot application in ICU of the First Affiliated Hospital of Zhejiang University School of Medicine<\/strong>.<\/p>","protected":false},"excerpt":{"rendered":"<p>December 27, Tencent today announced that it has joined hands with Meizu Medical to release the world's first major model of critical care - \"Qiyuan Critical Care Model\". According to reports, as an \"AI teammate\" with a \"critical care mindset\", Qiyuan can process disease data and take over the paperwork, allowing doctors to focus on treating the disease and saving lives. Its workflow is roughly divided into two steps: first, it integrates the patient's massive data to generate a digital image; then, it analyzes the image in depth with a critical thinking, predicts the development of the disease, and puts forward intervention suggestions. Based on these two steps, four major functions are finally realized: Disease Q&amp;A: combing the patient's disease history, extracting key indicators, generating digital portraits, predicting disease trends, and providing treatment recommendations within 5 seconds to help doctors make quick decisions. Medical Record Writing: Integrate diagnosis and treatment data<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[2729,323,5323],"collection":[],"class_list":["post-25815","post","type-post","status-publish","format-standard","hentry","category-news","tag-2729","tag-323","tag-5323"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/25815","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=25815"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/25815\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=25815"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=25815"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=25815"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=25815"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}