{"id":17574,"date":"2019-08-19T05:38:25","date_gmt":"2019-08-18T21:38:25","guid":{"rendered":"http:\/\/csccm.org.cn\/?p=17574"},"modified":"2019-08-28T22:51:50","modified_gmt":"2019-08-28T14:51:50","slug":"nature%e5%8f%91%e8%a1%a8%e8%ae%ba%e6%96%87%ef%bc%9a%e6%8c%81%e7%bb%ad%e9%a2%84%e6%b5%8baki%e7%9a%84%e4%b8%b4%e5%ba%8a%e5%8f%af%e8%a1%8c%e6%96%b9%e6%b3%95","status":"publish","type":"post","link":"https:\/\/csccm.org.cn\/?p=17574","title":{"rendered":"[Nature\u53d1\u8868\u8bba\u6587]\uff1a\u6301\u7eed\u9884\u6d4bAKI\u7684\u4e34\u5e8a\u53ef\u884c\u65b9\u6cd5"},"content":{"rendered":"\n

Letter | Published: 31 July 2019<\/a><\/p>\n\n\n\n

A clinically applicable approach to continuous prediction of future acute kidney injury<\/h1>\n\n\n\n

Nenad Toma\u0161ev, Xavier Glorot, Jack W. Rae, et al<\/h3>\n\n\n\n

Nature<\/em>  572<\/strong>, pages116\u2013119 (2019)<\/h3>\n\n\n\n

Abstract<\/h2>\n\n\n\n

The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients. To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records and using acute kidney injury\u2014a common and potentially life-threatening condition\u2014as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests. Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment.<\/p>\n\n\n\n

\u65e9\u671f\u9884\u6d4b\u75c5\u60c5\u6076\u5316\u5bf9\u4e8e\u533b\u52a1\u4eba\u5458\u6709\u91cd\u8981\u610f\u4e49\uff0c\u4f30\u8ba1\u7ea6\u670911%\u7684\u4f4f\u9662\u671f\u95f4\u6b7b\u4ea1\u4e0e\u672a\u80fd\u53ca\u65f6\u8bc6\u522b\u5e76\u6cbb\u7597\u75c5\u60c5\u6076\u5316\u6709\u5173\u3002\u5b9e\u73b0\u4e0a\u8ff0\u76ee\u6807\u9700\u8981\u5728\u4e2a\u4f53\u6c34\u5e73\u6301\u7eed\u5e76\u51c6\u786e\u9884\u6d4b\u60a3\u8005\u98ce\u9669\uff0c\u5e76\u6709\u5145\u8db3\u7684\u65f6\u95f4\u4ee5\u4fbf\u91c7\u53d6\u884c\u52a8\u3002\u8fd1\u671f\u6211\u4eec\u6839\u636e\u7535\u5b50\u75c5\u5386\u7cfb\u7edf\u4ee5\u6025\u6027\u80be\u635f\u4f24\uff08\u4e00\u79cd\u5e38\u89c1\u4e14\u53ef\u80fd\u5371\u53ca\u751f\u547d\u7684\u7efc\u5408\u5f81\uff09\u4e3a\u4f8b\uff0c\u5efa\u7acb\u4e86\u4e0d\u826f\u4e8b\u4ef6\u6a21\u578b\u3002\u5728\u6b64\u57fa\u7840\u4e0a\uff0c\u6211\u4eec\u5efa\u7acb\u4e86\u4e00\u79cd\u6df1\u5ea6\u5b66\u4e60\u65b9\u6cd5\uff0c\u4ee5\u6301\u7eed\u9884\u6d4b\u6b64\u540e\u60a3\u8005\u75c5\u60c5\u6076\u5316\u7684\u98ce\u9669\u3002\u6211\u4eec\u6839\u636e\u4e00\u4e2a\u5927\u89c4\u6a21\u7eb5\u5411\u7535\u5b50\u75c5\u5386\u7cfb\u7edf\u6570\u636e\u5e93\uff08\u8986\u76d6\u4e0d\u540c\u4e34\u5e8a\u60c5\u51b5\uff0c\u5305\u62ec172\u4e2a\u4f4f\u9662\u4e2d\u5fc3\u53ca1,062\u4e2a\u95e8\u8bca\u7684703,782\u540d\u6210\u5e74\u60a3\u8005\uff09\u5efa\u7acb\u6a21\u578b\u3002\u6211\u4eec\u7684\u6a21\u578b\u80fd\u591f\u9884\u6d4b55.8%\u7684\u6025\u6027\u80be\u635f\u4f24\u4f4f\u9662\u60a3\u8005\uff0c\u4ee5\u53ca\u540e\u7eed\u9700\u8981\u900f\u6790\u6cbb\u7597\u768490.2%\u7684\u6025\u6027\u80be\u635f\u4f24\u60a3\u8005\uff0c\u65f6\u95f4\u6700\u591a\u63d0\u524d48\u5c0f\u65f6\uff0c\u6bcf\u4e2a\u6b63\u786e\u7684\u9884\u8b66\u67092\u4e2a\u5047\u9633\u6027\u9884\u8b66\u3002\u9664\u9884\u6d4b\u672a\u6765\u7684\u6025\u6027\u80be\u635f\u4f24\u5916\uff0c\u6211\u4eec\u7684\u6a21\u578b\u8fd8\u53ef\u4ee5\u63d0\u4f9b\u53ef\u9760\u7684\u8bc4\u4f30\uff0c\u4ee5\u53ca\u5bf9\u4e8e\u6bcf\u4e2a\u9884\u6d4b\u81f3\u5173\u91cd\u8981\u7684\u4e00\u7cfb\u5217\u4e34\u5e8a\u7279\u5f81\uff0c\u5e76\u80fd\u591f\u9884\u6d4b\u4eca\u540e\u4e34\u5e8a\u4e2d\u836f\u7684\u8840\u6db2\u5316\u9a8c\u7ed3\u679c\u3002\u5c3d\u7ba1\u6025\u6027\u80be\u635f\u4f24\u7684\u8bc6\u522b\u4e0e\u53ca\u65f6\u6cbb\u7597\u9762\u4e34\u5f88\u5927\u6311\u6218\uff0c\u4f46\u6211\u4eec\u7684\u65b9\u6cd5\u6709\u52a9\u4e8e\u5728\u5145\u5206\u7684\u65f6\u95f4\u7a97\u5185\u9274\u522b\u9ad8\u5371\u60a3\u8005\u5e76\u5f00\u59cb\u65e9\u671f\u6cbb\u7597\u3002<\/p>\n\n\n\n

\"\"\/<\/figure>\n\n\n\n
\"\"\/<\/figure>\n\n\n\n
\"\"\/<\/figure>\n\n\n\n

[\u8bc4\u8bba]\uff08\u4ec5\u4ee3\u8868\u4e2a\u4eba\u610f\u89c1\uff09<\/h3>\n\n\n\n
  • \u4eba\u5de5\u667a\u80fd\u5728\u533b\u5b66\u9886\u57df\u7684\u5e94\u7528\u65b9\u5174\u672a\u827e\uff0c\u56fe\u5f62\u6216\u56fe\u50cf\u8bc6\u522b\u6050\u6015\u662f\u65e9\u671f\u6700\u5bb9\u6613\u53d6\u5f97\u6210\u529f\u53ca\u8d5a\u53d6\u773c\u7403\u7684\u5e94\u7528\u5b9e\u4f8b<\/li>
  • \u91cd\u75c7\u533b\u5b66\u9886\u57df\u7684\u7814\u7a76\u591a\u96c6\u4e2d\u5728\u4e34\u5e8a\u7efc\u5408\u5f81\uff08\u5982\u6025\u6027\u80be\u635f\u4f24\uff09\u6216\u4e34\u5e8a\u5206\u578b\uff08\u8113\u6bd2\u75c7\u5185\u8868\u578b\uff0cARDS\u8868\u578b\u7b49\uff09\u7684\u9884\u6d4b\uff0c\u4e5f\u6709\u5c11\u6570\u7814\u7a76\u6d89\u8db3\u56fe\u5f62\u8bc6\u522b\uff08\u5982\u4eba\u673a\u4e0d\u540c\u6b65\uff09<\/li>
  • \u4eba\u5de5\u667a\u80fd\u7528\u4e8e\u5371\u91cd\u75c5\u60a3\u8005\u7684\u533b\u7597\u51b3\u7b56\u4ec5\u89c1\u4e8e\u5c11\u6570\u7814\u7a76(Nat Med 2018; 24: 1716-1720)\uff0c\u4f46\u6216\u8bb8\u662f\u66f4\u6709\u610f\u4e49\u7684\u5e94\u7528\u65b9\u5411<\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"

    Letter | Published: 31 July 2019 A clini […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[32,23],"tags":[],"_links":{"self":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/17574"}],"collection":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=17574"}],"version-history":[{"count":4,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/17574\/revisions"}],"predecessor-version":[{"id":17589,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/17574\/revisions\/17589"}],"wp:attachment":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=17574"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=17574"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=17574"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}