{"id":28270,"date":"2025-08-18T04:24:00","date_gmt":"2025-08-17T20:24:00","guid":{"rendered":"https:\/\/csccm.org.cn\/?p=28270"},"modified":"2025-08-18T05:48:25","modified_gmt":"2025-08-17T21:48:25","slug":"npj-digital-med%e5%8f%91%e8%a1%a8%e8%ae%ba%e6%96%87%ef%bc%9a%e7%94%9f%e6%88%90%e5%bc%8f%e4%ba%ba%e5%b7%a5%e6%99%ba%e8%83%bd%e4%b8%8e%e5%8c%bb%e7%94%9f%e8%af%8a%e6%96%ad%e5%87%86%e7%a1%ae%e6%80%a7","status":"publish","type":"post","link":"https:\/\/csccm.org.cn\/?p=28270","title":{"rendered":"[NPJ Digital Med\u53d1\u8868\u8bba\u6587]\uff1a\u751f\u6210\u5f0f\u4eba\u5de5\u667a\u80fd\u4e0e\u533b\u751f\u8bca\u65ad\u51c6\u786e\u6027\u7684\u6bd4\u8f83"},"content":{"rendered":"\n<ul>\n<li>Article<\/li>\n<\/ul>\n\n\n\n<h1 class=\"wp-block-heading\">A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians<\/h1>\n\n\n\n<h3 class=\"wp-block-heading\">Hirotaka Takita,\u00a0Daijiro Kabata,\u00a0Shannon L. Walston,\u00a0et al<\/h3>\n\n\n\n<h3 class=\"wp-block-heading\"><em>npj Digital Medicine<\/em>\u00a0<strong>volume\u00a08<\/strong>, Article\u00a0number:\u00a0175\u00a0(2025)<\/h3>\n\n\n\n<h2 class=\"wp-block-heading\" id=\"Abs1\">Abstract<\/h2>\n\n\n\n<p>While generative artificial intelligence (AI) has shown potential in medical diagnostics, comprehensive evaluation of its diagnostic performance and comparison with physicians has not been extensively explored. We conducted a systematic review and meta-analysis of studies validating generative AI models for diagnostic tasks published between June 2018 and June 2024. Analysis of 83 studies revealed an overall diagnostic accuracy of 52.1%. No significant performance difference was found between AI models and physicians overall (<em>p<\/em>\u2009=\u20090.10) or non-expert physicians (<em>p<\/em>\u2009=\u20090.93). However, AI models performed significantly worse than expert physicians (<em>p<\/em>\u2009=\u20090.007). Several models demonstrated slightly higher performance compared to non-experts, although the differences were not significant. Generative AI demonstrates promising diagnostic capabilities with accuracy varying by model. Although it has not yet achieved expert-level reliability, these findings suggest potential for enhancing healthcare delivery and medical education when implemented with appropriate understanding of its limitations.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/media.springernature.com\/full\/springer-static\/image\/art%3A10.1038%2Fs41746-025-01543-z\/MediaObjects\/41746_2025_1543_Fig1_HTML.png\" alt=\"\"\/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/media.springernature.com\/full\/springer-static\/image\/art%3A10.1038%2Fs41746-025-01543-z\/MediaObjects\/41746_2025_1543_Fig2_HTML.png\" alt=\"\"\/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/media.springernature.com\/full\/springer-static\/image\/art%3A10.1038%2Fs41746-025-01543-z\/MediaObjects\/41746_2025_1543_Fig3_HTML.png\" alt=\"\"\/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/media.springernature.com\/full\/springer-static\/image\/art%3A10.1038%2Fs41746-025-01543-z\/MediaObjects\/41746_2025_1543_Fig4_HTML.png\" alt=\"\"\/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>A systematic review and meta-analysis of diagnostic per [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[32,23],"tags":[],"_links":{"self":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/28270"}],"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=28270"}],"version-history":[{"count":1,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/28270\/revisions"}],"predecessor-version":[{"id":28271,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/28270\/revisions\/28271"}],"wp:attachment":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=28270"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=28270"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=28270"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}