{"id":1785,"date":"2026-03-24T08:18:51","date_gmt":"2026-03-24T08:18:51","guid":{"rendered":"https:\/\/cloudlab.urv.cat\/catedracloud\/?p=1785"},"modified":"2026-03-24T11:16:08","modified_gmt":"2026-03-24T11:16:08","slug":"hackato-ia-urv-tsystems-2026-pma","status":"publish","type":"post","link":"https:\/\/cloudlab.urv.cat\/catedracloud\/2026\/03\/24\/hackato-ia-urv-tsystems-2026-pma\/","title":{"rendered":"Hackat\u00f3 IA URV-TSystems 2026: PMA"},"content":{"rendered":"\n<p><\/p>\n\n\n\n<div class=\"wp-block-uagb-image uagb-block-16dabc03 wp-block-uagb-image--layout-default wp-block-uagb-image--effect-static wp-block-uagb-image--align-none\"><figure class=\"wp-block-uagb-image__figure\"><img decoding=\"async\" srcset=\"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/D81_3477-1024x684.jpg ,https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/D81_3477.jpg 780w, https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/D81_3477.jpg 360w\" sizes=\"auto, (max-width: 480px) 150px\" src=\"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/D81_3477-1024x684.jpg\" alt=\"\" class=\"uag-image-1787\" width=\"2048\" height=\"1363\" title=\"D81_3477\" loading=\"lazy\" role=\"img\"\/><\/figure><\/div>\n\n\n\n<p>L&#8217;objectiu principal \u00e9s processar grans volums de dades cl\u00edniques de pacients (com PCC i MACA) per executar una suite de models predictius de manera ultrar\u00e0pida i eficient, minimitzant els costos computacionals al Cloud. Aquests models ajuden a predir descompensacions a urg\u00e8ncies, l&#8217;\u00edndex de mortalitat a un any i la necessitat de derivaci\u00f3 a cures interm\u00e8dies o sociosanit\u00e0ries.<\/p>\n\n\n\n<p><strong>Nom Grup:<\/strong> Ganadores FC<\/p>\n\n\n\n<p><strong>Entitat del repte:<\/strong> Hospital Universitari Joan XXIII<\/p>\n\n\n\n<p><strong>Integrants: <\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Satxa Fortuny Pimentel (<a>satxa.fortuny@estudiants.urv.cat<\/a>)<\/li>\n\n\n\n<li>Lyubomyr Grygoriv Lvivska (<a>lyubomyr.grygoriv@estudiants.urv.cat<\/a>)<\/li>\n\n\n\n<li>Iulian Sebastian Oprea (<a>iulian.oprea@estudiants.urv.cat<\/a>)<\/li>\n\n\n\n<li>Kevin S\u00e1nchez Ram\u00edrez (<a>kevin.sanchez@estudiants.urv.cat<\/a>)<\/li>\n<\/ul>\n\n\n\n<p><strong>Nom Projecte:<\/strong> PMA (Programa de Monitoratge Automatitzat)<a href=\"https:\/\/github.com\/Lyuuubo\/joanXXIII-ganadores-fc#pma-programa-de-monitoratge-automatitzat\"><\/a><\/p>\n\n\n\n<p><strong>Descripci\u00f3:<\/strong> El Programa de Monitoratge Automatitzat (PMA) neix per processar eficientment els historials cl\u00ednics de gaireb\u00e9 38.000 pacients, distribu\u00efts en m\u00faltiples taules relacionals (cohort, diagn\u00f2stics, f\u00e0rmacs, visites i laboratori). Per superar els colls d&#8217;ampolla del processament cl\u00e0ssic, el sistema implementa una arquitectura&nbsp;<em>serverless<\/em>&nbsp;basada en esdeveniments i una potent&nbsp;<em>pipeline<\/em>&nbsp;ETL. El nucli del PMA \u00e9s totalment reactiu: qualsevol addici\u00f3 o modificaci\u00f3 a la base de dades activa un&nbsp;<em>trigger<\/em>autom\u00e0tic. Aquest esdeveniment orquestra l&#8217;execuci\u00f3 en paral\u00b7lel de m\u00faltiples funcions Lambda, cadascuna encarregada d&#8217;un model predictiu especialitzat. Aquestes funcions realitzen la infer\u00e8ncia per pronosticar l&#8217;estat futur del pacient i, immediatament, emmagatzemen els resultats a la base de dades.Aquesta arquitectura as\u00edncrona permet al personal m\u00e8dic accedir a la plataforma web en qualsevol moment per consultar tant les dades reals com les prediccions. A m\u00e9s, els professionals disposen d&#8217;un xatbot integrat per interactuar amb les dades i, com a mesura preventiva, el metge pot activar notificacions autom\u00e0tiques per alertar i fer un seguiment estret dels pacients classificats amb un risc alt de mortalitat.<\/p>\n\n\n\n<p><strong>Reptes abordats:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Repte 1 (\u00cdndex de Mortalitat a 1 Any):<\/strong>&nbsp;Classificaci\u00f3 del risc vital basat en edat, ingressos severs previs i diagn\u00f2stics per prioritzar cures pal\u00b7liatives i atenci\u00f3 domicili\u00e0ria avan\u00e7ada.<\/li>\n\n\n\n<li><strong>Repte 2 (Predictor de Risc d&#8217;Urg\u00e8ncies a 30 Dies):<\/strong>&nbsp;Avaluaci\u00f3 de pacients complexos per predir una descompensaci\u00f3 imminent, optimitzant la gesti\u00f3 de llits i recursos a curt termini.<\/li>\n\n\n\n<li><strong>Repte 3 (Sistema recomandor de pacients no etiquetats com a PCC per\u00f2 potencialment candidats):<\/strong>Identificaci\u00f3 proactiva per similitud amb els ja etiquetats a cohort.<\/li>\n\n\n\n<li><strong>Repte addicional \/ Innovaci\u00f3 (Predictor de Derivaci\u00f3 Sociosanit\u00e0ria):<\/strong>&nbsp;Predicci\u00f3 de la necessitat de trasllat a cures interm\u00e8dies per a pacients ingressats, permetent a treball social iniciar els tr\u00e0mits des del primer dia i descongestionant l&#8217;hospital.<\/li>\n<\/ul>\n\n\n\n<p><strong>Tecnologies utilitzades:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Llenguatges de programaci\u00f3:<\/strong>&nbsp;Python, Typescript, HTML i CSS.<\/li>\n\n\n\n<li><strong>Frameworks i llibreries:<\/strong>\n<ul class=\"wp-block-list\">\n<li><em>Backend i Dades:<\/em>&nbsp;FastAPI, SQLAlchemy, SQLModel, Psycopg2, Google File Search.<\/li>\n\n\n\n<li><em>Intel\u00b7lig\u00e8ncia Artificial i MLOps:<\/em>&nbsp;NVIDIA RAPIDS (cuDF), XGBoost, LightGBM, ONNX, Google Generative AI, Pytorch.<\/li>\n\n\n\n<li><em>Frontend:<\/em>&nbsp;Vue 3, PrimeVue, Pinia, Tailwind CSS, Chart.js, vue-router.<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li><strong>Eines i plataformes:<\/strong>&nbsp;AWS (incloses integracions d&#8217;Amplify i Lambdas), NVIDIA Triton Inference Server i Vite, Docker<\/li>\n<\/ul>\n\n\n\n<p><strong>Recursos del Projecte:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Github:<\/strong> <a href=\"https:\/\/github.com\/Lyuuubo\/joanXXIII-ganadores-fc\">https:\/\/github.com\/Lyuuubo\/joanXXIII-ganadores-fc<\/a><\/li>\n\n\n\n<li><strong>V\u00eddeo:<\/strong> <a href=\"https:\/\/youtu.be\/q1JJkry1-0o\">https:\/\/youtu.be\/q1JJkry1-0o<\/a><\/li>\n\n\n\n<li><strong>Presentaci\u00f3:<\/strong> <a href=\"https:\/\/rovira-my.sharepoint.com\/:b:\/g\/personal\/52460503-x_epp_urv_cat\/IQAehL4kOIhSTItoS9vOHNnSAazF3XHSWpos2zaYZS6DkjE?e=BPPzUH\">https:\/\/rovira-my.sharepoint.com\/:b:\/g\/personal\/52460503-x_epp_urv_cat\/IQAehL4kOIhSTItoS9vOHNnSAazF3XHSWpos2zaYZS6DkjE?e=BPPzUH<\/a><\/li>\n<\/ul>\n\n\n\n<p><strong>Acc\u00e9s a la resta de projectes de la Hackat\u00f3 d&#8217;IA 2026:<\/strong> <a href=\"https:\/\/cloudlab.urv.cat\/catedracloud\/hackato2026\/\">https:\/\/cloudlab.urv.cat\/catedracloud\/hackato2026\/<\/a><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>L&#8217;objectiu principal \u00e9s processar grans volums de dades cl\u00edniques de pacients (com PCC i MACA) per executar una suite de models predictius de manera ultrar\u00e0pida i eficient, minimitzant els costos computacionals al Cloud. Aquests models ajuden a predir descompensacions a urg\u00e8ncies, l&#8217;\u00edndex de mortalitat a un any i la necessitat de derivaci\u00f3 a cures interm\u00e8dies [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":1789,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_uag_custom_page_level_css":"","_swt_meta_header_display":false,"_swt_meta_footer_display":false,"_swt_meta_site_title_display":false,"_swt_meta_sticky_header":false,"_swt_meta_transparent_header":false,"footnotes":""},"categories":[113,94,39],"tags":[],"class_list":["post-1785","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cloud-computing","category-hackathon","category-ia"],"jetpack_featured_media_url":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image.png","uagb_featured_image_src":{"full":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image.png",1184,983,false],"thumbnail":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image-150x150.png",150,150,true],"medium":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image-300x249.png",300,249,true],"medium_large":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image-768x638.png",768,638,true],"large":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image-1024x850.png",1024,850,true],"1536x1536":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image.png",1184,983,false],"2048x2048":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/image.png",1184,983,false]},"uagb_author_info":{"display_name":"Carlos Molina","author_link":"https:\/\/cloudlab.urv.cat\/catedracloud\/author\/carlos-molina\/"},"uagb_comment_info":0,"uagb_excerpt":"L&#8217;objectiu principal \u00e9s processar grans volums de dades cl\u00edniques de pacients (com PCC i MACA) per executar una suite de models predictius de manera ultrar\u00e0pida i eficient, minimitzant els costos computacionals al Cloud. Aquests models ajuden a predir descompensacions a urg\u00e8ncies, l&#8217;\u00edndex de mortalitat a un any i la necessitat de derivaci\u00f3 a cures interm\u00e8dies&hellip;","_links":{"self":[{"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/posts\/1785","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/comments?post=1785"}],"version-history":[{"count":7,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/posts\/1785\/revisions"}],"predecessor-version":[{"id":1887,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/posts\/1785\/revisions\/1887"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/media\/1789"}],"wp:attachment":[{"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/media?parent=1785"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/categories?post=1785"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/tags?post=1785"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}