{"id":1753,"date":"2026-03-24T08:00:00","date_gmt":"2026-03-24T08:00:00","guid":{"rendered":"https:\/\/cloudlab.urv.cat\/catedracloud\/?p=1753"},"modified":"2026-03-24T11:24:50","modified_gmt":"2026-03-24T11:24:50","slug":"hackato-ia-urv-tsystems-2026-prognos","status":"publish","type":"post","link":"https:\/\/cloudlab.urv.cat\/catedracloud\/2026\/03\/24\/hackato-ia-urv-tsystems-2026-prognos\/","title":{"rendered":"Hackat\u00f3 IA URV-TSystems 2026: PROGNOS"},"content":{"rendered":"\n<div class=\"wp-block-uagb-image uagb-block-daffcfe6 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\/D4S_9291-1024x682.jpg ,https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/D4S_9291.jpg 780w, https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/D4S_9291.jpg 360w\" sizes=\"auto, (max-width: 480px) 150px\" src=\"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/D4S_9291-1024x682.jpg\" alt=\"\" class=\"uag-image-1754\" width=\"2048\" height=\"1363\" title=\"D4S_9291\" loading=\"lazy\" role=\"img\"\/><\/figure><\/div>\n\n\n\n<h4 class=\"wp-block-heading has-text-align-center\"><strong>1er Premi<\/strong><\/h4>\n\n\n\n<p><strong>Prognos<\/strong> \u00e9s un sistema de suport cl\u00ednic per al Joan XXIII que combina classificaci\u00f3 ML, agents LLM i un chatbot accessible per a pacients cr\u00f2nics. En aquesta versi\u00f3, el sistema es desplega a AWS amb infraestructura escalable, persist\u00e8ncia a PostgreSQL i emmagatzematge segur de models i coneixement.<\/p>\n\n\n\n<p><strong>Entitat del repte:<\/strong> Hospital Universitari Joan XXIII<\/p>\n\n\n\n<p><strong>Nom Grup:<\/strong> Runtime Terror<\/p>\n\n\n\n<p><strong>Integrants:<\/strong> <\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Sonia Alfonso (<a>sonia.alfonso@estudiants.urv.cat<\/a>).<\/li>\n\n\n\n<li>\u00c0itor Olivares (<a>aitor.olivares@estudiants.urv.cat<\/a>)<\/li>\n\n\n\n<li>Marina Oteiza (<a>marina.oteiza@estudiants.urv.cat<\/a>)<\/li>\n\n\n\n<li>Javier Vega (<a>javier.vega@estudiants.urv.cat<\/a>)<\/li>\n<\/ul>\n\n\n\n<p><strong>Nom Projecte:<\/strong> PROGNOS (Intel\u00b7lig\u00e8ncia cl\u00ednica proactiva per a pacients cr\u00f2nics complexos, desplegada sobre AWS)<\/p>\n\n\n\n<p><strong>Descripci\u00f3:<\/strong>  Prognos mant\u00e9 els mateixos objectius cl\u00ednics del prototip original: classificaci\u00f3 PCC\/MACA\/NO, predicci\u00f3 de mortalitat a un any, predicci\u00f3 de visites a urg\u00e8ncies i suport conversacional per al personal sanitari i els pacients. La difer\u00e8ncia principal d&#8217;aquest projecte \u00e9s la seva industrialitzaci\u00f3 sobre AWS. La capa web continua oferint el portal del metge, el chatbot del pacient, el mapa assistencial, les estad\u00edstiques i el gemelo digital. Els serveis de classificaci\u00f3 i agents LLM es despleguen com a contenidors independents, mantenint la separaci\u00f3 funcional entre interf\u00edcie, infer\u00e8ncia cl\u00ednica i assistent conversacional. La persist\u00e8ncia deixa de dependre d&#8217;una base SQLite local i passa a RDS PostgreSQL, cosa que permet una explotaci\u00f3 multiusuari m\u00e9s robusta. Els models i la base de coneixement es gestionen des de S3, els secrets sensibles es mouen a AWS Secrets Manager i la descoberta entre serveis es resol amb Cloud Map. L&#8217;exposici\u00f3 p\u00fablica es fa a trav\u00e9s d&#8217;un Application Load Balancer, i l&#8217;execuci\u00f3 queda orquestrada amb ECS Fargate. Aquest desplegament converteix Prognos en una arquitectura cloud reprodu\u00efble amb Terraform, preparada per CI\/CD, validaci\u00f3 E2E i evoluci\u00f3 real cap a entorns cl\u00ednics m\u00e9s exigents, sense alterar el nucli funcional ni l&#8217;enfocament d&#8217;accessibilitat i interpretabilitat del sistema.<\/p>\n\n\n\n<p><strong>Reptes abordats: <\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Predicci\u00f3 del risc de mortalitat a un any vista: Permet identificar pacients amb pron\u00f2stic greu abans que la situaci\u00f3 cl\u00ednica es deteriori, facilitant la planificaci\u00f3 anticipada de cures pal\u00b7liatives i decisions compartides amb pacient i fam\u00edlia. <\/li>\n\n\n\n<li>Predicci\u00f3 de visites a urg\u00e8ncies a mes vista: Anticipa quins pacients cr\u00f2nics retornaran a urg\u00e8ncies el mes vinent, permetent intervencions proactives que redueixin pressi\u00f3 assistencial i millorin la continu\u00eftat de cures. <\/li>\n\n\n\n<li>Sistema recomanador de pacients PCC potencials: Detecta autom\u00e0ticament pacients sense classificar que presenten perfils cl\u00ednics compatibles amb PCC o MACA, evitant que quedin fora del circuit de seguiment especialitzat.<\/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; HTML5, CSS3, HCL, JavaScript (ES6+), Python 3.12<\/li>\n\n\n\n<li><strong>Frameworks i llibreries:<\/strong>\n<ul class=\"wp-block-list\">\n<li><em>Backend:<\/em>&nbsp;Flask, FastAPI, Uvicorn, Gunicorn, Pydantic<\/li>\n\n\n\n<li><em>ML\/Data:<\/em>&nbsp;XGBoost, scikit-learn, NumPy, Pandas<\/li>\n\n\n\n<li><em>LLM:<\/em>&nbsp;Google Gemini API, google-genai SDK<\/li>\n\n\n\n<li><em>Veu:<\/em>&nbsp;Gemini TTS, Gemini STT, SpeechRecognition, pydub<\/li>\n\n\n\n<li><em>Telefonia:<\/em>&nbsp;Twilio<\/li>\n\n\n\n<li><em>Frontend:<\/em>&nbsp;Chart.js, Leaflet.js, Leaflet.heat<\/li>\n\n\n\n<li><em>Infraestructura:<\/em>&nbsp;Terraform<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li><strong>Eines i plataformes:<\/strong>&nbsp;AWS ECS Fargate, Application Load Balancer, RDS PostgreSQL, S3, Secrets Manager, Cloud Map, CloudWatch, Docker, Git, GitHub Actions<\/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\/XaviVeC\/RuntimeTerror_Prognos\">https:\/\/github.com\/XaviVeC\/RuntimeTerror_Prognos<\/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\/IQAw2C9zLQyoSbAEl3OuVIe7AdZs7h63VQJwfGRAxICj5x4?e=AhyENZ\">https:\/\/rovira-my.sharepoint.com\/:b:\/g\/personal\/52460503-x_epp_urv_cat\/IQAw2C9zLQyoSbAEl3OuVIe7AdZs7h63VQJwfGRAxICj5x4?e=AhyENZ<\/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>1er Premi Prognos \u00e9s un sistema de suport cl\u00ednic per al Joan XXIII que combina classificaci\u00f3 ML, agents LLM i un chatbot accessible per a pacients cr\u00f2nics. En aquesta versi\u00f3, el sistema es desplega a AWS amb infraestructura escalable, persist\u00e8ncia a PostgreSQL i emmagatzematge segur de models i coneixement. Entitat del repte: Hospital Universitari Joan [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":1755,"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-1753","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\/circul-2.png","uagb_featured_image_src":{"full":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/circul-2.png",560,560,false],"thumbnail":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/circul-2-150x150.png",150,150,true],"medium":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/circul-2-300x300.png",300,300,true],"medium_large":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/circul-2.png",560,560,false],"large":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/circul-2.png",560,560,false],"1536x1536":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/circul-2.png",560,560,false],"2048x2048":["https:\/\/cloudlab.urv.cat\/catedracloud\/wp-content\/uploads\/2026\/03\/circul-2.png",560,560,false]},"uagb_author_info":{"display_name":"Carlos Molina","author_link":"https:\/\/cloudlab.urv.cat\/catedracloud\/author\/carlos-molina\/"},"uagb_comment_info":0,"uagb_excerpt":"1er Premi Prognos \u00e9s un sistema de suport cl\u00ednic per al Joan XXIII que combina classificaci\u00f3 ML, agents LLM i un chatbot accessible per a pacients cr\u00f2nics. En aquesta versi\u00f3, el sistema es desplega a AWS amb infraestructura escalable, persist\u00e8ncia a PostgreSQL i emmagatzematge segur de models i coneixement. Entitat del repte: Hospital Universitari Joan&hellip;","_links":{"self":[{"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/posts\/1753","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=1753"}],"version-history":[{"count":10,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/posts\/1753\/revisions"}],"predecessor-version":[{"id":1901,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/posts\/1753\/revisions\/1901"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/media\/1755"}],"wp:attachment":[{"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/media?parent=1753"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/categories?post=1753"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cloudlab.urv.cat\/catedracloud\/wp-json\/wp\/v2\/tags?post=1753"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}