1const i={cms:{page:{path:"/en/projects/prism-ai",is404:!1,isForbidden:!1,isRedirect:!1,seoProperties:{type:"article",url:"/en/projects/prism-ai",title:"PRISM-AI",description:"Development of artificial intelligence-based multiplex network for individualized risk stratification of prostate cancer.",locale:"en_US"},content:{id:"00000000-0000-0000-0000-000000000000",objectType:"article",permaLink:"/en/projects/prism-ai",language:"en",variants:["compact-header"],title:"PRISM-AI â AI network for risk stratification in prostate cancer",subtitle:"Biosystems",media:{objectType:"image",id:"00000000-0000-0000-0000-000000000000",src:"/assets/images/projects/prism-ai/hero-prism-ai.webp",caption:"",width:1888,height:1199},parts:[{id:"00000000-0000-0000-0000-000000000000",partType:"text-block",variants:["title-aside"],title:"Development of artificial intelligence-based multiplex network for individualized risk stratification of prostate cancer.",paragraphs:"<p>Prostate cancer (PCa) is the most frequently diagnosed malignancy among men in Western countries, with current risk stratification methods limited by subjectivity, diagnostic variability, and frequent misclassification. This study aims to develop and validate an <strong>artificial intelligenceâbased multiplex network</strong> that integrates genomic, transcriptomic, radiological, pathological, and clinical data to achieve individualized risk stratification for patients with newly diagnosed non-metastatic PCa.</p>"},{id:"00000000-0000-0000-0000-000000000000",partType:"text-block",paragraphs:"<p>The project will be conducted in two phases: a <strong>retrospective phase</strong>, analyzing data from 200 radical prostatectomy patients, and a <strong>prospective phase</strong>, enrolling 200 newly diagnosed biopsy-proven patients. Machine learning and deep learning algorithms will be applied to identify predictive features across data layers, building on the ARIADNE platform previously validated in breast cancer.</p><p>The main outcomes include improving prognostic accuracy for cancer-specific mortality, metastasis, recurrence, and treatment response, while reducing overtreatment and treatment-related morbidity. A secondary objective is to evaluate <strong>liquid biopsy approaches</strong> (RNA-seq of plasma and urine) as minimally invasive prognostic tools.</p><p>By bridging complex systems modeling with clinical oncology, this study aims to create a sustainable, cost-effective, and clinically implementable tool for personalized PCa management, ultimately improving patient quality of life and optimizing healthcare resources.</p>",image:{id:"00000000-0000-0000-0000-000000000000",objectType:"image",src:"/assets/images/projects/prism-ai/prism-ai-main.webp",width:1408,height:1408}},{id:"00000000-0000-0000-0000-000000000000",partType:"text-block",title:"Partners",paragraphs:"<p>University of Eastern Piedmont (coordinator)<br> University of Milan<br> University of Turin<br> University of Tor Vergata</p>"},{id:"00000000-0000-0000-0000-000000000000",partType:"text-block",variants:["disclaimer"],paragraphs:"<p>This project is supported by AIRC under Next Gen Clinician Scientist 2022 - ID. 28402 project â P.I. Carlotta Palumbo.</p>"}]}}}},e={data:i};export{i as data,e as default};
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.