[{"data":1,"prerenderedAt":275},["ShallowReactive",2],{"case-study-infermedica-triage-en":3},{"id":4,"title":5,"body":6,"description":248,"extension":249,"meta":250,"navigation":251,"path":252,"seo":253,"stem":254,"subtitle":255,"tags":256,"technologies":260,"__hash__":274},"caseStudiesEn\u002Fcase-studies\u002Fen\u002Finfermedica-triage.md","Infermedica Triage – AI-Powered Virtual Triage Solution",{"type":7,"value":8,"toc":232},"minimark",[9,14,23,26,30,33,49,52,56,59,64,96,113,117,120,124,151,155,183,187,199,203,206],[10,11,13],"h2",{"id":12},"overview","Overview",[15,16,17,18,22],"p",{},"During my time at Infermedica, I was part of the engineering team building the ",[19,20,21],"strong",{},"Triage"," module—a flagship product used by healthcare organizations worldwide to automate patient intake and navigation.",[15,24,25],{},"The system uses advanced AI and a curated Medical Knowledge Base to conduct dynamic symptom-assessment interviews, providing users with instant triage recommendations and educational content.",[10,27,29],{"id":28},"the-business-challenge","The Business Challenge",[15,31,32],{},"Healthcare providers face a massive influx of patients, many of whom are unsure about the level of care they need. This leads to:",[34,35,36,40,43,46],"ul",{},[37,38,39],"li",{},"Overcrowded emergency departments (ED).",[37,41,42],{},"Long wait times for patients with urgent needs.",[37,44,45],{},"High administrative burden on medical staff.",[37,47,48],{},"Inconsistent symptom reporting.",[15,50,51],{},"The goal was to provide a \"Digital Front Door\" that could accurately assess symptoms 24\u002F7 and refer patients to the most appropriate service (telemedicine, primary care, or emergency).",[10,53,55],{"id":54},"the-solution","The Solution",[15,57,58],{},"We built a highly configurable, multi-platform triage solution that leverages Natural Language Processing (NLP) and probabilistic modeling to simulate a doctor's initial interview.",[60,61,63],"h3",{"id":62},"key-features","Key Features",[34,65,66,72,78,84,90],{},[37,67,68,71],{},[19,69,70],{},"Intelligent Survey:"," A dynamic interview that adapts based on user input, risk factors, and demographic data.",[37,73,74,77],{},[19,75,76],{},"NLP Integration:"," Understanding free-text symptom descriptions to initiate the assessment.",[37,79,80,83],{},[19,81,82],{},"Triage Recommendations:"," Providing one of five care levels (e.g., Self-care, See a doctor, Emergency) based on clinical protocols.",[37,85,86,89],{},[19,87,88],{},"Medical Education:"," Access to evidence-based articles reviewed by medical doctors.",[37,91,92,95],{},[19,93,94],{},"Multi-language Support:"," Available in over 26 languages to serve a global audience.",[97,98,101,102],"figure",{"className":99},[100],"my-12","\n  ",[103,104],"img",{"src":105,"alt":106,"className":107},"\u002Fcase-studies\u002Finfermedica-triage\u002Fmain.png","Infermedica Triage Interface",[108,109,110,111,112],"w-full","rounded-2xl","border","border-smoke-500","shadow-sm",[10,114,116],{"id":115},"technical-contributions","Technical Contributions",[15,118,119],{},"My role involved working across the stack to ensure the platform's reliability, scalability, and clinical accuracy.",[60,121,123],{"id":122},"backend-api-development","Backend & API Development",[34,125,126,137,144],{},[37,127,128,129,132,133,136],{},"Developed and optimized APIs using ",[19,130,131],{},"Python"," and ",[19,134,135],{},"FastAPI",".",[37,138,139,140,143],{},"Contributed to the ",[19,141,142],{},"Inference Engine"," integration, handling complex probabilistic models for symptom analysis.",[37,145,146,147,150],{},"Implemented and managed ",[19,148,149],{},"vector stores"," to enhance NLP capabilities and condition matching.",[60,152,154],{"id":153},"architecture-infrastructure","Architecture & Infrastructure",[34,156,157,171,180],{},[37,158,159,160,163,164,167,168,136],{},"Worked within a ",[19,161,162],{},"microservices architecture"," deployed on ",[19,165,166],{},"Google Cloud Platform (GCP)"," using ",[19,169,170],{},"Kubernetes",[37,172,173,174,132,177,136],{},"Ensured compliance with strict healthcare standards, including ",[19,175,176],{},"HIPAA",[19,178,179],{},"GDPR",[37,181,182],{},"Integrated CI\u002FCD pipelines to maintain high code quality and deployment frequency.",[60,184,186],{"id":185},"frontend-integration","Frontend Integration",[34,188,189,196],{},[37,190,191,192,195],{},"Developed responsive UI components in ",[19,193,194],{},"Vue.js"," for the white-label version of the symptom checker.",[37,197,198],{},"Ensured the interface was accessible and followed medical device UI standards.",[10,200,202],{"id":201},"impact-results","Impact & Results",[15,204,205],{},"The Infermedica Triage solution has delivered significant real-world value:",[34,207,208,214,220,226],{},[37,209,210,213],{},[19,211,212],{},"35% Increase in completion rates"," for major national health services.",[37,215,216,219],{},[19,217,218],{},"39% Improvement in operational efficiency"," for clinical providers.",[37,221,222,225],{},[19,223,224],{},"Reduced ED visits"," by correctly identifying patients who can be treated via telemedicine or self-care.",[37,227,228,231],{},[19,229,230],{},"MDR Class IIb Certification",", proving the clinical safety and effectiveness of the solution.",{"title":233,"searchDepth":234,"depth":234,"links":235},"",2,[236,237,238,242,247],{"id":12,"depth":234,"text":13},{"id":28,"depth":234,"text":29},{"id":54,"depth":234,"text":55,"children":239},[240],{"id":62,"depth":241,"text":63},3,{"id":115,"depth":234,"text":116,"children":243},[244,245,246],{"id":122,"depth":241,"text":123},{"id":153,"depth":241,"text":154},{"id":185,"depth":241,"text":186},{"id":201,"depth":234,"text":202},"A world-class diagnostic solution that helps patients understand their symptoms and guides them to the right level of care using AI and a vast Medical Knowledge Base.","md",{},true,"\u002Fcase-studies\u002Fen\u002Finfermedica-triage",{"title":5,"description":248},"case-studies\u002Fen\u002Finfermedica-triage","Intelligent Symptom Assessment and Patient Navigation",[194,131,135,257,258,259,170],"LLM","NLP","Google Cloud",[261,263,265,267,269,271],{"name":194,"icon":262},"logos:vue",{"name":131,"icon":264},"logos:python",{"name":135,"icon":266},"logos:fastapi-icon",{"name":259,"icon":268},"logos:google-cloud",{"name":170,"icon":270},"logos:kubernetes",{"name":272,"icon":273},"PostgreSQL","logos:postgresql","Zr82b3-l3hmLCVXa3JDw3SD4SksYvUTj1qu48N18deU",1780334809939]