[{"data":1,"prerenderedAt":84},["ShallowReactive",2],{"work-healthcare-data-analysis":3,"work-next-\u002Fwork\u002Fhealthcare-data-analysis":81},{"id":4,"title":5,"accent":6,"body":7,"client":50,"cover":51,"coverAlt":51,"description":52,"duration":53,"extension":54,"featured":55,"industry":56,"meta":57,"navigation":58,"order":59,"path":60,"quote":51,"results":61,"seo":68,"services":69,"stack":71,"stem":78,"year":79,"__hash__":80},"work\u002Fwork\u002Fhealthcare-data-analysis.md","Clinical data analysis for a hospital network","#0891B2",{"type":8,"value":9,"toc":43},"minimark",[10,15,19,23,36,40],[11,12,14],"h2",{"id":13},"challenge","Challenge",[16,17,18],"p",{},"Clinicians and administrators were spending days pulling cohorts and spotting patterns across fragmented records. Risk flags depended on individual experience.",[11,20,22],{"id":21},"what-we-built","What we built",[24,25,26,30,33],"ul",{},[27,28,29],"li",{},"A de-identified analytics dataset assembled from the hospital information system with a documented data-flow and access model.",[27,31,32],{},"Classification models for readmission and deterioration risk, with feature importance shown alongside every score.",[27,34,35],{},"A clinician-facing dashboard for cohort exploration and a daily flagged-patient list.",[11,37,39],{"id":38},"results","Results",[16,41,42],{},"Risk flags were around 30% more accurate than the manual process in retrospective evaluation, and cohort analyses that took days now take minutes. All models are advisory; clinicians make the call.",{"title":44,"searchDepth":45,"depth":45,"links":46},"",2,[47,48,49],{"id":13,"depth":45,"text":14},{"id":21,"depth":45,"text":22},{"id":38,"depth":45,"text":39},"Hospital network (Pakistan)",null,"Machine-learning analysis of patient records that surfaces patterns and risk indicators for clinicians.","12 weeks","md",false,"Healthcare",{},true,3,"\u002Fwork\u002Fhealthcare-data-analysis",[62,65],{"value":63,"label":64},"30%","improvement in early risk-flag accuracy vs. manual triage",{"value":66,"label":67},"Minutes","not days, for cohort analysis",{"title":5,"description":52},[70],"data-analytics-predictive-ai",[72,73,74,75,76,77],"Python","scikit-learn","Pandas","FastAPI","Docker","Azure","work\u002Fhealthcare-data-analysis","2023","XPvfAoeJW_ccpAi66py2uPLN6X1w8EwLY7eaftC4S1E",{"path":82,"title":83},"\u002Fwork\u002Fsaas-onboarding-assistant","Onboarding assistant for a B2B SaaS product",1792973683819]