ICD-coded information on sites of metastasis in oncology real-world data is specific but not sensitive Published May 2018 Citation Parrinello, C.M., Seidl-Rathkopf, K.N., Bennette, C, Bourla, A.B., Nussbaum, N.C., Carson, K.R., Abernethy, A.P. . ISPOR Annual Meeting. . https://4076230.fs1.hubspotusercontent-na1.net/hubfs/4076230/flatiron-com-pdf/Sites-of-Mets-Structured-vs-Unstructured-ISPOR-2018-Poster_Vertical_Final_MM.pdf Authors: Sources:ISPOR Annual Meeting Share Posted inPublications More publicationsESMO AI & Digital OncologyNovember 2025Survival prediction in advanced NSCLC (aNSCLC) amid evolving standards of care (SOC): Digital twin modeling incorporating LLM-extracted clinical contextEstevez M, Griffith S, Williams T, et al.Publication summaryPublicationsMachine learningESMO AI & Digital OncologyNovember 2025A pan-tumor and pan-country approach to LLM-based extraction of systemic therapies from the electronic health recordViani N, Groizard L, Harrison K, et al. Publication summaryPublicationsMachine learningTumor agnosticData managementESMO AI & Digital OncologyNovember 2025Structuring GDPR-compliant private networks to enable LLM-Extracted oncology data on pseudonymized patient EHR data in EuropeEllsworth L, Groizard L, Stefan F, et al.Publication summaryPublicationsData scienceMachine learning