The analytical and clinical validity of AI algorithms to score TILs in TNBC: can we use different machine learning models interchangeably?
Vidal J, Tsiknakis N, Staaf J, Bosch A, Ehinger A, Nimeus E, Salgado R, Bai Y, Rimm D, Hartman J, Acs B. The analytical and clinical validity of AI algorithms to score TILs in TNBC: can we use different machine learning models interchangeably? EClinicalMedicine 2024, 78: 102928. DOI: 10.1016/j.eclinm.2024.102928.Peer-Reviewed Original ResearchTriple-negative breast cancerTumor-infiltrating lymphocytesBreast Cancer Research FoundationPrognostic validityMetastatic triple-negative breast cancerDisease-free survival endpointsHazard ratioHost anti-tumor immunityScored tumor infiltrating lymphocytesTumor-infiltrating lymphocyte scoresTriple-negative breast cancer patientsYears median follow-upTumour-infiltrating lymphocyte assessmentAnti-tumor immunityMedian follow-upIndependent prospective cohortTNBC tumorsPrognostic potentialProspective cohortBreast cancerPrognostic performanceAnalytic cohortFollow-upSchool of MedicineSwedish Society for Medical Research