biostudies-literatureAung TNNCI NIH HHSe2518906https://www.ebi.ac.uk/biostudies/studies/S-EPMC12232186biostudies-literatureUnknown8(7)<h4>Importance</h4>Tumor-infiltrating lymphocytes (TILs) are a provocative biomarker in melanoma, influencing diagnosis, prognosis, and immunotherapy outcomes; however, traditional pathologist-read TIL assessment on hematoxylin and eosin-stained slides is prone to interobserver variability, leading to inconsistent clinical decisions. Therefore, development of newer TIL scoring approaches that produce more reliable and consistent readouts is important.<h4>Objective</h4>To evaluate the analytical and clinical validity of a machine learning algorithm for TIL quantification in melanoma compared with traditional pathologist-read methods.<h4>Design, setting, and participants</h4>This multioperator, global, multi-institutional prognostic study compared TIL scoring reproducibility between traditioJAMA network openPathologist-Read vs AI-Driven Assessment of Tumor-Infiltrating Lymphocytes in Melanoma.PMC12232186P50 CA121974P50 CA225450U54 CA263001P50 CA196530P30 CA016359Su DTan SXOsman IGama JVesely MDFortarezza FRau TRimm DLTsiknakis NAcs BBracero YOliveira RCWilmott JTzoras EGonzalez MSPlummer JDema ABrautigam KWong PFQueipo Gutierrez FJSolass WJovic VPezzuto FNourmohammadi SBosic MHe MCowper SSun WGullo IGavirelatou NSinnberg TSzymonski KSaenger YAung TNKreis BPinto JPop OVigdorovits AVignati DBates KPoulios CWarrell JBarna RLiu MSkok KNeppl CVidal JMIllabochaca IToli MAPillar NPlotar VMicevic GLazar BBurela SBoyaci CMaher NSerbes EDStanowska OThimm FShafi SHacihasanoglu EOlinca MBai YSzasz MCserni GDjureinovic DSteen SChenhao ZGomes Pinto DPrieto VChan NNNBosisio FMohacsi RHartman JfalsePathologist-Read vs AI-Driven Assessment of Tumor-Infiltrating Lymphocytes in Melanoma.<h4>Importance</h4>Tumor-infiltrating lymphocytes (TILs) are a provocative biomarker in melanoma, influencing diagnosis, prognosis, and immunotherapy outcomes; however, traditional pathologist-read TIL assessment on hematoxylin and eosin-stained slides is prone to interobserver variability, leading to inconsistent clinical decisions. Therefore, development of newer TIL scoring approaches that produce more reliable and consistent readouts is important.<h4>Objective</h4>To evaluate the analytical and clinical validity of a machine learning algorithm for TIL quantification in melanoma compared with traditional pathologist-read methods.<h4>Design, setting, and participants</h4>This multioperator, global, multi-institutional prognostic study compared TIL scoring reproducibility between traditio2025-01-01T00:00:00Z2025 Jul2026-06-06T17:23:56.809Z2026-06-03T03:10:16.585ZS-EPMC122321864060834110.1001/jamanetworkopen.2025.18906