biostudies-literatureVidal JMBreast Cancer Research FoundationNCATS NIH HHSVetenskapsrådetSvenska Sällskapet för Medicinsk ForskningLunds Universitet102928https://www.ebi.ac.uk/biostudies/studies/S-EPMC11615110biostudies-literatureUnknown78<h4>Background</h4>Pathologist-read tumor-infiltrating lymphocytes (TILs) have showcased their predictive and prognostic potential for early and metastatic triple-negative breast cancer (TNBC) but it is still subject to variability. Artificial intelligence (AI) is a promising approach toward eliminating variability and objectively automating TILs assessment. However, demonstrating robust analytical and prognostic validity is the key challenge currently preventing their integration into clinical workflows.<h4>Methods</h4>We evaluated the impact of ten AI models on TILs scoring, emphasizing their distinctions in TILs analytical and prognostic validity. Several AI-based TILs scoring models (seven developed and three previously validated AI models) were tested in a retrospective analytical cohEClinicalMedicineThe analytical and clinical validity of AI algorithms to score TILs in TNBC: can we use different machine learning models interchangeably?PMC116151102022-067252021-03061UL1 TR001863Acs BStaaf JBosch ANimeus EVidal JMEhinger ASalgado RBai YRimm DLHartman JTsiknakis NfalseThe analytical and clinical validity of AI algorithms to score TILs in TNBC: can we use different machine learning models interchangeably?<h4>Background</h4>Pathologist-read tumor-infiltrating lymphocytes (TILs) have showcased their predictive and prognostic potential for early and metastatic triple-negative breast cancer (TNBC) but it is still subject to variability. Artificial intelligence (AI) is a promising approach toward eliminating variability and objectively automating TILs assessment. However, demonstrating robust analytical and prognostic validity is the key challenge currently preventing their integration into clinical workflows.<h4>Methods</h4>We evaluated the impact of ten AI models on TILs scoring, emphasizing their distinctions in TILs analytical and prognostic validity. Several AI-based TILs scoring models (seven developed and three previously validated AI models) were tested in a retrospective analytical coh2024-01-01T00:00:00Z2024 Dec2026-06-02T09:12:06.008Z2025-04-06T17:33:08.328ZS-EPMC116151103963403510.1016/j.eclinm.2024.102928