{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Vidal JM"],"funding":["Breast Cancer Research Foundation","NCATS NIH HHS","Vetenskapsrådet","Svenska Sällskapet för Medicinsk Forskning","Lunds Universitet"],"pagination":["102928"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11615110"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["78"],"pubmed_abstract":["<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 coh"],"journal":["EClinicalMedicine"],"pubmed_title":["The analytical and clinical validity of AI algorithms to score TILs in TNBC: can we use different machine learning models interchangeably?"],"pmcid":["PMC11615110"],"funding_grant_id":["2022-06725","2021-03061","UL1 TR001863"],"pubmed_authors":["Acs B","Staaf J","Bosch A","Nimeus E","Vidal JM","Ehinger A","Salgado R","Bai Y","Rimm DL","Hartman J","Tsiknakis N"],"additional_accession":[]},"is_claimable":false,"name":"The analytical and clinical validity of AI algorithms to score TILs in TNBC: can we use different machine learning models interchangeably?","description":"<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 coh","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Dec","modification":"2026-06-02T09:12:06.008Z","creation":"2025-04-06T17:33:08.328Z"},"accession":"S-EPMC11615110","cross_references":{"pubmed":["39634035"],"doi":["10.1016/j.eclinm.2024.102928"]}}