Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Xiyao, Fu, Kai
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.26685
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911351962599424
author Yu, Xiyao
Fu, Kai
author_facet Yu, Xiyao
Fu, Kai
contents Background: Despite high in-silico performance (AUC >0.80), 85% of AI cancer biomarkers fail clinical translation, exposing a critical algorithm-to-outcome gap. Methods: We introduce the Algorithm-to-Outcome Concordance (AOC) framework, integrating model accuracy (AUC), clinical correlation (Corr), and trial heterogeneity. We validated AOC across 6 neoantigen vaccine trials (2017-2025) and 3 independent melanoma immunotherapy cohorts (n=188 patients). Results: AOC ranged 0.18-0.79 across trials, with failed trials (ORR <15%) showing AOC <0.40. External validation revealed unstable algorithm-outcome correlation (C-index: 0.49-0.61, p>0.05), demonstrating the necessity of explicit concordance assessment. Conclusions: AOC provides a quantitative framework for pre-trial risk assessment and adaptive trial design. Prospective validation is underway in KEYNOTE-942 extension studies.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26685
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying AI-to-Clinical Translation: The Algorithm-to-Outcome Concordance (AOC) Framework
Yu, Xiyao
Fu, Kai
Quantitative Methods
Background: Despite high in-silico performance (AUC >0.80), 85% of AI cancer biomarkers fail clinical translation, exposing a critical algorithm-to-outcome gap. Methods: We introduce the Algorithm-to-Outcome Concordance (AOC) framework, integrating model accuracy (AUC), clinical correlation (Corr), and trial heterogeneity. We validated AOC across 6 neoantigen vaccine trials (2017-2025) and 3 independent melanoma immunotherapy cohorts (n=188 patients). Results: AOC ranged 0.18-0.79 across trials, with failed trials (ORR <15%) showing AOC <0.40. External validation revealed unstable algorithm-outcome correlation (C-index: 0.49-0.61, p>0.05), demonstrating the necessity of explicit concordance assessment. Conclusions: AOC provides a quantitative framework for pre-trial risk assessment and adaptive trial design. Prospective validation is underway in KEYNOTE-942 extension studies.
title Quantifying AI-to-Clinical Translation: The Algorithm-to-Outcome Concordance (AOC) Framework
topic Quantitative Methods
url https://arxiv.org/abs/2510.26685