Development and Validation of a Computational Histology Artificial Intelligence-Powered Predictive Biomarker for Selection of Chemotherapy in Advanced Pancreatic Cancer.
Andrew E Hendifar, Viswesh Krishna, Vrishab Krishna, Haochen Zhang, Asit Tarsode, Vivek Nimgaonkar, Katelyn Smith, Kawther Abdilleh, Snehal Sonawane, Akshay Neema, Ekin Tiu, Brent K Larson, Vladimir Kazarov, Natalie Moshayedi, Shawn Hutchinson, Daniela Bevacqua, Sudheer Doss, Alejandra Alvarez, Drew Watson, Waleed M Abuzeid, Barbara T Grünwald, Marcus Noel, Rashmi Samdani, Dove Keith, Rosalie C Sears, Davendra Sohal, Christos Fountzilas, Grainne M O'Kane, Robert C Grant, Arsen Osipov, Eric A Collisson, Lesli A Kiedrowski, Trevor J Royce, Anirudh R Joshi, Aatur D Singhi, Jennifer J Knox
{"title":"Development and Validation of a Computational Histology Artificial Intelligence-Powered Predictive Biomarker for Selection of Chemotherapy in Advanced Pancreatic Cancer.","authors":"Andrew E Hendifar, Viswesh Krishna, Vrishab Krishna, Haochen Zhang, Asit Tarsode, Vivek Nimgaonkar, Katelyn Smith, Kawther Abdilleh, Snehal Sonawane, Akshay Neema, Ekin Tiu, Brent K Larson, Vladimir Kazarov, Natalie Moshayedi, Shawn Hutchinson, Daniela Bevacqua, Sudheer Doss, Alejandra Alvarez, Drew Watson, Waleed M Abuzeid, Barbara T Grünwald, Marcus Noel, Rashmi Samdani, Dove Keith, Rosalie C Sears, Davendra Sohal, Christos Fountzilas, Grainne M O'Kane, Robert C Grant, Arsen Osipov, Eric A Collisson, Lesli A Kiedrowski, Trevor J Royce, Anirudh R Joshi, Aatur D Singhi, Jennifer J Knox","doi":"10.1200/JCO-25-02199","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Predictive biomarkers to guide selection of first-line chemotherapy for advanced pancreatic ductal adenocarcinoma (PDAC) are an unmet clinical need. This study used the Computational Histology Artificial Intelligence (CHAI) platform to develop and validate a histomorphology-based G-chemo versus F-chemo (GvF) biomarker that predicts benefit from first-line fluoropyrimidine-based (F-chemo) versus gemcitabine-based (G-chemo) regimens.</p><p><strong>Methods: </strong>The CHAI platform extracted quantitative histomorphologic features from whole-slide images of hematoxylin and eosin-stained diagnostic biopsies. In a multi-institutional development cohort, features associated with differential outcomes as measured by time to next treatment or death (TNTD) between F-chemo-treated and G-chemo-treated patients produced continuous biomarker scores, which were dichotomized into G-pref or F-pref results. The biomarker and threshold were locked. An independent validation cohort from the prospective COMPASS and Know Your Tumor studies assessed differential treatment outcomes by TNTD and overall survival (OS).</p><p><strong>Results: </strong>There were 477 patients (development: 178; validation: 299). In validation, among 173 F-pref patients, those treated with F-chemo had significantly better outcomes than G-chemo for both TNTD (<i>P</i> = .035; median TNTD: F-chemo 8.6 months; G-chemo 7.5 months) and OS (<i>P</i> = .003; median OS: F-chemo 14.4 months; G-chemo 11.7 months). Among 126 G-pref patients, G-chemo had significantly superior TNTD (<i>P</i> = .038; median TNTD: F-chemo 7.2 months; G-chemo 9.6 months), but no difference in OS (<i>P</i> = .5; median OS: F-chemo 12.4 months; G-chemo 14.3 months). In propensity score-weighted analysis, the biomarker predicted treatment effect (biomarker-treatment interaction TNTD <i>P</i> < .001; OS <i>P</i> = .005). RNA subtypes were associated with TNTD and OS but did not predict differential treatment effects (<i>P</i> = .3).</p><p><strong>Conclusion: </strong>The histomorphology-based GvF biomarker predicted differential treatment benefit of first-line GvF. This biomarker can guide optimal treatment selection for first-line therapy in advanced PDAC.</p>","PeriodicalId":15384,"journal":{"name":"Journal of Clinical Oncology","volume":" ","pages":"2496-2506"},"PeriodicalIF":44.7000,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Clinical Oncology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1200/JCO-25-02199","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/2/11 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: Predictive biomarkers to guide selection of first-line chemotherapy for advanced pancreatic ductal adenocarcinoma (PDAC) are an unmet clinical need. This study used the Computational Histology Artificial Intelligence (CHAI) platform to develop and validate a histomorphology-based G-chemo versus F-chemo (GvF) biomarker that predicts benefit from first-line fluoropyrimidine-based (F-chemo) versus gemcitabine-based (G-chemo) regimens.
Methods: The CHAI platform extracted quantitative histomorphologic features from whole-slide images of hematoxylin and eosin-stained diagnostic biopsies. In a multi-institutional development cohort, features associated with differential outcomes as measured by time to next treatment or death (TNTD) between F-chemo-treated and G-chemo-treated patients produced continuous biomarker scores, which were dichotomized into G-pref or F-pref results. The biomarker and threshold were locked. An independent validation cohort from the prospective COMPASS and Know Your Tumor studies assessed differential treatment outcomes by TNTD and overall survival (OS).
Results: There were 477 patients (development: 178; validation: 299). In validation, among 173 F-pref patients, those treated with F-chemo had significantly better outcomes than G-chemo for both TNTD (P = .035; median TNTD: F-chemo 8.6 months; G-chemo 7.5 months) and OS (P = .003; median OS: F-chemo 14.4 months; G-chemo 11.7 months). Among 126 G-pref patients, G-chemo had significantly superior TNTD (P = .038; median TNTD: F-chemo 7.2 months; G-chemo 9.6 months), but no difference in OS (P = .5; median OS: F-chemo 12.4 months; G-chemo 14.3 months). In propensity score-weighted analysis, the biomarker predicted treatment effect (biomarker-treatment interaction TNTD P < .001; OS P = .005). RNA subtypes were associated with TNTD and OS but did not predict differential treatment effects (P = .3).
Conclusion: The histomorphology-based GvF biomarker predicted differential treatment benefit of first-line GvF. This biomarker can guide optimal treatment selection for first-line therapy in advanced PDAC.
期刊介绍：
The Journal of Clinical Oncology serves its readers as the single most credible, authoritative resource for disseminating significant clinical oncology research. In print and in electronic format, JCO strives to publish the highest quality articles dedicated to clinical research. Original Reports remain the focus of JCO, but this scientific communication is enhanced by appropriately selected Editorials, Commentaries, Reviews, and other work that relate to the care of patients with cancer.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
