학술논문
External Validation of a Digital Pathology-based Multimodal Artificial Intelligence Architecture in the NRG/RTOG 9902 Phase 3 Trial.
Document Type
Academic Journal
Author
Ross AE; Department of Urology, Northwestern Medicine, Chicago, IL, USA. Electronic address: ashley.ross@nm.org.; Zhang J; Artera Inc., Los Altos, CA, USA.; Huang HC; Artera Inc., Los Altos, CA, USA.; Yamashita R; Artera Inc., Los Altos, CA, USA.; Keim-Malpass J; Artera Inc., Los Altos, CA, USA.; Simko JP; University of California San Francisco, San Francisco, CA, USA.; DeVries S; University of California San Francisco, San Francisco, CA, USA.; Morgan TM; University of Michigan, Ann Arbor, MI, USA.; Souhami L; The Research Institute of the McGill University Health Centre (MUHC), Montreal, QC, Canada.; Dobelbower MC; University of Alabama at Birmingham Cancer Center, Birmingham, AL, USA.; McGinnis LS; Novant Health Presbyterian Medical Center, Charlotte, NC, USA.; Jones CU; Sutter Medical Center Sacramento, Sacramento, CA, USA.; Dess RT; University of Michigan, Ann Arbor, MI, USA.; Zeitzer KL; Albert Einstein Medical Center, Philadelphia, PA, USA.; Choi K; Brooklyn MB-CCOP/SUNY Downstate, Brooklyn, NY, USA.; Hartford AC; Dartmouth Hitchcock Medical Center, Lebanon, NH, USA.; Michalski JM; Washington University School of Medicine, Saint Louis, MO, USA.; Raben A; Christiana Care Health Services, Inc. CCOP, Wilmington, DE, USA.; Gomella LG; Thomas Jefferson University Hospital, Philadelphia, PA, USA.; Sartor AO; Tulane University Health Sciences Center, New Orleans, LA, USA.; Rosenthal SA; Sutter Medical Center Sacramento, Sacramento, CA, USA.; Sandler HM; Cedars-Sinai Medical Center, Los Angeles, CA, USA.; Spratt DE; UH Seidman Cancer Center, Case Western Reserve University, Cleveland, OH, USA.; Pugh SL; NRG Oncology Statistics and Data Management Center and American College of Radiology, Philadelphia, PA, USA.; Mohamad O; University of California San Francisco, San Francisco, CA, USA.; Esteva A; Artera Inc., Los Altos, CA, USA.; Chen E; Artera Inc., Los Altos, CA, USA.; Schaeffer EM; Northwestern University, Chicago, IL, USA.; Tran PT; University of Maryland, Baltimore, MD, USA.; Feng FY; University of California San Francisco, San Francisco, CA, USA.
Source
Publisher: Elsevier B.V Country of Publication: Netherlands NLM ID: 101724904 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2588-9311 (Electronic) Linking ISSN: 25889311 NLM ISO Abbreviation: Eur Urol Oncol Subsets: MEDLINE
Subject
Language
English
Abstract
Background: Accurate risk stratification is critical to guide management decisions in localized prostate cancer (PCa). Previously, we had developed and validated a multimodal artificial intelligence (MMAI) model generated from digital histopathology and clinical features. Here, we externally validate this model on men with high-risk or locally advanced PCa treated and followed as part of a phase 3 randomized control trial.
Objective: To externally validate the MMAI model on men with high-risk or locally advanced PCa treated and followed as part of a phase 3 randomized control trial.
Design, Setting, and Participants: Our validation cohort included 318 localized high-risk PCa patients from NRG/RTOG 9902 with available histopathology (337 [85%] of the 397 patients enrolled into the trial had available slides, of which 19 [5.6%] failed due to poor image quality).
Outcome Measurements and Statistical Analysis: Two previously locked prognostic MMAI models were validated for their intended endpoint: distant metastasis (DM) and PCa-specific mortality (PCSM). Individual clinical factors and the number of National Comprehensive Cancer Network (NCCN) high-risk features served as comparators. Subdistribution hazard ratio (sHR) was reported per standard deviation increase of the score with corresponding 95% confidence interval (CI) using Fine-Gray or Cox proportional hazards models.
Results and Limitations: The DM and PCSM MMAI algorithms were significantly and independently associated with the risk of DM (sHR [95% CI] = 2.33 [1.60-3.38], p < 0.001) and PCSM, respectively (sHR [95% CI] = 3.54 [2.38-5.28], p < 0.001) when compared against other prognostic clinical factors and NCCN high-risk features. The lower 75% of patients by DM MMAI had estimated 5- and 10-yr DM rates of 4% and 7%, and the highest quartile had average 5- and 10-yr DM rates of 19% and 32%, respectively (p < 0.001). Similar results were observed for the PCSM MMAI algorithm.
Conclusions: We externally validated the prognostic ability of MMAI models previously developed among men with localized high-risk disease. MMAI prognostic models further risk stratify beyond the clinical and pathological variables for DM and PCSM in a population of men already at a high risk for disease progression. This study provides evidence for consistent validation of our deep learning MMAI models to improve prognostication and enable more informed decision-making for patient care.
Patient Summary: This paper presents a novel approach using images from pathology slides along with clinical variables to validate artificial intelligence (computer-generated) prognostic models. When implemented, clinicians can offer a more personalized and tailored prognostic discussion for men with localized prostate cancer.
(Copyright © 2024 European Association of Urology. Published by Elsevier B.V. All rights reserved.)
Objective: To externally validate the MMAI model on men with high-risk or locally advanced PCa treated and followed as part of a phase 3 randomized control trial.
Design, Setting, and Participants: Our validation cohort included 318 localized high-risk PCa patients from NRG/RTOG 9902 with available histopathology (337 [85%] of the 397 patients enrolled into the trial had available slides, of which 19 [5.6%] failed due to poor image quality).
Outcome Measurements and Statistical Analysis: Two previously locked prognostic MMAI models were validated for their intended endpoint: distant metastasis (DM) and PCa-specific mortality (PCSM). Individual clinical factors and the number of National Comprehensive Cancer Network (NCCN) high-risk features served as comparators. Subdistribution hazard ratio (sHR) was reported per standard deviation increase of the score with corresponding 95% confidence interval (CI) using Fine-Gray or Cox proportional hazards models.
Results and Limitations: The DM and PCSM MMAI algorithms were significantly and independently associated with the risk of DM (sHR [95% CI] = 2.33 [1.60-3.38], p < 0.001) and PCSM, respectively (sHR [95% CI] = 3.54 [2.38-5.28], p < 0.001) when compared against other prognostic clinical factors and NCCN high-risk features. The lower 75% of patients by DM MMAI had estimated 5- and 10-yr DM rates of 4% and 7%, and the highest quartile had average 5- and 10-yr DM rates of 19% and 32%, respectively (p < 0.001). Similar results were observed for the PCSM MMAI algorithm.
Conclusions: We externally validated the prognostic ability of MMAI models previously developed among men with localized high-risk disease. MMAI prognostic models further risk stratify beyond the clinical and pathological variables for DM and PCSM in a population of men already at a high risk for disease progression. This study provides evidence for consistent validation of our deep learning MMAI models to improve prognostication and enable more informed decision-making for patient care.
Patient Summary: This paper presents a novel approach using images from pathology slides along with clinical variables to validate artificial intelligence (computer-generated) prognostic models. When implemented, clinicians can offer a more personalized and tailored prognostic discussion for men with localized prostate cancer.
(Copyright © 2024 European Association of Urology. Published by Elsevier B.V. All rights reserved.)