Assessing Algorithmic Fairness With a Multimodal Artificial Intelligence Model in Men of African and Non-African Origin on NRG Oncology Prostate Cancer Phase III Trials.
Mack Roach, Jingbin Zhang, Osama Mohamad, Douwe van der Wal, Jeffry P Simko, Sandy DeVries, Huei-Chung Huang, Songwan Joun, Edward M Schaeffer, Todd M Morgan, Jessica Keim-Malpass, Emmalyn Chen, Rikiya Yamashita, Jedidiah M Monson, Farah Naz, James Wallace, Jean-Paul Bahary, Derek Wilke, Sonny Batra, Gregory B Biedermann, Sergio Faria, Lindsay Hwang, Howard M Sandler, Daniel E Spratt, Stephanie L Pugh, Andre Esteva, Phuoc T Tran, Felix Y Feng
{"title":"Assessing Algorithmic Fairness With a Multimodal Artificial Intelligence Model in Men of African and Non-African Origin on NRG Oncology Prostate Cancer Phase III Trials.","authors":"Mack Roach, Jingbin Zhang, Osama Mohamad, Douwe van der Wal, Jeffry P Simko, Sandy DeVries, Huei-Chung Huang, Songwan Joun, Edward M Schaeffer, Todd M Morgan, Jessica Keim-Malpass, Emmalyn Chen, Rikiya Yamashita, Jedidiah M Monson, Farah Naz, James Wallace, Jean-Paul Bahary, Derek Wilke, Sonny Batra, Gregory B Biedermann, Sergio Faria, Lindsay Hwang, Howard M Sandler, Daniel E Spratt, Stephanie L Pugh, Andre Esteva, Phuoc T Tran, Felix Y Feng","doi":"10.1200/CCI-24-00284","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Artificial intelligence (AI) tools could improve clinical decision making or exacerbate inequities because of bias. African American (AA) men reportedly have a worse prognosis for prostate cancer (PCa) and are underrepresented in the development genomic biomarkers. We assess the generalizability of tools developed using a multimodal AI (MMAI) deep learning system using digital histopathology and clinical data from NRG/Radiation Therapy Oncology Group PCa trials across racial subgroups.</p><p><strong>Methods: </strong>In total, 5,708 patients from five randomized phase III trials were included. Two MMAI algorithms were evaluated: (1) the distant metastasis (DM) MMAI model optimized to predict risk of DM, and (2) the PCa-specific mortality (PCSM) MMAI model optimized to focus on prediction death in the presence of DM (DDM). The prognostic performance of the MMAI algorithms was evaluated in AA and non-AA subgroups using time to DM (primary end point) and time to DDM (secondary end point). Exploratory end points included time to biochemical failure and overall survival with Fine-Gray or Cox proportional hazards models. Cumulative incidence estimates were computed for time-to-event end points and compared using Gray's test.</p><p><strong>Results: </strong>There were 948 (16.6%) AA patients, 4,731 non-AA patients (82.9%), and 29 (0.5%) patients with unknown or missing race status. The DM-MMAI algorithm showed a strong prognostic signal for DM in the AA (subdistribution hazard ratio [sHR], 1.2 [95% CI, 1.0 to 1.3]; <i>P</i> = .007) and non-AA subgroups (sHR, 1.4 [95% CI, 1.3 to 1.5]; <i>P</i> < .001). Similarly, the PCSM-MMAI score showed a strong prognostic signal for DDM in both AA (sHR, 1.3 [95% CI, 1.1 to 1.5]; <i>P</i> = .001) and non-AA subgroups (sHR, 1.5 [95% CI, 1.4 to 1.6]; <i>P</i> < .001), with similar distributions of risk.</p><p><strong>Conclusion: </strong>Using cooperative group data sets with a racially diverse population, the MMAI algorithm performed well across racial subgroups without evidence of algorithmic bias.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2400284"},"PeriodicalIF":3.3000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JCO Clinical Cancer Informatics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1200/CCI-24-00284","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/5/9 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: Artificial intelligence (AI) tools could improve clinical decision making or exacerbate inequities because of bias. African American (AA) men reportedly have a worse prognosis for prostate cancer (PCa) and are underrepresented in the development genomic biomarkers. We assess the generalizability of tools developed using a multimodal AI (MMAI) deep learning system using digital histopathology and clinical data from NRG/Radiation Therapy Oncology Group PCa trials across racial subgroups.
Methods: In total, 5,708 patients from five randomized phase III trials were included. Two MMAI algorithms were evaluated: (1) the distant metastasis (DM) MMAI model optimized to predict risk of DM, and (2) the PCa-specific mortality (PCSM) MMAI model optimized to focus on prediction death in the presence of DM (DDM). The prognostic performance of the MMAI algorithms was evaluated in AA and non-AA subgroups using time to DM (primary end point) and time to DDM (secondary end point). Exploratory end points included time to biochemical failure and overall survival with Fine-Gray or Cox proportional hazards models. Cumulative incidence estimates were computed for time-to-event end points and compared using Gray's test.
Results: There were 948 (16.6%) AA patients, 4,731 non-AA patients (82.9%), and 29 (0.5%) patients with unknown or missing race status. The DM-MMAI algorithm showed a strong prognostic signal for DM in the AA (subdistribution hazard ratio [sHR], 1.2 [95% CI, 1.0 to 1.3]; P = .007) and non-AA subgroups (sHR, 1.4 [95% CI, 1.3 to 1.5]; P < .001). Similarly, the PCSM-MMAI score showed a strong prognostic signal for DDM in both AA (sHR, 1.3 [95% CI, 1.1 to 1.5]; P = .001) and non-AA subgroups (sHR, 1.5 [95% CI, 1.4 to 1.6]; P < .001), with similar distributions of risk.
Conclusion: Using cooperative group data sets with a racially diverse population, the MMAI algorithm performed well across racial subgroups without evidence of algorithmic bias.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
