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
JCO Clinical Cancer Informatics · 2025
DOI: 10.1200/cci-24-00284 ↗Kurz gefasst
Klinische Studie (Phase III) in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von Mack Roach und 27 weiteren Autor:innen. Beteiligte Einrichtung: UCSF Medical Center, San Francisco, CA. Hauptthemen laut MEDLINE: Algorithms, Artificial Intelligence, Prostatic Neoplasms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- UCSF Medical Center, San Francisco, CA.
- Artera, Santa Barbara, CA.
- University of California San Francisco, San Francisco, CA.
- Northwestern University, Chicago, IL.
- University of Michigan Comprehensive Cancer Center, Ann Arbor, MI.
- Hematology-Oncology Medical Group of Fresno Inc, Fresno, CA.
ORCID-Profile: Mack Roach, Osama Mohamad, Todd M Morgan, Jessica Keim-Malpass, Derek Wilke, Howard M Sandler, Daniel E Spratt, Phuoc T Tran, Felix Y Feng
Förderung
- NCI NIH HHS
Zitieren
APA
Roach, M., Zhang, J., Mohamad, O., van der Wal, D., Simko, J. P., DeVries, S., Huang, H. C., Joun, S., Schaeffer, E. M., Morgan, T. M., Keim-Malpass, J., Chen, E., Yamashita, R., Monson, J. M., Naz, F., Wallace, J., Bahary, J. P., Wilke, D., Batra, S., …, & Feng, F. Y. (2025). 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. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-24-00284
Vancouver
Roach M, Zhang J, Mohamad O, van der Wal D, Simko JP, DeVries S, et al. 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. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-24-00284
BibTeX
@article{Roach2025,
author = {Roach, Mack and Zhang, Jingbin and Mohamad, Osama and van der Wal, Douwe and Simko, Jeffry P and DeVries, Sandy and Huang, Huei-Chung and Joun, Songwan and Schaeffer, Edward M and Morgan, Todd M and Keim-Malpass, Jessica and Chen, Emmalyn and Yamashita, Rikiya and Monson, Jedidiah M and Naz, Farah and Wallace, James and Bahary, Jean-Paul and Wilke, Derek and Batra, Sonny and Biedermann, Gregory B and Faria, Sergio and Hwang, Lindsay and Sandler, Howard M and Spratt, Daniel E and Pugh, Stephanie L and Esteva, Andre and Tran, Phuoc T and Feng, Felix Y},
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},
journal = {JCO Clinical Cancer Informatics},
year = {2025},
doi = {10.1200/cci-24-00284}
}
EUVIMED