Prostate cancer is among the most commonly diagnosed cancers in men worldwide, underscoring the necessity of effective screening tools for early detection and mortality prevention [1]. Risk calculators based on patient demographics, clinical parameters, and biomarker data help define individualized risk and can assist providers and patients to drive personalized screening pathways. Novel prostate cancer risk calculators should be instrumental in reducing over-diagnosis while enhancing early detection of clinical-significant cases, with the goals of decreasing mortality rates while also decreasing overtreatment of biologically indolent cancers. However, a significant concern with many of the studies reporting novel risk calculators is their lack of external validity. This raises questions about the accuracy and reliability of these tools across different populations, which could lead to missed diagnoses or over-diagnosis in certain patient groups.
We eagerly read the systematic review by Denijs et al. reporting on risk calculators for the detection of prostate cancer [2]. Recognizing that PSA-based prostate cancer screening is fraught with lack of specificity, it is commendable that so much effort has been put forth to develop risk calculators for patient-specific guidance in the diagnosis of this malignancy. The ideal goals of risk stratification would be to optimize early detection of clinically impactful prostate cancers while overcoming the historical challenges of overdiagnosis and overtreatment of biologically indolent prostate cancers, which have had a measurably significant quality-of-life burden across generations of men.
With the addition of imaging with multiparametric MRI into the diagnostic landscape, we have found high-fidelity colocalization of imaging areas of suspicion and foci of clinically-significant prostate cancer with a less common diagnosis of low-grade, low-volume disease [3]. Due to its widespread use and high fidelity, the integration of MRI findings, as a functional biomarker of risk, is critical in the current and future generations of risk calculators used for prostate cancer detection [4]. Hence, risk calculators integrating MRI findings when available, can truly derive recommendations based on readily available, pre-biopsy datapoints to help guide shared decision-making in the pre-biopsy setting, with the ultimate goals of minimizing the number and frequency of biopsies, without compromising the diagnosis of clinically-significant prostate cancers that would benefit from early diagnosis and curative treatment [5, 6].
Additionally, the importance of developing widespread applicability of risk calculators by external validation across multiple institutions, allows for broad utilization and a measurable patient impact globally [7,8,9]. Furthermore, it is imperative to ensure that diverse populations are represented in risk calculators, to be reflective of the populations they are intended to serve, particularly as there are well-recognized, multifactorial disparities in the diagnosis and care pathways for patients with prostate cancer [10].
It is also worth noting that maintaining an existing risk calculator, even if it initially performs poorly with a new patient population, could be a valuable approach. This phenomenon may partly explain why so many published risk calculators have undergone only internal validation or a limited degree of external validation. Janssen et al. suggest that building on the accumulated knowledge of existing risk calculators may be more beneficial than developing a completely new risk calculator [11]. Additionally, the integration of artificial intelligence and natural language processing into the landscape of medical decision-making will likely be transformative [12]. The use of these technologies may propose optimized workflows and use of risk calculators that have been vetted and most appropriate for a given patient based upon patient demographics, clinical criteria, and biomarker profiles available for evaluation [13]. These evolving strategies could lead to a more effective, standardized risk calculator formulation and utilization, making a more global impact over risk calculators serving a more narrow population based on limited external proven validity.
The impetus to create and validate risk calculators that use readily available clinical and biomarker datapoints, which are representative of the population, and have high validity to predict the presence of clinically-significant prostate cancer as an impactful endpoint, will hopefully shift the field toward routine adoption and use of these tools.
References
National Cancer Institute: Surveillance, Epidemiology, and End Resuls Program. Cancer Stat Facts: Prostate Cancer. National Cancer Institute Website 2023, National Cancer Institute: Bethesda, MD. Accessed at https://seer.cancer.gov/statfacts/html/prost.html.
Denijs FB, van Harten MJ, Meenderink JJL, Leenen RCA, Remmers S, Venderbos LDF, et al. Risk Calculators for the Detection of Prostate Cancer: a systematic review. Prostate Cancer Prostatic Dis. 2024 (in press).
Siddiqui MM, Rais-Bahrami S, Turkbey B, George AK, Rothwax J, Shakir N, et al. Comparison of MR/ultrasound fusion-guided biopsy with ultrasound- guided biopsy for the diagnosis of prostate cancer. JAMA. 2015;313:390–7.
Gennaro KH, Porter KK, Gordetsky JB, Galgano SJ, Rais-Bahrami S. Imaging as a personalized biomarker for prostate cancer risk stratification. Diagnostics. 2018;8:80.
Brinkley GJ, Fang AM, Rais-Bahrami S. Integration of magnetic resonance imaging into prostate cancer nomograms. Ther Adv Urol. 2022;14:17562872221096386.
Fang AM, Rais-Bahrami S. Magnetic resonance imaging-based risk calculators optimize selection for prostate biopsy among biopsy-naive men. Cancer. 2022;128:25–27.
Wang NN, Zhou SR, Chen L, Tibshirani R, Fan RE, Ghanouni P, et al. The Stanford prostate cancer calculator: development and external validation of online nomograms incorporating PIRADS scores to predict clinically significant prostate cancer. Urol Oncol. 2021;39:831.e19–831.e27.
Truong M, Wang B, Gordetsky JB, Nix JW, Frye TP, Messing EM, et al. Multi-institutional nomogram predicting benign prostate pathology on magnetic resonance/ultrasound fusion biopsy in men with a prior negative 12-core systematic biopsy. Cancer. 2018;124:278–85.
Patel HD, Remmers S, Ellis JL, Li EV, Roobol MJ, Fang AM, et al. Comparison of magnetic resonance imaging-based risk calculators to predict prostate cancer risk. JAMA Netw Open. 2024;7:e241516.
Rais-Bahrami S, Zhu Y. Disparities in prostate cancer diagnosis and management: recognizing that disparities exist at all junctures along the prostate cancer journey. Prostate Cancer Prostatic Dis. 2023;26:441–2.
Janssen KJ, Siccama I, Vergouwe Y, Koffijberg H, Debray TP, Keijzer M, et al. Development and validation of clinical prediction models: marginal differences between logistic regression, penalized maximum likelihood estimation, and genetic programming. J Clin Epidemiol. 2012;65:404–12.
Cocci A, Pezzoli M, Lo Re M, Russo GI, Asmundo MG, Fode M, et al. Quality of information and appropriateness of ChatGPT outputs for urology patients. Prostate Cancer Prostatic Dis. 2024;27:103–8.
Baydoun A, Jia AY, Zaorsky NG, Kashani R, Rao S, Shoag JE, et al. Artificial intelligence applications in prostate cancer. Prostate Cancer Prostatic Dis. 2024;27:37–45.
Author information
Authors and Affiliations
Contributions
CMA and JLS provided primary drafting critical review and revisions of the manuscript. SRB provided conceptualization, draft outlining, critical review, revisions, and submission of this manuscript.
Corresponding author
Ethics declarations
Competing interests
SR-B has research funding from the NIH/NCI, Department of Defense, Blue Earth Diagnostics, Genomic Health Inc, Astellas, and Progenics. He serves as a consultant to Philips Corp, Blue Earth Diagnostics, Genomic Health Inc, Bayer Healthcare, Intuitive Surgical, Sanofi/Genzyme, Progenics, GE Healthcare, Boston Scientific, and Tempus.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Anger, C.M., Stallworth, J.L. & Rais-Bahrami, S. Integrating risk calculators into routine clinical workflow for the detection of prostate cancer: next steps to achieve widespread adoption. Prostate Cancer Prostatic Dis (2024). https://doi.org/10.1038/s41391-024-00859-3
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41391-024-00859-3