Multi-institutional Development and External Validation of a Machine Learning Model for the Prediction of Distant Metastasis in Patients Treated by Salvage Radiotherapy for Biochemical Failure After Radical Prostatectomy

Ali Sabbagh; Derya Tilki; Jean Feng; Hartwig Huland; Markus Graefen; Thomas Wiegel; Dirk Böhmer; Julian C Hong; Gilmer Valdes; Janet E Cowan; Matthew Cooperberg; Felix Y Feng; Tarek Mohammad; Mohamed Shelan; Anthony V D'Amico; Peter R Carroll; Osama Mohamad

doi:10.1016/j.euf.2023.07.004

Multi-institutional Development and External Validation of a Machine Learning Model for the Prediction of Distant Metastasis in Patients Treated by Salvage Radiotherapy for Biochemical Failure After Radical Prostatectomy

Eur Urol Focus. 2024 Jan;10(1):66-74. doi: 10.1016/j.euf.2023.07.004. Epub 2023 Jul 26.

Authors

Ali Sabbagh¹, Derya Tilki², Jean Feng³, Hartwig Huland⁴, Markus Graefen⁴, Thomas Wiegel⁵, Dirk Böhmer⁶, Julian C Hong¹, Gilmer Valdes¹, Janet E Cowan⁷, Matthew Cooperberg⁸, Felix Y Feng⁹, Tarek Mohammad¹⁰, Mohamed Shelan¹¹, Anthony V D'Amico¹², Peter R Carroll⁷, Osama Mohamad¹³

Affiliations

¹ Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA.
² Department of Urology, University Hospital Hamburg-Eppendorf, Hamburg, Germany; Martini-Klinik Prostate Cancer Center, University Hospital-Hamburg-Eppendorf, Hamburg, Germany.
³ Department of Epidemiology and Biostatistics, University of California San Francisco, San Francisco, CA, USA.
⁴ Martini-Klinik Prostate Cancer Center, University Hospital-Hamburg-Eppendorf, Hamburg, Germany.
⁵ Department of Radio Oncology, University Hospital Ulm, Ulm, Germany.
⁶ Department of Radiation Oncology, Charité University Hospital, Berlin, Germany.
⁷ Department of Urology, University of California San Francisco, San Francisco, CA, USA.
⁸ Department of Epidemiology and Biostatistics, University of California San Francisco, San Francisco, CA, USA; Department of Urology, University of California San Francisco, San Francisco, CA, USA.
⁹ Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA; Department of Urology, University of California San Francisco, San Francisco, CA, USA.
¹⁰ University of California Berkeley, Berkeley, CA, USA.
¹¹ Department of Radiation Oncology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
¹² Department of Radiation Oncology, Brigham and Women's Hospital and Dana Farber Cancer Institute, Boston, MA, USA.
¹³ Department of Radiation Oncology, University of California San Francisco, San Francisco, CA, USA; Department of Urology, University of California San Francisco, San Francisco, CA, USA. Electronic address: osama.mohamad@ucsf.edu.

PMID: 37507248
DOI: 10.1016/j.euf.2023.07.004

Abstract

Background: Up to 40% of patients with prostate cancer may develop biochemical recurrence after surgery, with salvage radiation therapy (SRT) being the only curative option. In 2016, Tendulkar et al. (Contemporary update of a multi-institutional predictive nomogram for salvage radiotherapy after radical prostatectomy. J Clin Oncol 2016;34:3648-54) published a nomogram to predict distant metastasis in a cohort of patients treated with SRT with pre-SRT prostate-specific antigen (PSA) of 0.5 ng/ml after radical prostatectomy. In modern practice, SRT is delivered at lower PSA values.

Objective: To train and externally validate a machine learning model to predict the risk of distant metastasis at 5 yr in a contemporary cohort of patients receiving SRT.

Design, setting, and participants: We trained a machine learning model on data from 2418 patients treated with SRT at one institution, with a median PSA value of 0.27 ng/ml. External validation was done in 475 patients treated at two different institutions. Patients with cM1, pN1, or pT4 disease were excluded, as were patients with PSA >2 ng/ml or PSA 0, and patients with radiation dose <60 or ≥80 Gy.

Outcome measurements and statistical analysis: Model performance was assessed using calibration and time-dependent area under the receiver operating curve (tAUC).

Results and limitations: Our model had better calibration and showed improved discrimination (tAUC = 0.72) compared with the Tendulkar model (tAUC = 0.60, p < 0.001). The main limitations of this study are its retrospective design and lack of validation on patients who received hormone therapy.

Conclusions: The updated model can be used to provide more individualized risk assessments to patients treated with SRT at low PSA values, improving decision-making.

Patient summary: Up to 40% of patients with prostate cancer may develop biochemical recurrence after surgery, with salvage radiation therapy as the only potentially curative option. We trained and validated a machine learning model using clinical and surgical data to predict a patient's risk of distant metastasis at 5 yr after treatment. Our model outperformed the reference tool and can improve clinical decision-making by providing more personalized risk assessment.

Keywords: Biochemical recurrence; Distant metastasis; Machine leaning; Prostate cancer; Radical prostatectomy; Salvage radiotherapy.

MeSH terms

Humans
Male
Prostate / pathology
Prostate-Specific Antigen*
Prostatectomy / methods
Prostatic Neoplasms* / pathology
Prostatic Neoplasms* / radiotherapy
Prostatic Neoplasms* / surgery
Retrospective Studies
Salvage Therapy / methods

Substances

Prostate-Specific Antigen