Secondary Logo

Journal Logo

Prostate Cancer: Markers (MP60): Moderated Poster 60: Monday, September 13, 2021

MP60-04 SUPERVISED MACHINE LEARNING ALGORITHMS DEMONSTRATE COMPARATIVE ADVANTAGE OVER NOMOGRAMS IN PREDICTING BIOCHEMICAL RECURRENCE AFTER RADICAL PROSTATECTOMY

Tan, Yu Guang; Chen, Kenneth; Yuen, John S. P.; Huang, Hong Hong; Lim, Jay K. S.; Tay, Kae Jack

doi: 10.1097/JU.0000000000002095.04
  • Free

INTRODUCTION AND OBJECTIVE:

After radical prostatectomy (RP), up to one-third of patients experience biochemical recurrence (BCR), which is associated with subsequent metastasis and cancer-specific mortality. We aimed to employ supervised machine learning (ML) algorithms to predict BCR after RP, and compare with conventional regression models and nomograms.

METHODS:

Utilizing a large prospective Uro-oncology registry, 18 clinicopathological parameters of 1130 consecutive patients who underwent RP (2009 – 2018) were recorded, yielding over 20,000 data points for analysis. The dataset was split in a 70:30 ratio for training and validation. Three ML models: Naïve Bayes (NB), Random forest (RF) and Support Vector Machine (SVM) were studied and compared with traditional regression models and nomograms (Kattan, CAPSURE, John Hopkins [JHH]) to predict BCR at 1,3 and 5 years.

RESULTS:

Over a median follow-up of 70.0 months, 176 (15.6%) developed BCR, at a median time of 16.0 months (IQR 11.0 – 26.0). Multivariate analyses demonstrated strongest association of BCR with PSA (p: 0.015), surgical margins (p<0.001), extraprostatic extension (p :0.002), seminal vesicle invasion ((p: 0.004) and Grade Group (p<0.001). The 3 ML models demonstrated good prediction of BCR at 1, 3 and 5 years, with the area under curves (AUC) of NB at 0.894, 0.876 and 0.894, RF at 0.846, 0.875 and 0.888 and SVM at 0.835, 0.850 and 0.855 respectively. All models demonstrated robust accuracy (>0.82), good calibration with minimal overfitting, longitudinal consistency and inter-model validity. The ML models were comparable to traditional regression analyses [AUC: 0.797, 0.848 and 0.861] outperformed the three nomograms: Kattan [AUC: 0.815, 0.798 and 0.799], JHH [AUC: 0.820, 0.757 and 0.750] and CAPSURE nomograms [AUC: 0.706, 0.720 and 0.749].

CONCLUSIONS:

Supervised ML algorithms can deliver accurate performances and outperform nomograms in predicting BCR after RP. This may facilitate tailored care provisions by identifying high-risk patients who will benefit from early multimodal therapy.

Source of Funding:

NA

© 2021 by American Urological Association Education and Research, Inc.