Machine learning algorithms to estimate 10-Year survival in patients with bone metastases due to prostate cancer: toward a disease-specific survival estimation tool

Background

Prognostic indicators, treatments, and survival estimates vary by cancer type. Therefore, disease-specific models are needed to estimate patient survival. Our primary aim was to develop models to estimate survival duration after treatment for skeletal-related events (SREs) (symptomatic bone metastasis, including impending or actual pathologic fractures) in men with metastatic bone disease due to prostate cancer. Such disease-specific models could be added to the PATHFx clinical-decision support tool, which is available worldwide, free of charge. Our secondary aim was to determine disease-specific factors that should be included in an international cancer registry.

Methods

We analyzed records of 438 men with metastatic prostate cancer who sustained SREs that required treatment with radiotherapy or surgery from 1989–2017. We developed and validated 6 models for 1-, 2-, 3-, 4-, 5-, and 10-year survival after treatment. Model performance was evaluated using calibration analysis, Brier scores, area under the receiver operator characteristic curve (AUC), and decision curve analysis to determine the models’ clinical utility. We characterized the magnitude and direction of model features.

Results

The models exhibited acceptable calibration, accuracy (Brier scores < 0.20), and classification ability (AUCs > 0.73). Decision curve analysis determined that all 6 models were suitable for clinical use. The order of feature importance was distinct for each model. In all models, 3 factors were positively associated with survival duration: younger age at metastasis diagnosis, proximal prostate-specific antigen (PSA) < 10 ng/mL, and slow-rising alkaline phosphatase velocity (APV).

Conclusions

We developed models that estimate survival duration in patients with metastatic bone disease due to prostate cancer. These models require external validation but should meanwhile be included in the PATHFx tool. PSA and APV data should be recorded in an international cancer registry.

Patterns of recurrence after prostate bed radiotherapy

BACKGROUND AND PURPOSE

Prostate bed radiotherapy is a standard treatment after radical prostatectomy. Recent evidence suggests that, for patients with a PSA > 0.34 ng/ml, the radiotherapy treatment volume should include not only the prostate bed but also the pelvic lymph nodes. We describe the patterns of failure after prostate bed radiotherapy, focussing on the proportion of patients with radiologically confirmed pelvic nodal failure only, in the absence of distant disease.

MATERIALS AND METHODS

Patients included were men receiving prostate bed radiotherapy at the Royal Marsden Hospital between 1997 and 2013. The key outcome of interest was the pattern of radiologic failure after prostate bed radiotherapy. Baseline characteristics of patients experiencing pelvic nodal failure without distant disease were compared versus all other relapse patterns. Comparisons were by Chi-square test, with multiple testing adjusted p < 0.005 significant.

RESULTS

140 of 322 patients developed biochemical failure after salvage RT. Radiologic failure occurred in 89 patients. 35 of the 89 patients (39%) with radiologic failure had pelvic nodal failure without distant disease, with no significant differences in baseline characteristics when compared to all other patients. The rate of pelvic nodal failure was the same for patients with PSA above or below 0.34 ng/ml (16/149, 95% CI = 6-17% vs 19/171, 95% CI = 7-17%).

CONCLUSIONS

Pelvic lymph node disease, without more distant disease, is a common site of failure in men receiving radiotherapy to the prostate bed, including those with PSA < 0.34 ng/ml. This observation informs the case for including the pelvic lymph nodes in the radiotherapy treatment volume.