Eastern Cooperative Oncology Group Performance Score Is Associated With Survival After Radiotherapy of Bone Metastases from Prostate Cancer

Comprehensive Analysis of Metastatic Prostate Cancer: Real-World Data From the Middle East

PURPOSE

Metastatic prostate cancer (Pca) is a complex disease with diverse clinical characteristics and outcomes across the geographical distribution. Herein, we present a series of patients from the Middle East, aiming at identifying disease outcomes and prognostic factors specific to this regional context.

METHODS AND MATERIALS

This is a retrospective study of patients with metastatic Pca, diagnosed at King Hussein Cancer Center, Jordan, between 2006 and 2018. Survival was estimated using the Kaplan-Meier method and compared using the log-rank test. Factors that significantly affected overall survival (OS) in the univariable analysis were examined in a multivariable Cox regression analysis.

RESULTS

A total of 188 patients with metastatic Pca were included in this analysis, of whom 168 (89%) had de novo metastatic disease. The median age at diagnosis was 68 years, 144 (77%) had bone metastasis, 32 (17%) had visceral metastasis, and 126 (67%) had high-volume disease. At a median follow-up of 67 months, the median OS was 44.3 months. The following factors predicted inferior OS in univariable analysis: smoking, normal BMI, high-volume disease, high alkaline phosphatase (ALP), previous local therapy for prostate, and orchiectomy versus medical androgen deprivation therapy (ADT). On multivariable analysis, high-volume disease (hazard ratio [HR], 1.92 [95% CI, 1.17 to 3.13]; P = .0094), high ALP (HR, 2.136 [95% CI, 1.38 to 3.31]; P < .001), and orchiectomy (HR, 2.40 [95% CI, 1.51 to 3.82]; P < .001) emerged as independent factors for inferior OS.

CONCLUSION

Metastatic Pca outcomes in our population closely align with the global benchmark. High volume status, elevated ALP, and performance of surgical as opposed to medical ADT emerge as prognostic indicators of poor survival.

A Web-Based Calculator to Predict Early Death Among Patients With Bone Metastasis Using Machine Learning Techniques: Development and Validation Study

BACKGROUND

Patients with bone metastasis often experience a significantly limited survival time, and a life expectancy of <3 months is generally regarded as a contraindication for extensive invasive surgeries. In this context, the accurate prediction of survival becomes very important since it serves as a crucial guide in making clinical decisions.

OBJECTIVE

This study aimed to develop a machine learning-based web calculator that can provide an accurate assessment of the likelihood of early death among patients with bone metastasis.

METHODS

This study analyzed a large cohort of 118,227 patients diagnosed with bone metastasis between 2010 and 2019 using the data obtained from a national cancer database. The entire cohort of patients was randomly split 9:1 into a training group (n=106,492) and a validation group (n=11,735). Six approaches-logistic regression, extreme gradient boosting machine, decision tree, random forest, neural network, and gradient boosting machine-were implemented in this study. The performance of these approaches was evaluated using 11 measures, and each approach was ranked based on its performance in each measure. Patients (n=332) from a teaching hospital were used as the external validation group, and external validation was performed using the optimal model.

RESULTS

In the entire cohort, a substantial proportion of patients (43,305/118,227, 36.63%) experienced early death. Among the different approaches evaluated, the gradient boosting machine exhibited the highest score of prediction performance (54 points), followed by the neural network (52 points) and extreme gradient boosting machine (50 points). The gradient boosting machine demonstrated a favorable discrimination ability, with an area under the curve of 0.858 (95% CI 0.851-0.865). In addition, the calibration slope was 1.02, and the intercept-in-large value was -0.02, indicating good calibration of the model. Patients were divided into 2 risk groups using a threshold of 37% based on the gradient boosting machine. Patients in the high-risk group (3105/4315, 71.96%) were found to be 4.5 times more likely to experience early death compared with those in the low-risk group (1159/7420, 15.62%). External validation of the model demonstrated a high area under the curve of 0.847 (95% CI 0.798-0.895), indicating its robust performance. The model developed by the gradient boosting machine has been deployed on the internet as a calculator.

CONCLUSIONS

This study develops a machine learning-based calculator to assess the probability of early death among patients with bone metastasis. The calculator has the potential to guide clinical decision-making and improve the care of patients with bone metastasis by identifying those at a higher risk of early death.

Association of dynamic change in patient-reported pain with survival in metastatic castrate sensitive prostate cancer-exploratory analysis of LATITUDE study

BACKGROUND

Pain is an important dimension of quality-of-life in patients with metastatic castrate-sensitive prostate cancer (mCSPC). However, it is unclear if dynamic change in pain over time can predict for overall survival (OS) or progression-free survival (PFS) in these patients.

METHODS

This is an exploratory analysis of LATITUDE, a phase III randomized study, in which men with de novo mCSPC were randomized to receive either ADT plus abiraterone versus ADT alone. Information was collected on patient-reported worst pain score (WPS) and pain-interference score (PIS) from the Brief Pain Inventory-Short Form. A Bayesian joint modelling approach was used determine the association of dynamic change in WPS and PIS with OS and PFS.

RESULTS

Overall, 1125 patients with at least 3 measurements on pain scores were eligible. On Cox multivariable regression, increase in baseline WPS was associated with inferior OS (hazard ratio [HR] 1.049 [95% confidence intervals [CI] 1.015-1.085]; time dependent area under curve [tAUC] 0.64) and PFS (HR 1.045 [1.011-1.080]; tAUC: 0.64). Increase in baseline PIS was associated with inferior OS (HR 1.062 [1.020-1.105]; tAUC: 0.63) but not with PFS (HR 1.038 [0.996-1.08]). On independent joint models, an increase in the current value of WPS by 1-unit was associated with inferior OS (HR 1.316 [1.258-1.376]; tAUC 0.74) and PFS (HR 1.319 [1.260-1.382]; tAUC 0.70). Similar association was seen for increase in the current value of PIS with OS (HR 1.319 [1.261-1.381]; tAUC 0.73) and PFS (HR 1.282 [1.224-1.344]; tAUC 0.73).

CONCLUSIONS

The above findings highlight the potential dynamic interplay between patient-reported pain with OS and PFS in mCSPC. Compared to baseline pain, such dynamic assessment of pain was found to have superior predictive ability and thus has the potential to tailor subsequent treatment based on response to initial therapy beyond its role as a very important dimension of quality-of-life.