A community-based collaboration to build prediction models for short-term discontinuation of docetaxel in metastatic castration-resistant prostate cancer

Abstract

BackgroundDocetaxel has a demonstrated survival benefit for metastatic castration-resistant prostate cancer (mCRPC). However, 10-20% of patients discontinue docetaxel prematurely because of toxicity-induced adverse events, and managing risk factors for toxicity remains an ongoing challenge for health care providers and patients. Prospective identification of high-risk patients for early discontinuation has the potential to assist clinical decision-making and can improve the design of more efficient clinical trials. In partnership with Project Data Sphere (PDS), a nonprofit initiative facilitating clinical trial data-sharing, we designed an open-data, crowdsourced DREAM (Dialogue for Reverse Engineering Assessments and Methods) Challenge for developing models to predict early discontinuation of docetaxel MethodsData from the comparator arms of four phase III clinical trials in first-line mCRPC were obtained from PDS, including 476 patients treated with docetaxel and prednisone from the ASCENT2 trial, 598 patients treated with docetaxel, prednisone/prednisolone, and placebo in the VENICE trial, 526 patients treated with docetaxel, prednisone, and placebo in the MAINSAIL trial, and 528 patients treated with docetaxel and placebo in the ENTHUSE 33 trial. Early discontinuation was defined as treatment stoppage within three months due to adverse treatment effects. Over 150 clinical features including laboratory values, medical history, lesion measures, prior treatment, and demographic variables were curated and made freely available for model building for all four trials. The ASCENT2, VENICE, and MAINSAIL trial data sets formed the training set that also included patient discontinuation status. The ENTHUSE 33 trial, with patient discontinuation status hidden, was used as an independent validation set to evaluate model performance. Prediction performance was assessed using area under the precision-recall curve (AUPRC) and the Bayes factor was used to compare the performance between prediction models. ResultsThe frequency of early discontinuation was similar between training (ASCENT2, VENICE, and MAINSAIL) and validation (ENTHUSE 33) sets, 12.3% versus 10.4% of docetaxel-treated patients, respectively. In total, 34 independent teams submitted predictions from 61 different models. AUPRC ranged from 0.088 to 0.178 across submissions with a random model performance of 0.104. Seven models with comparable AUPRC scores (Bayes factor ≤ 3) were observed to outperform all other models. A post-challenge analysis of risk predictions generated by these seven models revealed three distinct patient subgroups: patients consistently predicted to be at high-risk or low-risk for early discontinuation and those with discordant risk predictions. Early discontinuation events were two-times higher in the high-versus low-risk subgroup and baseline clinical features such as presence/absence of metastatic liver lesions, and prior treatment with analgesics and ACE inhibitors exhibited statistically significant differences between the high-and low...

BepiTBR: T-B reciprocity enhances B cell epitope prediction

“…BepiTBR (LBEEP) is not as successful as the corresponding HLA II-only model, but BepiTBR (LBEEP) also seems to be the least accurate of all three BepiTBR models. The Bayes Factor (Guinney et al, 2017;Seyednasrollah et al, 2017) was employed for deriving the statistical significance of model comparison, which again confirmed the significant improvement in the performance of BepiTBR models (Table S1).…”

A Crowdsourcing Approach to Develop Machine Learning Models to Quantify Radiographic Joint Damage in Rheumatoid Arthritis

“…We then used these scores to calculate Bayes factors for each subchallenge using the computeBayesFactor function of R package challengescoring 20 in comparison with the top-performing model using R statistical software version 4.2.1 (R Project for Statistical Computing). [21][22][23][24][25][26]…”

Treatment Stratification of Patients with Metastatic Castration-Resistant Prostate Cancer by Machine Learning

“…To find the key determinants of treatment discontinuation, we investigated the feature importance by calculating the delta-error of each feature in our random forest model (see Methods), on both the full dataset and subsets (ASC + CEL; CEL + VEN; VEN + ASC). We also colored the features according to their categories defined in the previous study (Seyednasrollah et al, 2017).…”

“…Since docetaxel-based chemotherapy is still an essential treatment for mCRPC and hormone-sensitive metastatic prostate cancer (Sweeney et al, 2015), it is important to identify whether a patient is able to tolerate the docetaxel therapy. However, whether the early discontinuation is predictable based on the clinical characteristics of a patient remains unclear (Seyednasrollah et al, 2017).…”

“…Recognizing the critical clinical need for identifying patients who are expected to suffer from immediate adverse events upon docetaxel treatment, the international Dialogue for Reverse Engineering Assessment and Methodology (DREAM) committee organized the Prostate Cancer Challenge, which called for the research community to develop algorithms for predicting AE (Seyednasrollah et al, 2017). In this challenge, a benchmark dataset was held out to systematically evaluate different computational methods.…”