Management of de novo metastatic hormone-sensitive prostate cancer: A comprehensive report of a single-center experience.

BACKGROUND: Upfront docetaxel or novel hormonal agents (NHA) such as abiraterone and enzalutamide have become the standard of care for metastatic hormone sensitive prostate cancer (mHSPC). We evaluated real-world management of patients treated with these agents at a single center. PATIENTS AND METHODS: Patients with de novo mHSPC treated with upfront docetaxel or an NHA between January 2014 and April 2019 at Mount Sinai Health System were included. We evaluated time to next treatment (TTNT), PSA progression free survival (PFS) and overall survival (OS) after initial treatment with these drugs. Kaplan Meier method and multivariable Cox proportional hazards models were used for analysis. We additionally assessed the prognostic value of post-treatment PSA. RESULTS: We identified 94 de novo mHSPC patients; 52 and 42 treated with upfront docetaxel and NHAs, respectively. NHAs were associated with a median TTNT of 20.7 months compared to 10.1 months with docetaxel (log-rank p = 0.023). We also observed median PSA PFS of 19 months for NHAs and 13.2 months for docetaxel (p = 0.069). However, OS between the two treatment groups was unchanged. Among docetaxel treated patients, TTNT was shorter among those with high metastasis burden (9.63 vs 25.5 months, p = 0.026) which was not observed among NHA treated patients (25.1 vs 20.7 months, p = 0.79). Regardless of treatment, lower post-treatment PSA levels were associated with improved TTNT (58.95 vs. 11.57 vs. 9.4 months for PSA ≤0.2, 0.2-0.4, >0.4ng/ml, respectively; p<0.001). CONCLUSION: Real world data demonstrated a shorter duration of treatment with docetaxel than NHAs, reflecting the time-limited nature of docetaxel regimens compared to the treat-till-progression approach of NHAs. While TTNT was generally longer for NHAs than docetaxel, some docetaxel-treated patients achieved significant periods of time off treatment. In addition, the depth of PSA response following combination treatment may hold prognostic value for mHSPC outcomes.

Extraction of Treatment Information From Electronic Health Records and Evaluation of Testosterone Recovery in Patients With Prostate Cancer.

PURPOSE: Data quality and standardization remain a challenge when analyzing real-world clinical data. We built a clinical research database, using machine learning and natural learning processing, and investigated factors influencing testosterone recovery (T-recovery) in patients with localized prostate cancer (LPC) after initial androgen deprivation therapy (ADT). METHODS: Medication and treatment-associated dates missing in structured tables were extracted from patient notes using ConceptMapper, an automated data extraction tool, standardized and curated in Sema4 clinical research database. ADT usage duration was evaluated, and T-recovery in patients with LPC was analyzed by the Kaplan-Meier method and multivariable Cox proportional hazards models. We assessed the prognostic value of post-ADT T-recovery with prostate-specific antigen progression-free survival and failure-free survival. RESULTS: In total, 4,125 of 30,832 (13.4%) patients with prostate cancer had medication exclusively from notes with high precision and recall, F1 score ≥ 0.95. Association of dates with medication usage had a F1 score of 0.76. ADT duration estimation had higher accuracy combining information from notes to tables from electronic medical record (70% v 45%). Baseline testosterone was the strongest predictor of T-recovery in these patients. Patients with a baseline testosterone ≥ 300 ng/dL recovered in 9.79 versus 38 months for patients with baseline testosterone < 300 ng/dL (P < .0001). Shorter prostate-specific antigen progression-free interval was observed for patients with T-recovery (≥ 300 ng/dL) at 6 months after ADT cessation compared with patients without T-recovery (< 300 ng/dL; 13.7 v 25.1 months; P = .055). CONCLUSION: We augmented structured electronic medical record data with data extracted from notes and improved the accuracy of medication information for patients. ADT exposure and T-recovery in patients with LPC produced results consistent with the literature and clinical experience and illustrates the power of applying machine learning methods to enhance the quality of real-world evidence in answering clinically relevant questions.