New method for determining breast cancer recurrence-free survival using routinely collected real-world health data

Abstract

Background In cancer survival analyses using population-based data, researchers face the challenge of ascertaining the timing of recurrence. We previously developed algorithms to identify recurrence of breast cancer. This is a follow-up study to detect the timing of recurrence. Methods Health events that signified recurrence and timing were obtained from routinely collected administrative data. The timing of recurrence was estimated by finding the timing of key indicator events using three different algorithms, respectively. For validation, we compared algorithm-estimated timing of recurrence with that obtained from chart-reviewed data. We further compared the results of cox regressions models (modeling recurrence-free survival) based on the algorithms versus chart review. Results In total, 598 breast cancer patients were included. 121 (20.2%) had recurrence after a median follow-up of 4 years. Based on the high accuracy algorithm for identifying the presence of recurrence (with 94.2% sensitivity and 79.2% positive predictive value), the majority (64.5%) of the algorithm-estimated recurrence dates fell within 3 months of the corresponding chart review determined recurrence dates. The algorithm estimated and chart-reviewed data generated Kaplan–Meier (K-M) curves and Cox regression results for recurrence-free survival (hazard ratios and P-values) were very similar. Conclusion The proposed algorithms for identifying the timing of breast cancer recurrence achieved similar results to the chart review data and were potentially useful in survival analysis.

Adjuvant Ovarian Function Suppression in Premenopausal Hormone Receptor–Positive Breast Cancer

“…The primary outcome of interest for aims 2 and 3 was 5-year RFS. The occurrence of relapses is not routinely collected in administrative data; thus, a case-finding algorithm by Jung et al 21 was used to identify patients with a recurrence. Time zero or baseline was defined as the date of hormone treatment initiation.…”

Bias and Class Imbalance in Oncologic Data—Towards Inclusive and Transferrable AI in Large Scale Oncology Data Sets

“…Patient management in oncology can vary based on several clinical and disease-related factors, including features discussed in Section 1 and Section 2 above and the evolution of staging and treatment paradigms in any one condition over time. Notably, demographics and management can be drastically different between trial populations and the real world [ 27 , 28 ], resulting in heterogeneous data mirrored in data sets employed for analysis, training, testing, and validation ( Figure 2 ). In real-world settings, oncologic management can be highly variable based on geographical location, access, and resources, which can significantly impact training AI algorithms and result in non-transferable products.…”