Incorporating Breast Cancer Recurrence Events Into Population-Based Cancer Registries Using Medical Claims: Cohort Study

Abstract

Background There is a need for automated approaches to incorporate information on cancer recurrence events into population-based cancer registries. Objective The aim of this study is to determine the accuracy of a novel data mining algorithm to extract information from linked registry and medical claims data on the occurrence and timing of second breast cancer events (SBCE). Methods We used supervised data from 3092 stage I and II breast cancer cases (with 394 recurrences), diagnosed between 1993 and 2006 inclusive, of patients at Kaiser Permanente Washington and cases in the Puget Sound Cancer Surveillance System. Our goal was to classify each month after primary treatment as pre- versus post-SBCE. The prediction feature set for a given month consisted of registry variables on disease and patient characteristics related to the primary breast cancer event, as well as features based on monthly counts of diagnosis and procedure codes for the current, prior, and future months. A month was classified as post-SBCE if the predicted probability exceeded a probability threshold (PT); the predicted time of the SBCE was taken to be the month of maximum increase in the predicted probability between adjacent months. Results The Kaplan-Meier net probability of SBCE was 0.25 at 14 years. The month-level receiver operating characteristic curve on test data (20% of the data set) had an area under the curve of 0.986. The person-level predictions (at a monthly PT of 0.5) had a sensitivity of 0.89, a specificity of 0.98, a positive predictive value of 0.85, and a negative predictive value of 0.98. The corresponding median difference between the observed and predicted months of recurrence was 0 and the mean difference was 0.04 months. Conclusions Data mining of medical claims holds promise for the streamlining of cancer registry operations to feasibly collect information about second breast cancer events.

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

“…Previous studies [ 4 – 12 ] attempting to identify breast cancer recurrence and timing of recurrence vary by method and data used. The majority of these studies focused on identifying the recurrence status but not the timing of cancer recurrence.…”

“…The majority of these studies focused on identifying the recurrence status but not the timing of cancer recurrence. A few studies [ 5 , 10 – 12 ] addressed the issue of determining the timing of recurrence by applying a prediction-model based methodology which incorporates a list of recurrence indicator variables to assign a probability of recurrence to each patient, then set a cutoff for the probability to classify recurrence vs. non-recurrence. Ritzwoller et al [ 10 ] developed recurrence identification algorithms based on multivariable logistic regression models using data derived from several distinct but integrated health care delivery settings in the U.S., and reported 60–70% estimated dates of recurrence falling within ± 6 months of the true date of recurrence.…”

“…the chart review defined) for each patient. Similar with previous study [ 10 – 12 ], taking the difference between the estimated and real recurrence date, we then classified the absolute difference (in months) into the corresponding interval (e.g. 0–1, 1–2, 2–3, 3–6, or > 6 months) and constructed a frequency table to examine the agreement between the estimated and real recurrence date.…”

“…Although several studies (mainly in the United States) have used procedure and diagnostic codes to detect and identify cancer recurrence status [ 4 – 12 ], most of these algorithms were not developed to identify timing of cancer recurrence. A few studies [ 5 , 10 – 12 ] addressed the challenge of identifying timing of breast cancer recurrence, however, due to differences in study cohorts, health systems (universal vs. mixed market system), and data coding standards (e.g. the Current Procedural Terminology is only used in the United States data) between their data and ours, these previously developed algorithms are not applicable to be implemented in our data.…”

Validated algorithms for identifying timing of second event of oropharyngeal squamous cell carcinoma using real‐world data

“…While a number of studies explored the development of algorithms to identify second events of cancer, 6–28 very few explored developing algorithms to establish temporality of second events in the head and neck cancer population. Previous work by Xu et al developed and validated algorithms to determine second events of OPSCC 29 .…”