Apples and pears? A comparison of two sources of national lung cancer audit data in England

Abstract

In 2014, the method of data collection from NHS trusts in England for the National Lung Cancer Audit (NLCA) was changed from a bespoke dataset called LUCADA (Lung Cancer Data). Under the new contract, data are submitted via the Cancer Outcome and Service Dataset (COSD) system and linked additional cancer registry datasets. In 2014, trusts were given opportunity to submit LUCADA data as well as registry data. 132 NHS trusts submitted LUCADA data, and all 151 trusts submitted COSD data. This transitional year therefore provided the opportunity to compare both datasets for data completeness and reliability. We linked the two datasets at the patient level to assess the completeness of key patient and treatment variables. We also assessed the interdata agreement of these variables using Cohen's kappa statistic, κ. We identified 26 001 patients in both datasets. Overall, the recording of sex, age, performance status and stage had more than 90% agreement between datasets, but there were more patients with missing performance status in the registry dataset. Although levels of agreement for surgery, chemotherapy and external-beam radiotherapy were high between datasets, the new COSD system identified more instances of active treatment. There seems to be a high agreement of data between the datasets, and the findings suggest that the registry dataset coupled with COSD provides a richer dataset than LUCADA. However, it lagged behind LUCADA in performance status recording, which needs to improve over time.

FIGURE 1

Data merging of registry dataset and LUCADA (Lung Cancer Data).

FIGURE 2

Kaplan–Meier curve of survival (in days) by data source. LUCADA: Lung Cancer Data; COSD: Cancer Outcome and Service Dataset.

FIGURE 3

Kaplan–Meier curve of survival (in days) by data source adjusted for age, sex, performance status, cancer stage and lung cancer type. LUCADA: Lung Cancer Data; COSD: Cancer Outcome and Service Dataset.