Constructing multicancer risk cohorts using national data from medical helplines and secondary care

Abstract

Identification of cohorts at higher risk of cancer can enable earlier diagnosis of the disease, which significantly improves patient outcomes. In this study, we select nine cancer sites with high incidence of late-stage diagnosis or worsening survival rates, and where there are currently no national screening programmes. We use data from medical helplines (NHS 111) and secondary care appointments from all hospitals in England. We show that features based on information captured in NHS 111 calls are among the most influential in driving predictions of a future cancer diagnosis. Our predictive models exhibit good discrimination, ranging from 0.69 (ovarian cancer) to 0.83 (oesophageal cancer). We present an approach of constructing cohorts at higher risk of cancer based on feature importance and considering possible bias in model results. This approach is flexible and can be tailored based on data availability and the group the intervention targets (i.e. symptomatic or asymptomatic patients).

Fig. 1. Data flow diagram.

The population dataset from Bridges to Health (all those registered to a GP practice in England) is filtered to the age range of 40–74, and those with current and previous cancer diagnoses (relative to August 2021) are removed, resulting in an analysis dataset of 23.6M patients, which are then split into training, validation and testing datasets.

Fig. 2. Patient pathway.

The figure shows a stylised patient pathway with various types of events recorded during the 5 (history) + 1 (predictive window) years we observe the patients.

Fig. 3. Model feature importance from SHAP and XGBoost average gain.

a SHAP value, shown by order of the top 20 features based on model gain value. Red (Blue) colour indicates high (low) values for the specific feature. Dots to the right (left) of the vertical line where SHAP value is zero indicate that this feature increases (decreases) predicted probability of cancer diagnosis in year 6. Features written in bold with an asterisk were also among the top 20 in feature importance based on mean absolute SHAP value. b XGBoost model average gain value c Mean absolute SHAP value for the top 20 features.

Fig. 4. Illustration of Method A—the risk-based cohort construction.

Cohorts of different sizes are created by applying thresholds to model risk scores. The cancer incidence in such cohorts is calculated and compared to the baseline cancer rate to generate the lift value.

Fig. 5. Variation in lift value (ratio of cancer incidence in cohort to baseline incidence) with increasing cohort size.

Lift curve values for cohorts from a 0.5% to 100% of the population b 0.5% to 22% of the population. Predictions were obtained from a XGBoost model trained on all variables, and on another trained only on demographic variables to showcase the improved accuracy in identifying high risk groups when additional variables such as comorbidities and symptoms related to 111 calls are added.

Fig. 6. Illustration of Method B—Feature based cohort construction.

The most informative features from the trained model are identified and used to identify high-risk cohorts by identifying pairs of features which result in the cohorts with highest incidence. These decision rules can be applied either population wide, or to specific demographic sub-groups.