JMIR Publications

ABSTRACT

Background:

Lung cancer is the leading cause of cancer death worldwide. Early detection of individuals at risk of lung cancer is critical to reduce the mortality rate.

Objective:

The aim of this study was to develop and validate a prospective risk prediction model to identify patients at risk of receiving a new diagnosis of lung cancer (incident lung cancer) within the next one year in a general population.

Methods:

Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. The study population consisted of patients having at least one EHR between April 1, 2016 and March 31, 2018, who had no history of lung cancer. A retrospective (N=873,598) cohort and a prospective (N=836,659) cohort were formed for model construction and validation. An Extreme Gradient Boosting (XGBoost) algorithm was adopted to build the model. It assigned a score to each individual that measured the probability of receiving a new diagnosis of lung cancer from October 1, 2016 to September 31, 2017, based on the clinical profile in the retrospective cohort from the preceding 6 months. The model was validated using the prospective cohort to predict risk of incident lung cancer from April 1, 2017 to March 31, 2018, using the preceding 6 months’ clinical profile.

Results:

The model had an area under the curve (AUC) of 0.881(95% CI 0.873-0.889) in the prospective cohort. Two thresholds of 0.0045 and 0.01 were applied to the predictive scores to stratify the population into low-, medium- and high-risk categories. The incidence of lung cancer in the high-risk category (579/53,922, 1.07%) was 7.7 times higher than the incidence in the overall cohort (1,167/836,659, 0.14%). Age, a history of pulmonary diseases and other chronic diseases, medications for mental disorders, and social disparities were found to be associated with incident lung cancer.

Conclusions:

We developed and prospectively validated an accurate risk prediction model of incident lung cancer in the next one year by statistically learning from the statewide EHR data in the preceding 6 months. Our model was able to identify patients at high risk of incident lung cancer, which will benefit population health through preventive interventions or more intensive surveillance.