Can National Registries Contribute to Predict the Risk of Cancer? The Cancer Risk Assessment Model (CRAM)

Abstract

Purpose: To develop a predictive model based on Danish administrative registers to facilitate automated identification of individuals at risk of any type of cancer. Methods: A nationwide register-based cohort study covering all individuals in Denmark aged +20 years. The outcome was all-type cancer during 2017 excluding nonmelanoma skin cancer. Diagnoses, medication, and contact with general practitioners in the exposure period (2007–2016) were considered for the predictive model. We applied backward selection to all variables by logistic regression to develop a risk model for cancer. We applied the models to the validation cohort, calculated the receiver operating characteristic curves, and estimated the corresponding areas under the curve (AUC). Results: The study population consisted of 4.2 million persons; 32,447 (0.76%) were diagnosed with cancer in 2017. We identified 39 predictive risk factors in women and 42 in men, with age above 30 as the strongest predictor for cancer. Testing the model for cancer risk showed modest accuracy, with an AUC of 0.82 (95% CI 0.81–0.82) for men and 0.75 (95% CI 0.74–0.75) for women. Conclusion: We have developed and tested a model for identifying the individual risk of cancer through the use of administrative data. The models need to be further investigated before being applied to clinical practice.

Developing and Validating a Lung Cancer Risk Prediction Model: A Nationwide Population-Based Study

“…The first prediction model (CRAM) for identifying the individual risk of any cancer included 39 and 42 risk factors for cancer for women and men, respectively, and showed moderate accuracy. In addition to age, almost all included factors contributed statistically significantly but also only marginally to the prediction models [14]. In this study, we focused on a specific cancer type, lung cancer, and expected more precise risk estimations.…”

“…Lower SES is associated with late stage cancer diagnosis [12], while low SES predicts an overall slightly worse prognosis for lung cancer patients [13]. In a recent cancer risk assessment model (CRAM) we investigated the predictive effect of combining individual-level data on risk factors, hospital and primary care visits, main medical reasons for diagnostic procedures or treatment, and SES on all types of cancer [14]. This study identified 39 and 42 predictive individual risk factors in women and men, respectively, and found that SES also affects risk prediction, but only marginally.…”

Development and External Validation of Partial Proportional Odds Risk Prediction Models for Cancer Stage at Diagnosis among Males and Females in Canada

“…Risk prediction models are increasingly used to support clinical decision-making [17]. While a number of cancer risk prediction models have been developed, most involve predicting dichotomous outcomes (e.g., presence versus absence of cancer) [18][19][20][21][22]. Fewer risk prediction models have been developed to predict ordinal outcomes, such as cancer stage at diagnosis [23][24][25][26][27][28].…”