Globally accessible end-user-friendly prostate cancer risk prediction tools based on contemporary cohorts with heterogeneous missing risk factors

Background: Missing risk factors, whether random or not measured at all, across different hospitals and patients provide challenges, both for the developers of online clinical risk tools and the patients trying to use such tools. This paper provides a development and end-user solution to the commonly encountered limitations of clinical risk tool based decision making due to missing information. Methods: : Six state-of-the-art logistic regression approaches accommodating missing data were compared using prostate cancer data from ten North American and European cohorts from the Prostate Biopsy Collaborative Group (PBCG). An additional large European PBCG cohort was withheld for external validation, where calibration-in-the-large (CIL), calibration curves, and area-underneath-the-receiver-operating characteristic curve (AUC) were evaluated. Ten-fold leave-one-cohort-internal validation further validated the optimal missing data approach. Results: : Among 12,703 biopsies from 10 training cohorts, 3,597 (28%) had clinically significant prostate cancer, compared to 1,757 of 5,540 (32%) in the external validation cohort. In external validation, the available cases method that pooled individual patient data containing all risk factors input by an end-user had best CIL, under-predicting risks as percentages by 2.9% on average, and obtained an AUC of 75.7%. Imputation had the worst CIL (-13.3%). The available cases method was further validated as optimal in internal cross-validation and thus used for development of an online risk tool. For end-users of the risk tool, two risk factors were mandatory: serum prostate-specific antigen (PSA) and age, and ten were optional: digital rectal exam, prostate volume, prior negative biopsy, 5-alpha-reductase-inhibitor use, prior PSA screen, African ancestry, Hispanic ethnicity, first-degree prostate-, breast-, and second-degree prostate-cancer family history. Conclusion: Developers of clinical risk prediction tools should optimize use of available data and sources even in the presence of high amounts of missing data and offer options for users with missing risk factors.