Anomaly Detection Algorithm for Real-World Data and Evidence in Clinical Research (Preprint)
BACKGROUND Statistical analysis, which has become an integral part of evidence-based medicine, relies heavily on data quality that is of critical importance in modern clinical research. Input data are not only at risk of being falsified or fabricated, but also of being mishandled by investigators. OBJECTIVE The urgent need to assure the highest data quality possible has led to implementation of various auditing strategies designed to monitor clinical trials and detect errors of different origin that frequently occur in the field. METHODS An automatic anomaly detection algorithm based on machine learning that combines clustering with a series of distance metrics is presented. RESULTS The algorithm is built in a particular electronic data capture (EDC) system that stores real-world data in clinical registries. These data, together with newly generated, simulated anomalous data were utilized to evaluate the detection performance of this algorithm. CONCLUSIONS The experimental results demonstrate that the algorithm, which is universal, and as such may be implemented in other EDC systems, is capable of anomalous data detection with sensitivity exceeding 85%.