This research paper discusses the issue of missing data in electronic patient records (EPRs) and its impact on clinical data analysis. The authors argue that missing data can lead to bias and distortions in important conclusions. This study utilized statistical approaches and machine learning for interpreting missing data and imputing it. The data used in this study were gathered from a pediatric emergency department and the UK’s traumatic injury database. The authors found that missing data are likely to be non-random and linked to healthcare professional practice patterns. They concluded that the most effective method for data imputation was the 1NN imputer, which is based on finding the most similar patients and using their attributes for imputation.
Publication date: 12 Feb 2024
Project Page: Unavailable
Paper: https://arxiv.org/pdf/2402.06563
