Abstract
Electronic health records (EHRs) have been widely adopted in recent years, but often include a high proportion of missing data, which can create difficulties in implementing machine learning and other tools of personalized medicine. Completed datasets are preferred for a number of analysis methods, and successful imputation of missing EHR data can improve interpretation and increase our power to predict health outcomes. However, use of the most popular imputation methods mainly require scripting skills, and are implemented using various packages and syntax. Thus, the implementation of a full suite of methods is generally out of reach to all except experienced data scientists. Moreover, imputation is often considered as a separate exercise from exploratory data analysis, but should be considered as art of the data exploration process. We have created a new graphical tool, ImputEHR, that is based on a Python base and allows implementation of a range of simple and sophisticated (e.g., gradient-boosted tree-based and neural network) data imputation approaches. In addition to imputation, the tool enables data exploration for informed decision-making, as well as implementing machine learning prediction tools for response data selected by the user. Although the approach works for any missing data problem, the tool is primarily motivated by problems encountered for EHR and other biomedical data. We illustrate the tool using multiple real datasets, providing performance measures of imputation and downstream predictive analysis.
Highlights
Hospitals in the United States have made a concerted effort to transition their health records from paper to digital, the proportion of which has dramatically increased, from 9.4% in 2008 to 75.5% in 2014 (Charles et al, 2013)
We evaluate the effectiveness of various imputation methods on Electronic health records (EHRs) and other real-world datasets, and proposed a practical and fast imputation method as a hybrid of existing methods
Our experiments show that both ImputeEHR1 and ImputeEHR2 can accelerate the imputation process 20–25 times faster than MissForest while achieving lower Root Mean Squared Error (RMSE)
Summary
Hospitals in the United States have made a concerted effort to transition their health records from paper to digital, the proportion of which has dramatically increased, from 9.4% in 2008 to 75.5% in 2014 (Charles et al, 2013). The process of data imputation (artificially replacing missing data with an estimated value) offers a practical work-around so that many downstream data handling steps become feasible. This process preserves all observations by replacing missing data with an estimated value based on other available information. Our focus here is on the practical impact of imputation for downstream analysis, such as EHR-based prediction of important health measures. For such efforts, the emphasis is placed on the success of machine-learning methods, which themselves may involve penalization techniques and estimation known to be biased. We evaluate the effectiveness of various imputation methods on EHR and other real-world datasets, and proposed a practical and fast imputation method as a hybrid of existing methods
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.