Summary of Missing Data Imputation For Noisy Time-series Data and Applications in Healthcare, by Lien P. Le et al.
Missing data imputation for noisy time-series data and applications in healthcare
by Lien P. Le, Xuan-Hien Nguyen Thi, Thu Nguyen, Michael A. Riegler, Pål Halvorsen, Binh T. Nguyen
First submitted to arxiv on: 15 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Applications (stat.AP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A machine learning study compares various imputation methods for noisy and missing healthcare time series data. The focus is on multiple imputation with random forest (MICE-RF) and advanced deep learning approaches like SAITS, BRITS, and Transformer. Evaluation metrics include mean absolute error (MAE), F1-score, area under the curve (AUC), and Matthews correlation coefficient (MCC). Results show MICE-RF performs well in imputing missing data compared to deep learning methods. The denoising effects of imputation are also explored. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study compares different ways to fill in missing values in healthcare time series data. The data is often noisy and has gaps due to sensor errors or interruptions. Researchers tested multiple methods, including some that use machine learning techniques like random forests and deep learning. They looked at how well each method performed by comparing its results to the original data. One method called MICE-RF did very well in filling in missing values. This study shows that using an imputation algorithm can not only fill in gaps but also help remove noise from the data. |
Keywords
» Artificial intelligence » Auc » Deep learning » F1 score » Machine learning » Mae » Random forest » Time series » Transformer
