Summary of Explain Variance Of Prediction in Variational Time Series Models For Clinical Deterioration Prediction, by Jiacheng Liu and Jaideep Srivastava
Explain Variance of Prediction in Variational Time Series Models for Clinical Deterioration Prediction
by Jiacheng Liu, Jaideep Srivastava
First submitted to arxiv on: 9 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 In this paper, researchers propose a novel approach to determining clinical variable measurement frequency from a predictive modeling perspective. They argue that measuring clinical variables reduces uncertainty in model predictions and suggest using Shapley Additive Explanation (SHAP) algorithm with variational time series models to achieve this goal. The proposed method, variance SHAP, estimates prediction variance by sampling the conditional hidden space in variational models and can be approximated deterministically by delta’s method. The authors test their ideas on a public ICU dataset with deterioration prediction task and explore the relationship between variance SHAP and measurement time intervals. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study helps doctors decide how often to check patients’ conditions, which is important for making good treatment plans. The researchers want to know when it’s most helpful to measure things like blood pressure or temperature. They use a special kind of math called predictive modeling to figure out what’s best. Their new approach looks at how measuring these variables affects the accuracy of predictions about patient outcomes. By doing this, they hope to help doctors make better decisions and improve patient care. |
Keywords
* Artificial intelligence * Temperature * Time series
