Summary of Enhancing Uncertain Demand Prediction in Hospitals Using Simple and Advanced Machine Learning, by Annie Hu et al.
Enhancing Uncertain Demand Prediction in Hospitals Using Simple and Advanced Machine Learning
by Annie Hu, Samuel Stockman, Xun Wu, Richard Wood, Bangdong Zhi, Oliver Y. Chén
First submitted to arxiv on: 29 Apr 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 The paper proposes two novel methods for accurately predicting patient care demand in hospitals. The first method employs a time-varying linear model that forecasts hourly patient arrivals over a week, considering factors such as day of the week and previous 7-day arrival patterns. The second approach utilizes a Long Short-Term Memory (LSTM) neural network model to capture non-linear relationships between past data and a three-day forecasting window. The authors evaluate these methods against two baseline approaches – reduced-rank vector autoregressive (VAR) and TBATS models – using patient care demand data from Rambam Medical Center in Israel. Results demonstrate that both proposed models effectively capture hourly variations of patient demand, with the linear model being more explainable due to its simplicity and the LSTM model delivering lower prediction errors by accurately modeling weekly seasonal trends. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about how hospitals can better predict when patients will need care. This is important because it helps them prepare for a busy day or adjust their schedule if they don’t expect many patients. The authors developed two new ways to make these predictions: one uses simple math and the other uses special computer programs called neural networks. They tested these methods against some older ones and found that they work well, especially when predicting what will happen three days or a week in advance. |
Keywords
» Artificial intelligence » Autoregressive » Lstm » Neural network
