Summary of Effect Of a Process Mining Based Pre-processing Step in Prediction Of the Critical Health Outcomes, by Negin Ashrafi et al.
Effect of a Process Mining based Pre-processing Step in Prediction of the Critical Health Outcomes
by Negin Ashrafi, Armin Abdollahi, Greg Placencia, Maryam Pishgar
First submitted to arxiv on: 3 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 This study tackles the challenge of predicting patient mortality and hospital readmission by improving healthcare dataset quality. The authors focus on decreasing data complexity using an existing pre-processing algorithm, concatenation. They apply this method to 16 healthcare datasets from two databases (MIMIC III and University of Illinois Hospital) before feeding them into the Split Miner (SM) algorithm to produce process models. Process model quality is evaluated using metrics such as fitness, precision, F-Measure, and complexity. The pre-processed event logs are also used to predict critical outcomes using the Decay Replay Mining (DREAM) algorithm, with results indicating improved quality of process models and predictions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Predicting patient mortality and hospital readmission is crucial for improving healthcare outcomes. This study focuses on making healthcare datasets better by reducing their complexity. They use a method called concatenation to make the data simpler. They apply this method to many healthcare datasets before using them to create process models that help predict critical health outcomes. The results show that making the data simpler improves the quality of the process models and predictions. |
Keywords
* Artificial intelligence * Precision
