Summary of Many Happy Returns: Machine Learning to Support Platelet Issuing and Waste Reduction in Hospital Blood Banks, by Joseph Farrington et al.
Many happy returns: machine learning to support platelet issuing and waste reduction in hospital blood banks
by Joseph Farrington, Samah Alimam, Martin Utley, Kezhi Li, Wai Keong Wong
First submitted to arxiv on: 22 Nov 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 The proposed machine learning (ML)-guided issuing policy aims to reduce platelet wastage in hospital blood banks by increasing the likelihood of returned units being reissued before expiration. The ML model trained on 17,297 requests for platelets achieved an AUROC of 0.74 on 9,353 held-out requests. A simulation was built prior to ML model development to understand the scale of benefits, which estimated a reduction in wastage of 14%. The approach is particularly beneficial for hospitals with higher return rates and shorter remaining useful life on arrival. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to solve a problem in hospital blood banks where they waste platelets. They want to find a way to use up the platelets that are not used before they expire. They built a special computer model that can predict when someone will need more platelets, and then give them those platelets first. This could help save 14% of the wasted platelets. |
Keywords
* Artificial intelligence * Likelihood * Machine learning
