Summary of Ram-ehr: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records, by Ran Xu et al.
RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records
by Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Bowen Jin, May D. Wang, Joyce C. Ho, Carl Yang
First submitted to arxiv on: 25 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Other Quantitative Biology (q-bio.OT)
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 RAM-EHR pipeline aims to improve clinical predictions on Electronic Health Records (EHRs) by leveraging retrieval and augmentation techniques. The approach first collects multiple knowledge sources, converts them into text format, and uses dense retrieval to extract relevant information related to medical concepts. This addresses the challenges posed by complex concept names. Next, RAM-EHR augments a local EHR predictive model co-trained with consistency regularization to capture complementary information from patient visits and summarized knowledge. Experimental results on two EHR datasets demonstrate the effectiveness of RAM-EHR over previous knowledge-enhanced baselines, achieving gains in AUROC (3.4%) and AUPR (7.2%). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary RAM-EHR is a new way to help doctors make better predictions about patients’ health based on their medical records. It takes information from many different places and uses it to find important details related to patient care. This helps doctors make more accurate diagnoses and develop better treatment plans. The system does this by combining different types of information, like what’s written in patient charts and what’s learned from other patients with similar conditions. The results show that RAM-EHR is a big improvement over current methods. |
Keywords
» Artificial intelligence » Regularization
