Summary of Leveraging Pre-trained and Transformer-derived Embeddings From Ehrs to Characterize Heterogeneity Across Alzheimer’s Disease and Related Dementias, by Matthew West et al.
Leveraging Pre-trained and Transformer-derived Embeddings from EHRs to Characterize Heterogeneity Across Alzheimer’s Disease and Related Dementias
by Matthew West, Colin Magdamo, Lily Cheng, Yingnan He, Sudeshna Das
First submitted to arxiv on: 30 Mar 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 This paper explores Alzheimer’s disease, a debilitating neurodegenerative disorder affecting 50 million people globally. Despite its significant health burden, available treatments are limited, and the disease’s fundamental causes remain poorly understood. The study proposes that clinically-meaningful sub-types may correspond to distinct etiologies, disease courses, and ultimately appropriate treatments. To characterize heterogeneity in this disease population, the authors employ unsupervised learning techniques on electronic health records (EHRs) from a memory disorder patient cohort. They use pre-trained embeddings for medical codes and transformer-derived Clinical BERT embeddings of free text to encode patient EHRs. The study identifies sub-populations based on comorbidities and shared textual features, discussing their clinical significance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Alzheimer’s disease is a serious brain condition that affects millions of people worldwide. Researchers are still trying to understand why it happens and how to treat it better. One idea is that there might be different types of Alzheimer’s that need different treatments. To test this idea, scientists used computer algorithms to analyze medical records from patients with memory disorders. They found that these records can be grouped into different categories based on things like other health conditions the patient has and what they wrote in their doctor’s notes. This could help doctors figure out which treatment is best for each person. |
Keywords
» Artificial intelligence » Bert » Transformer » Unsupervised
