Summary of Detection and Prediction Of Clopidogrel Treatment Failures Using Longitudinal Structured Electronic Health Records, by Samuel Kim et al.
Detection and prediction of clopidogrel treatment failures using longitudinal structured electronic health records
by Samuel Kim, In Gu Sean Lee, Mijeong Irene Ban, Jane Chiang
First submitted to arxiv on: 12 Oct 2023
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 algorithms aim to automatically detect and predict clopidogrel treatment failure using longitudinal structured electronic health records (EHR). The approach draws analogies between natural language and EHR, applying techniques from natural language processing (NLP) to build models for treatment failure detection and prediction. A cohort of patients with clopidogrel prescriptions was generated from UK Biobank, annotated for treatment failure events within one year of the first prescription. Time series models outperformed bag-of-words approaches in both detection and prediction tasks, with a Transformer-based model (BERT) achieving 0.928 AUC in detection and 0.729 AUC in prediction. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers developed a new way to use computer algorithms to predict when people taking the medication clopidogrel might not respond well. They looked at medical records from over half a million patients in the UK Biobank database. The algorithm they created used patterns and relationships found in language to identify when treatment was failing. They compared this approach to other methods and found that it worked better, especially when there wasn’t much data available to train the model. |
Keywords
* Artificial intelligence * Auc * Bag of words * Bert * Machine learning * Natural language processing * Nlp * Time series * Transformer
