Summary of Identifying Reasons For Contraceptive Switching From Real-world Data Using Large Language Models, by Brenda Y. Miao et al.
Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models
by Brenda Y. Miao, Christopher YK Williams, Ebenezer Chinedu-Eneh, Travis Zack, Emily Alsentzer, Atul J. Butte, Irene Y. Chen
First submitted to arxiv on: 6 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Information Retrieval (cs.IR); Machine Learning (cs.LG)
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 abstract discusses the role of prescription contraceptives in supporting women’s reproductive health. With millions of users, understanding factors that drive contraceptive selection and switching is crucial. However, extracting relevant information from unstructured clinical notes can be challenging. A recently developed large language model, GPT-4, was evaluated for its ability to identify reasons for switching between classes of contraceptives using the UCSF Information Commons clinical notes dataset. The results show that GPT-4 outperforms baseline BERT-based models with high microF1 scores and minimal hallucinations. Human evaluation confirmed the accuracy of extracted reasons, revealing key factors such as patient preference, adverse events, and insurance coverage driving switching decisions. Additionally, demographic-specific patterns were identified using unsupervised topic modeling approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A recent study looked at how people choose and switch between different types of birth control pills. The researchers used a special kind of computer program called a large language model to help them understand why people make these choices. This program can read and understand text, like medical notes written by doctors. The team found that this program was really good at finding reasons why people switch from one type of birth control to another. They also discovered some interesting patterns about what makes people choose certain types of birth control over others. |
Keywords
* Artificial intelligence * Bert * Gpt * Large language model * Unsupervised
