Summary of Automatic Differential Diagnosis Using Transformer-based Multi-label Sequence Classification, by Abu Adnan Sadi et al.
Automatic Differential Diagnosis using Transformer-Based Multi-Label Sequence Classification
by Abu Adnan Sadi, Mohammad Ashrafuzzaman Khan, Lubaba Binte Saber
First submitted to arxiv on: 28 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL)
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 proposes a transformer-based approach for providing differential diagnoses in healthcare, leveraging patient information such as age, sex, medical history, and symptoms. The DDXPlus dataset is used, which contains differential diagnosis information for 49 disease types. A novel method is introduced to process tabular patient data into patient reports suitable for research. Data modification modules are also proposed to improve model robustness. Four transformer models are trained as multi-label classification problems, achieving over 97% F1 score on the test set. Behavioral tests demonstrate improved generalization capabilities with custom data sets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, researchers developed a new way to help doctors diagnose patients using AI. They used a big dataset called DDXPlus that has information about different diseases and patient symptoms. The team created a special method to turn patient data into reports that can be used for diagnosis. To make the models better at predicting diagnoses, they added two new modules to the training data. Four different AI models were tested and all performed well on a test dataset. This research could help create more accurate diagnostic tools in the future. |
Keywords
» Artificial intelligence » Classification » F1 score » Generalization » Transformer
