Summary of Specialty Detection in the Context Of Telemedicine in a Highly Imbalanced Multi-class Distribution, by Alaa Alomari et al.
Specialty detection in the context of telemedicine in a highly imbalanced multi-class distribution
by Alaa Alomari, Hossam Faris, Pedro A. Castillo
First submitted to arxiv on: 21 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 A machine learning-based specialty detection classifier is proposed to automate the process of routing medical questions to the correct doctor, reducing operational load and improving efficiency. The study focuses on handling multiclass and highly imbalanced datasets for Arabic medical questions, comparing oversampling techniques, developing a Deep Neural Network (DNN) model, and exploring hidden business areas. The proposed module is deployed in synchronous and asynchronous medical consultations, providing real-time classification and minimizing doctor effort. Evaluation metrics include accuracy, precision, recall, and F1-score, with improved performance achieved by combining techniques such as SMOTE and reweighing with keyword identification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a machine learning model to help doctors quickly get the right questions for the correct specialty, making medical consultations more efficient. The model uses special algorithms to handle datasets that are imbalanced or have many classes. The researchers tested their model on Arabic medical questions and found that combining different techniques can improve its performance. |
Keywords
* Artificial intelligence * Classification * F1 score * Machine learning * Neural network * Precision * Recall
