Summary of Comparative Performance Of Machine Learning Algorithms For Early Genetic Disorder and Subclass Classification, by Abu Bakar Siddik et al.
Comparative Performance of Machine Learning Algorithms for Early Genetic Disorder and Subclass Classification
by Abu Bakar Siddik, Faisal R. Badal, Afroza Islam
First submitted to arxiv on: 3 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- 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 study explores the application of machine learning (ML) models in diagnosing genetic disorders at early life stages, leveraging basic clinical indicators measurable at birth or infancy. The researchers implemented supervised learning algorithms on a large dataset of 22,083 instances with 42 features, including family history, newborn metrics, and lab tests. They developed two multi-class classifiers: one for predicting disorder classes (mitochondrial, multifactorial, and single-gene) and another for subtypes (9 disorders). The study evaluated the performance of these models using accuracy, precision, recall, and F1-score metrics. The CatBoost classifier achieved an accuracy of 77% in predicting genetic disorder classes, while SVM attained a maximum accuracy of 80% for subtype prediction. This research demonstrates the feasibility of using basic clinical data in ML models for early categorization and diagnosis across various genetic disorders. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study tries to figure out how to use machine learning (a type of artificial intelligence) to diagnose genetic disorders earlier, when it’s still possible to make a big difference. They’re trying to find patterns in simple information that doctors already know, like family history and newborn measurements. The researchers created special computer programs that can look at this data and predict what kind of genetic disorder someone might have. They tested these programs on a huge dataset and found that one of them was really good at predicting the type of disorder (77% accurate!). This research shows that using basic information in machine learning models could help doctors make earlier diagnoses, which is important for improving outcomes. |
Keywords
» Artificial intelligence » F1 score » Machine learning » Precision » Recall » Supervised
