Summary of Leveraging Machine Learning For Early Autism Detection Via Indt-asd Indian Database, by Trapti Shrivastava et al.
Leveraging Machine Learning for Early Autism Detection via INDT-ASD Indian Database
by Trapti Shrivastava, Harshal Chaudhari, Vrijendra Singh
First submitted to arxiv on: 2 Apr 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 Machine learning has revolutionized healthcare, particularly in diagnosing neurodevelopmental problems like autism spectrum disorder (ASD). ASD is one of the fastest-growing developmental disorders globally, making early detection crucial. Traditional clinical screening tests are expensive and time-consuming, but machine learning holds promise for rapid and cost-effective identification. Previous studies have employed various techniques, but none have achieved reliable predictions using a clinically validated Indian ASD database. To address this, researchers developed a novel method combining machine learning classifiers, including Adaboost (AB), Gradient Boost (GB), Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Gaussian Naive Bayes (GNB), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). The proposed model was tested on the AIIMS Modified INDT-ASD (AMI) database, demonstrating promising accuracy. Feature engineering played a crucial role in simplifying the solution. Compared to other models, SVM emerged as the superior performer, achieving 100% accuracy, higher recall, and improved accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning is helping doctors diagnose autism better. Autism spectrum disorder (ASD) is a growing problem worldwide. Doctors currently use tests that are expensive and take a long time. But now, machine learning might help identify ASD quickly and cheaply. Earlier studies tried different approaches, but none worked well using real Indian data about autism. So, researchers created a new method using many machine learning techniques. They tested this on real data from India and found it worked well. The best method was Support Vector Machine (SVM), which was very accurate. |
Keywords
* Artificial intelligence * Decision tree * Feature engineering * Logistic regression * Machine learning * Naive bayes * Random forest * Recall * Support vector machine
