IEEE BASE PAPER TITLE:
A Machine Learning Framework for Early-Stage Detection of Autism Spectrum Disorders
OUR PROPOSED PROJECT TITLE:
Detection of Autism Spectrum Disorder using Machine Learning
IEEE BASE PAPER ABSTRACT:
Autism Spectrum Disorder (ASD) is a type of neurodevelopmental disorder that affects the everyday life of affected patients. Though it is considered hard to completely eradicate this disease, disease severity can be mitigated by taking early interventions. In this paper, we propose an effective framework for the evaluation of various Machine Learning (ML) techniques for the early detection of ASD. The proposed framework employs four different Feature Scaling (FS) strategies i.e., Quantile Transformer (QT), Power Transformer (PT), Normalizer, and Max Abs Scaler (MAS). Then, the feature-scaled datasets are classified through eight simple but effective ML algorithms like Ada Boost (AB), Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), Gaussian Naïve Bayes (GNB), Logistic Regression (LR), Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA). Our experiments are performed on four standard ASD datasets (Toddlers, Adolescents, Children, and Adults). Comparing the classification outcomes using various statistical evaluation measures (Accuracy, Receiver Operating Characteristic: ROC curve, F1-score, Precision, Recall, Mathews Correlation Coefficient: MCC, Kappa score, and Log loss), the best-performing classification methods, and the best FS techniques for each ASD dataset are identified. After analyzing the experimental outcomes of different classifiers on feature-scaled ASD datasets, it is found that AB predicted ASD with the highest accuracy of 99.25%, and 97.95% for Toddlers and Children, respectively and LDA predicted ASD with the highest accuracy of 97.12% and 99.03% for Adolescents and Adults datasets, respectively. These highest accuracies are achieved while scaling Toddlers and Children with normalizer FS and Adolescents and Adults with the QT FS method. Afterward, the ASD risk factors are calculated, and the most important attributes are ranked according to their importance values using four different Feature Selection Techniques (FSTs) i.e., Info Gain Attribute Evaluator (IGAE), Gain Ratio Attribute Evaluator (GRAE), Relief F Attribute Evaluator (RFAE), and Correlation Attribute Evaluator (CAE). These detailed experimental evaluations indicate that proper fine tuning of the ML methods can play an essential role in predicting ASD in people of different ages. We argue that the detailed feature importance analysis in this paper will guide the decision-making of healthcare practitioners while screening ASD cases. The proposed framework has achieved promising results compared to existing approaches for the early detection of ASD.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
Random Forest Classifier & Decision Tree Classifier.
OUR PROPOSED PROJECT ABSTRACT:
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition that affects social interaction, communication, and behavior. Early diagnosis of ASD is crucial for providing timely interventions and support to affected individuals. In this project, we present a novel approach for the detection of ASD using machine learning techniques, implemented in Python.
We employed two distinct algorithms, namely the Random Forest Classifier and the Decision Tree Classifier, to analyze a dataset containing 704 records with 21 features. The dataset includes a diverse range of attributes, such as sensory perception, cognitive abilities, demographics, and medical history, which are potentially indicative of ASD. Our model’s performance on this dataset is a testament to the power of machine learning in healthcare applications.
The Random Forest Classifier achieved remarkable results with a training accuracy score of 100% and a testing accuracy score of 99%. This indicates that the model can effectively learn from the training data and generalize well to unseen cases. The Decision Tree Classifier, while achieving a training accuracy score of 100%, maintained a testing accuracy score of 96%, showcasing robust performance.
The dataset used in this project encompasses a comprehensive set of attributes, including sensory perception (A1_Score – A6_Score), cognitive abilities (A7_Score – A10_Score), age, gender, ethnicity, parental medical history (jundice), autism diagnosis (austim), country of residence, prior app usage, and various demographic features. The extensive range of attributes ensures that our model takes into account a multitude of factors when making predictions.
The project’s findings are of significant clinical relevance, as they can aid in the early identification of ASD, enabling timely intervention and support for affected individuals. Furthermore, the high accuracy scores achieved by the machine learning models emphasize the potential of these algorithms in improving ASD diagnosis. This research contributes to the field of healthcare by showcasing the capabilities of machine learning in tackling complex neurodevelopmental disorders.
In summary, this project demonstrates the utility of Python-based machine learning models, Random Forest Classifier and Decision Tree Classifier, in accurately detecting ASD from a diverse set of attributes. The findings underline the potential for early diagnosis and intervention, ultimately improving the quality of life for individuals with Autism Spectrum Disorder.
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
- Operating system : Windows 10 Pro.
- Coding Language : Python 3.10.9.
- Web Framework : FLASK.
M. MAHEDY HASAN, MD PALASH UDDIN, MD AL MAMUN, MUHAMMAD IMRAN SHARIF, ANWAAR ULHAQ, AND GOVIND KRISHNAMOORTHY, “A Machine Learning Framework for Early-Stage Detection of Autism Spectrum Disorders”, IEEE ACCESS, 2023.