Autism Spectrum Disorder (ASD) Prediction

A machine learning-based diagnostic model designed to predict Autism Spectrum Disorder (ASD) using personal, medical, and behavioral features. This project aims to assist early detection by analyzing survey-based responses, helping clinicians and researchers make informed decisions.

---

Project Overview

• Goal: To develop a predictive system for detecting autism likelihood based on ASD screening datasets.
• Dataset: Autism Screening Adult Dataset (UCI Machine Learning Repository).
• Model: Trained and evaluated multiple classification algorithms .

---

🛠️ Features

• 📁 Cleaned and preprocessed medical dataset

• 🔍 Exploratory Data Analysis (EDA)

• 📊 Feature correlation heatmaps and visuals

• 🧠 Multiple ML algorithms tested

• 🏆 Best model selection based on accuracy and F1-score

• 🧪 Binary classification output (Yes/No for ASD)

  📊 Machine Learning Pipeline--

• Data Preprocessing

• Handling missing values

• Encoding categorical features

• Normalization/Standardization

• Exploratory Data Analysis

• Distribution plots

• Feature correlation heatmaps

• Class imbalance analysis

• Model Training & Evaluation

📄 License

This project is licensed under the MIT License.