diff --git a/Machine Learning and Data Science/Basic/Autism Identification System/README.md b/Machine Learning and Data Science/Basic/Autism Identification System/README.md index 8d7308e91..ec5d7dd14 100644 --- a/Machine Learning and Data Science/Basic/Autism Identification System/README.md +++ b/Machine Learning and Data Science/Basic/Autism Identification System/README.md @@ -1,6 +1,6 @@ --- - +
@@ -8,15 +8,15 @@ ![](https://img.shields.io/badge/Main_Tool_Used-Jupyter_Notebook-orange.svg) ![](https://img.shields.io/badge/Status-Complete-green.svg) -## Autism Identification System +# Autism Identification System -### Problem Statement: +## Problem Statement - **Autistic Spectrum Disorder (ASD)** is a neurodevelopmental condition that incurs significant healthcare costs. Early diagnosis can substantially reduce these costs and improve patient outcomes. - Current ASD diagnostic procedures involve long wait times and are not cost-effective. - There is a need for a **time-efficient and accessible ASD screening tool** to assist healthcare professionals and guide individuals toward pursuing formal clinical diagnosis. - The objective is to leverage **machine learning techniques** to create a faster and more effective screening process. -### Tools and Algorithms: +## Tools and Algorithms - You can use any tool of your choice (Python/R/Tableau/PowerBI/Excel/SAP/SAS). - **Programming Language Used**: Python - **Main Tool Used**: Jupyter Notebook @@ -25,34 +25,63 @@ - Support Vector Machine (SVM) - Random Forest Classifier -### Dataset: -- The dataset for this project can be found here: [Dataset.csv](Machine Learning and Data Science/Intermediate/Autism Identification System/Data.csv) - -### Solution: -- The project notebook can be accessed here: [Autism Identification System](Machine Learning and Data Science/Intermediate/Autism Identification System/autism_identification_notebook.ipynb) - -### Project Details: - -1. **Introduction**: - - This project aims to develop an ASD screening tool using machine learning techniques to provide quick and accurate predictions. - -2. **Data Exploration and Preprocessing**: - - Load and explore the dataset. - - Handle missing values and encode categorical variables. - - Split the data into training and testing sets. - -3. **Model Development**: - - Implement and train three machine learning models: Logistic Regression, SVM, and Random Forest. - - Evaluate the models using appropriate metrics such as accuracy, precision, recall, and F1-score. - -4. **Model Evaluation**: - - Compare the performance of the models to determine the best one for ASD screening. - -5. **Conclusion**: - - Summarize the findings and highlight the model that performs the best. - - Discuss the potential impact of the screening tool in real-world healthcare settings. - -### Contact: +## Dataset +- The dataset for this project is included in the repository: [Data.csv](Data.csv) + +### Dataset Description +The dataset contains information related to ASD screening. Below are the key features included in the dataset: + +- `A1_Score`: Score for question A1 (binary: 0, 1) +- `A2_Score`: Score for question A2 (binary: 0, 1) +- `A3_Score`: Score for question A3 (binary: 0, 1) +- `A4_Score`: Score for question A4 (binary: 0, 1) +- `A5_Score`: Score for question A5 (binary: 0, 1) +- `A6_Score`: Score for question A6 (binary: 0, 1) +- `A7_Score`: Score for question A7 (binary: 0, 1) +- `A8_Score`: Score for question A8 (binary: 0, 1) +- `A9_Score`: Score for question A9 (binary: 0, 1) +- `A10_Score`: Score for question A10 (binary: 0, 1) +- `age`: Age of the individual +- `gender`: Gender of the individual +- `ethnicity`: Ethnicity of the individual +- `jundice`: Whether the individual had jaundice at birth (binary: yes, no) +- `austim`: Whether the individual has a family history of autism (binary: yes, no) +- `contry_of_res`: Country of residence +- `used_app_before`: Whether the individual has used an app for autism screening before (binary: yes, no) +- `result`: Result of the screening test (binary: 0, 1) +- `age_desc`: Age description +- `relation`: Relationship status + +## Solution +- The project notebook can be accessed here: [Autism Identification System](autism_identification_notebook.ipynb) + +## Project Details + +### 1. Introduction +This project aims to develop an ASD screening tool using machine learning techniques to provide quick and accurate predictions. + +### 2. Data Exploration and Preprocessing +- **Loading and Exploring the Dataset**: Initial exploration to understand the structure and summary statistics of the dataset. +- **Handling Missing Values**: Strategies to deal with any missing data in the dataset. +- **Encoding Categorical Variables**: Converting categorical variables into a format that can be used by machine learning algorithms. +- **Splitting the Data**: Dividing the dataset into training and testing sets to evaluate the model performance. + +### 3. Model Development +- **Logistic Regression**: Implementation and training of a logistic regression model. +- **Support Vector Machine (SVM)**: Implementation and training of an SVM model. +- **Random Forest Classifier**: Implementation and training of a random forest classifier model. +- **Hyperparameter Tuning**: Techniques to optimize the performance of the models. + +### 4. Model Evaluation +- **Performance Metrics**: Evaluating the models using metrics such as accuracy, precision, recall, and F1-score. +- **Comparison of Models**: Comparing the performance of the models to determine the best one for ASD screening. + +### 5. Conclusion +- **Summary of Findings**: Highlighting the key findings and results from the models. +- **Best Performing Model**: Identifying the model that performs the best in terms of predictive accuracy and reliability. +- **Impact**: Discussing the potential impact of the screening tool in real-world healthcare settings and its benefits for early diagnosis of ASD. + +## Contact If you have any queries or suggestions, feel free to reach out to me. [][LinkedIn]