Skip to content

KyleCarlo/Logic-Based-Chatbot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

58 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Disease Diagnosis Chatbot - Project Documentation

Introduction

The Disease Diagnosis Chatbot was designed to automate the process of diagnosing specific diseases, including diarrhea, bronchitis, influenza, tuberculosis, chickenpox, measles, malaria, schistosomiasis, dengue, and tetanus. The chatbot aims to assist individuals without immediate access to medical professionals or those seeking rough diagnoses based on symptoms. It is not a substitute for professional medical advice but serves as a tool for initial guidance.

Expertise and Significance

Automating disease diagnosis requires expertise due to the complexity and variability of symptoms. Extensive research, including expert interviews and consultation with medical sources, ensures the chatbot provides accurate and reliable information. The chatbot's significance extends to revolutionizing disease diagnosis, aiding medical professionals, and improving healthcare outcomes.

Knowledge Base and Chatbot

The knowledge base is structured based on prevalent infectious diseases in the Philippines. Symptoms are classified as common or disease-specific, determining the order of questions. Major and minor symptoms are defined, and disease confirmation follows logical conditions.

Program Flowchart

Program Flowchart

Results and Analysis

The chatbot efficiently prioritizes diseases and limits questions based on user responses. However, being hard-coded limits flexibility and causes delays in redirection. Impressive and poor sample conversations showcase strengths and weaknesses, emphasizing the need for improvements.

Sample Conversations

Impressive Sample Conversation 1

User assumed to have influenza
Impressive Sample Conversation 1

Impressive Sample Conversation 2

User assumed to have chickenpox with additional symptoms
Impressive Sample Conversation 2

Poor Sample Conversation 1

User assumed to have tetanus
Poor Sample Conversation 1

Poor Sample Conversation 2

User with no symptoms, defaulting to diarrhea
Poor Sample Conversation 2

Recommendations

Improvements are needed to address hard-coding limitations and delays in redirection. Implementing machine learning for learning from interactions and refining redirection logic can enhance the chatbot's accuracy and efficiency.

References

Contributors

  • Gabriel Luis B. Bacosa: Documentation and Coding
  • Bianca Mari A. Cuales: Documentation and Coding
  • Kyle Carlo C. Lasala: Research, Documentation, and Coding
  • Alyza L. Reynado: Research and Documentation

About

Logic Based Medical Chatbot

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages