Scribd
Upload
1 views

Stellars_Conversational Healthcare Chatbot Using LSTM and Decision Tree Classifier Models

This document outlines the creation of a conversational healthcare chatbot that utilizes Long Short-Term Memory (LSTM) and decision tree classifier models for diagnosing illnesses based on user-reported symptoms. The chatbot engages users interactively, providing detailed analysis through LSTM and quick evaluations via the decision tree, enhancing the accuracy and accessibility of healthcare diagnostics. The combination of these models aims to improve user experience and facilitate better health assessments.

Uploaded by

nodiwa8125
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
1 views

Stellars_Conversational Healthcare Chatbot Using LSTM and Decision Tree Classifier Models

This document outlines the creation of a conversational healthcare chatbot that utilizes Long Short-Term Memory (LSTM) and decision tree classifier models for diagnosing illnesses based on user-reported symptoms. The chatbot engages users interactively, providing detailed analysis through LSTM and quick evaluations via the decision tree, enhancing the accuracy and accessibility of healthcare diagnostics. The combination of these models aims to improve user experience and facilitate better health assessments.

Uploaded by

nodiwa8125
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Conversational Healthcare Chatbot Using LSTM and Decision Tree Classifier

Models

Shashwath V R 1 , Abinaya R 2, Arvindh S 3, Enitha J R 4


1,2,3,4
Department of Information Technology, Bannari Amman Institute of Technology, Sathyamangalam

This work describes the development of a conversational healthcare chatbot that leverages
the strengths of both Long Short-Term Memory (LSTM) and decision tree classifier models. The
chatbot aims to provide users with an interactive platform to diagnose potential illnesses based on
their reported symptoms.

This code creates an illness-diagnosing chatbot for the healthcare industry. It makes use
of two models: an LSTM for more in-depth analysis based on user-reported symptoms, and a
decision tree for a rapid first evaluation. Conversationally interacting with users, the chatbot leads
them through the process and presents possible diagnoses with different degrees of confidence.
For illness prediction, the system makes use of an LSTM model that was trained on a dataset of
labeled symptom descriptions. This model provides a possibly more detailed comprehension of
user input while capturing the sequential character of symptoms. Furthermore, a decision tree
model is used to diagnose symptoms, offering a quick and comprehensible method for preliminary
evaluation.

The chatbot engages users in conversational interaction, asking them about specific
symptoms and providing support at each stage. Depending on the model (LSTM or decision tree)
used, different degrees of confidence are associated with the anticipated disease and possible
causes. The development of healthcare chatbots is made more flexible and maybe more accurate
with the use of this combination method. Deeper analysis is provided by the LSTM model, and
effective initial assessments are ensured by the decision tree. The technology is more approachable
and available to a larger audience because to its conversational interface.

Keywords: Conversational AI, Healthcare Chatbot, LSTM, Decision Tree, Symptom Diagnosis

You might also like