# Improving Skin Condition Classification with a Visual Symptom Checker Trained using Reinforcement Learning

## TL;DR

This paper introduces a novel visual symptom checker that integrates a CNN with a reinforcement learning agent to improve diagnosis accuracy and reduce the number of questions needed, outperforming traditional methods.

## Contribution

The study presents a reinforcement learning-based question answering system that enhances skin condition classification accuracy and efficiency over existing CNN and decision tree approaches.

## Key findings

- Increases diagnosis accuracy by over 20% compared to CNN-only methods.
- Reduces the number of questions asked by up to 10% relative to traditional decision tree systems.
- Outperforms existing approaches in both accuracy and speed of diagnosis.

## Abstract

We present a visual symptom checker that combines a pre-trained Convolutional Neural Network (CNN) with a Reinforcement Learning (RL) agent as a Question Answering (QA) model. This method increases the classification confidence and accuracy of the visual symptom checker, and decreases the average number of questions asked to narrow down the differential diagnosis. A Deep Q-Network (DQN)-based RL agent learns how to ask the patient about the presence of symptoms in order to maximize the probability of correctly identifying the underlying condition. The RL agent uses the visual information provided by CNN in addition to the answers to the asked questions to guide the QA system. We demonstrate that the RL-based approach increases the accuracy more than 20% compared to the CNN-only approach, which only uses the visual information to predict the condition. Moreover, the increased accuracy is up to 10% compared to the approach that uses the visual information provided by CNN along with a conventional decision tree-based QA system. We finally show that the RL-based approach not only outperforms the decision tree-based approach, but also narrows down the diagnosis faster in terms of the average number of asked questions.