Lyme Disease Erythema Migrans Rashes

Description:

Lyme Disease Erythema Migrans Rashes, a growing yet underfunded field, impacts over 300,000 people each year. Erythema Migrans (EM), known as the “Bull’s Eye Rash,” is a key early indicator of Lyme Disease. This dataset is aimed at supporting healthcare AI research and improving diagnostic accuracy by providing a comprehensive collection of EM and non-EM rashes, as these conditions are often confused by healthcare professionals.

Download Dataset

Dataset Utility

This dataset is particularly useful for:

Machine Learning Research: For training and evaluating AI models focused on image recognition for Lyme Disease detection.

Medical Training: For doctors and dermatologists to differentiate between EM rashes and other similar conditions.

Public Health: Raising awareness and educating patients on the identification of Lyme Disease symptoms.

New Additions

The dataset includes an expanded range of metadata, such as:

Time Duration: How long each rash has been present.

Environmental Factors: Potential exposure to Lyme Disease vectors (e.g., geographical data, tick bite history).

Medical History: Details on whether the patient had previous Lyme Disease diagnosis or other conditions.

Additionally, the dataset is enriched with expert commentary, providing insights into:

How EM rash varies with different stages of Lyme Disease.

Typical vs. atypical EM presentations that may confuse diagnosis.

Acknowledgements

The dataset is compiled using web scraping and manual filtering, ensuring the data is accurate, clean, and relevant. Medical professionals have reviewed the data, contributing expert insights to improve its usability for research and diagnosis purposes.

Use Case Suggestions

AI Model Training: Can be used to build or refine AI models for automatic detection of Lyme Disease.

Misdiagnosis Prevention: The inclusion of similar non-EM rashes helps create models that reduce the risk of misdiagnosis by providing comparative datasets.

Medical Research: Provides valuable resources for researching the manifestation of Lyme Disease across diverse populations.

This dataset is sourced from Kaggle.