Skip to content

Releases: giuseppericcio/MediCARE

GREAT-CARE_v1.0.0

15 Mar 10:05
Compare
Choose a tag to compare
GREAT-CARE_v1.0.0 Pre-release
Pre-release

GREAT-CARE: Framework for Personalized and Interpretable Medical Recommendations

GREAT-CARE is an innovative open-source framework designed to provide personalized medical recommendations through advanced analysis of clinical data. Built on a combination of Machine Learning techniques and Heterogeneous Graphs, GREAT-CARE enables the extraction, representation, and contextualization of crucial information from Electronic Health Records (EHRs).

The framework offers an intuitive interface for Exploratory Data Analysis (EDA), extraction of medical concepts through Named Entity Recognition (NER) and Entity Linking (EL), and generation of personalized recommendations using Graph Neural Networks (GNNs).

Moreover, GREAT-CARE integrates eXplainable Artificial Intelligence (XAI) methods such as GNNExplainer and Integrated Gradients to interpret and explain the recommendations. This additional step enhances transparency and trust in the recommendation process by providing insights into how the model arrives at its decisions.

GREAT-CARE represents a powerful and flexible tool to support clinical decision-making, thus contributing to improving the quality of medical care. 🩺📊🔬

Check it out on GitHub! 🚀