# Classification of angioedema types using decision tree modeling

## TL;DR

This paper introduces a machine learning model to help diagnose different types of angioedema, a condition marked by swelling, with high accuracy and agreement with expert diagnoses.

## Contribution

The first machine learning algorithm designed to pre-assess and aid in the diagnosis of angioedema types.

## Key findings

- The optimized random forest model achieved up to 94% true positive rate for hereditary angioedema due to C1 inhibitor deficiency.
- The model showed 89.2% accuracy and 81.8% Kappa value across six angioedema types.
- The model's predictions showed high agreement with diagnoses made by specialists.

## Abstract

All angioedema (AE) presents with transient, localized swelling; however, the underlying causes, prognosis, and treatments vary significantly. Consequently, identifying a specific AE type is challenging.

We aimed to apply a machine learning (ML) model to improve AE diagnosis. Random forest (RF) ML was used to create a prediction model for diagnosing correct AE types. Development comprised a literature search to establish AE's clinical characteristics, developing and translating questions in collaboration with 12 European AE centers, and selecting, testing, validating and optimizing the established ML model. Analysis included 342 specialist-diagnosed patients with one of six AE types.

The final optimized RF model correctly identified AE types with true positive rates of up to 94% in hereditary AE due to C1 inhibitor deficiency (C1INH), with a Percentage Accuracy of 89·2% and a Kappa value of 81·8% across the six AE types, with a high agreement with the diagnoses made by experts.

This is the first ever reported ML algorithm designed to pre-assess to aid AE diagnosis.