A different way to diagnosis acute appendicitis: machine learning.

Area of Science:

• Medical Informatics
• Artificial Intelligence in Medicine
• Surgical Diagnostics

Background:

• Acute appendicitis is the most frequent reason for emergency surgery.
• Accurate and timely diagnosis is crucial for effective treatment.
• Existing diagnostic methods can be invasive or costly.

Purpose of the Study:

• To develop and evaluate a machine learning model for predicting acute appendicitis.
• To establish an easy, inexpensive, and rapid method for appendicitis diagnosis.
• To leverage patient data and algorithms for improved diagnostic accuracy.

Main Methods:

• Analysis of surgically treated patients with suspected acute appendicitis (2011-2021).
• Inclusion of patients presenting with right lower quadrant pain.
• Utilized gender and hemogram data with machine learning algorithms (Python 3.7).

Main Results:

• A voting classifier combining logistic regression, k-nearest neighbors, support vector machines, and neural networks achieved 86.2% accuracy.
• The voting classifier demonstrated 83.7% sensitivity and 88.6% specificity.
• Individual algorithms showed varying accuracies, with neural networks at 83.9% and logistic regression at 82.7%.

Conclusions:

• Machine learning provides an effective approach for diagnosing acute appendicitis.
• The developed method is practical, simple, rapid, and cost-effective.
• This AI-driven approach can aid in the early and accurate prediction of acute appendicitis.