Human monkeypox diagnose (HMD) strategy based on data mining and artificial intelligence techniques.

Area of Science:

• Artificial Intelligence in Healthcare
• Machine Learning for Disease Detection
• Bioinformatics and Computational Biology

Background:

• Monkeypox re-emerged in May 2022, posing a significant public health risk due to its zoonotic and human-to-human transmission.
• Early and accurate detection of monkeypox is crucial for effective disease control and management.
• Existing diagnostic methods may require improvement in speed and accuracy for emerging infectious diseases.

Purpose of the Study:

• To propose a novel artificial intelligence-based strategy, the Human Monkeypox Detection (HMD) strategy, for the early detection of monkeypox.
• To develop and evaluate a new feature selection algorithm, Improved Binary Chimp Optimization (IBCO), for identifying relevant diagnostic features.
• To introduce an Ensemble Diagnosis (ED) model that combines multiple algorithms for accurate monkeypox patient identification.

Main Methods:

• The HMD strategy employs a two-phase approach: a Selection Phase (SP) using the IBCO algorithm and a Detection Phase (DP) using an Ensemble Diagnosis (ED) model.
• The IBCO algorithm integrates filter and wrapper methods (Filter Selection Layer and Wrapper Selection Layer) for efficient and precise feature selection.
• The ED model combines Weighted Naïve Bayes (WNB), Weighted K-Nearest Neighbors (WKNN), and deep learning algorithms using a novel weighted voting mechanism.

Main Results:

• The proposed IBCO feature selection algorithm demonstrated superior performance compared to existing methods.
• The ED model achieved high diagnostic accuracy, outperforming other modern diagnostic approaches.
• The HMD strategy reported excellent performance metrics, including 98.48% accuracy, 91.1% precision, and 88.91% recall, with a low implementation time of 5.4 seconds.

Conclusions:

• The developed Human Monkeypox Detection (HMD) strategy, integrating IBCO and ED, offers a promising AI-driven solution for early and accurate monkeypox diagnosis.
• The study highlights the effectiveness of hybrid feature selection and ensemble learning techniques in improving diagnostic performance for viral diseases.
• The HMD strategy provides a robust and efficient tool for public health surveillance and clinical decision-making in managing monkeypox outbreaks.