Monkeypox diagnosis using ensemble classification.

Area of Science:

• Medical Diagnostics
• Computational Biology
• Epidemiology

Background:

• Global health systems are strained by viral outbreaks like COVID-19.
• Emerging diseases such as monkeypox pose a pandemic risk if not diagnosed promptly.
• Accurate and efficient diagnostic tools are crucial for managing infectious disease outbreaks.

Purpose of the Study:

• To introduce a novel and accurate strategy for diagnosing monkeypox.
• To enhance the early detection and management of potential monkeypox outbreaks.
• To provide a robust diagnostic framework applicable to emerging viral threats.

Main Methods:

• The Accurate Monkeypox Diagnosing Strategy (AMDS) employs a two-phase approach: pre-processing and classification.
• Feature selection is performed using the Binary Tiki-Taka Algorithm (BTTA).
• Ensemble classification combines Layered K-Nearest Neighbors (LKNN), Statistical Naïve Bayes (SNB), and Deep Learning Classifier (DLC) with a Fuzzified Voting Scheme (FVS).

Main Results:

• The proposed AMDS demonstrated superior performance in monkeypox diagnosis.
• Experimental results confirmed the high accuracy of AMDS across two distinct datasets.
• AMDS outperformed existing diagnostic strategies in identifying monkeypox cases.

Conclusions:

• The Accurate Monkeypox Diagnosing Strategy (AMDS) offers a highly accurate method for monkeypox diagnosis.
• This strategy provides a valuable tool for combating the spread of viral diseases.
• AMDS represents a significant advancement in computational diagnostics for infectious diseases.