IOTEML: An Internet of Things (IoT)-Based Enhanced Machine Learning Model for Tumour Investigation

Area of Science:

• Medical Technology
• Artificial Intelligence
• Machine Learning

Background:

• Rising incidence of diseases, particularly tumors, necessitates advanced diagnostic tools.
• Current medical field advancements focus on Internet of Things (IoT) devices and artificial intelligence (AI) for improved healthcare solutions.
• Early cancer detection is crucial for effective treatment and patient outcomes.

Purpose of the Study:

• To propose an improved algorithm named Internet of Things-based enhanced machine learning (IoT-EML) for tumor diagnosis.
• To develop a system capable of analyzing tumor characteristics such as size, shape, and location.
• To enhance early cancer detection rates through AI-driven analysis.

Main Methods:

• Development of a novel algorithm: Internet of Things-based enhanced machine learning (IoT-EML).
• Implementation of specialized functions within the algorithm for diagnosing different tumor types.
• Analysis of key tumor attributes including size, shape, and location.

Main Results:

• The proposed IoT-EML model achieved high performance metrics: 94.56% accuracy, 94.12% precision, 94.98% recall, and 95.12% F1-score.
• The model demonstrated an execution time of 1856 ms.
• Simulations confirmed the superior intelligence and efficacy of the IoT-EML model compared to existing methods.

Conclusions:

• The developed IoT-EML model shows significant promise for accurate and efficient tumor diagnosis.
• Early detection capabilities are enhanced, potentially leading to improved cancer treatment outcomes.
• The integration of IoT and AI in medical diagnostics represents a significant advancement in healthcare technology.