Efficient lung cancer detection using computational intelligence and ensemble learning.

Area of Science:

• Computational intelligence
• Medical informatics
• Artificial intelligence in healthcare

Background:

• Lung cancer is a leading cause of cancer mortality, necessitating early detection for effective treatment.
• Current diagnostic methods face challenges with high false-positive rates and accuracy limitations.
• Advancements in computational intelligence and the Internet of Medical Things (IoMT) offer potential for improved lung cancer detection.

Purpose of the Study:

• To develop an ecologically considerate lung cancer therapy prototype model using computational intelligence.
• To propose an Internet of Medical Things (IoMT)-based framework for patient-centered lung cancer care.
• To enhance lung cancer detection accuracy and efficiency, addressing current diagnostic challenges.

Main Methods:

• Utilized Logistic Regression, MLP Classifier, and Gaussian NB Classifier for lung cancer detection.
• Employed K-Means and Fuzzy Logic for intelligent feature selection.
• Integrated ensemble learning via a voting classifier and optimized hyperparameters using grid search.

Main Results:

• Achieved a high accuracy rate of 98.50% in lung cancer detection.
• Demonstrated superior performance compared to existing NB, J48, and SVM approaches.
• Showcased significant potential for time and cost savings in diagnostic procedures.

Conclusions:

• Computational intelligence and IoMT integration can lead to effective and resource-efficient lung cancer therapies.
• The proposed model offers a promising advancement in early and accurate lung cancer diagnosis.
• This research highlights the transformative potential of AI in improving cancer care outcomes.