Performance Evaluation Of Machine Learning Algorithm For Lung Cancer

Document Type : Primary Research paper


1 Dept Of Computer Applications, Kongu Engineering College, Taimlnadu, India

2 It Department, University Of Technology And Applied Science, Salalah, Oman.

3 Dept Of Computer Science & Engineering, Kongu Engineering College, India,

4 Pg Student, Dept Of Computer Applications, Kongu Engineering College, India


Background: Lung Cancer Is A Cancer That Is Difficult To Identify, And Deadly.
Early Detection Of Cancer Can Be Effective In Curing The Disease Altogether. The
Proposed Model Is An Effective Classification-Based Method, Using Machine Learning
Methods To Identify Lung Cancer Diseases. The Method Can Significantly Reduce The
Danger Of Disease Through Digging Out A Transparent And Understandable Model For
Lung Carcinoma From A Medical Database. Methods: This Work Tried To Assess The
Efficacy Of Machine Learning Algorithms In The Task Of Classifying Lung Cancer Based
On Diagnostic Levels. In This Analysis We Analyzed And Compared Various
Classifications To Identify And Predict Lung Cancer Disease. We Applied Benchmark
Machine Learning Techniques Like Support Vector Machine, K-Nearest Neighbor,
Random Forest, Linear Regression, And Logistic Regression. The Main Objective Is To
Evaluate The Precision, Accuracy, Sensitivity And Specificity Of Data Classification
Regarding The Effectiveness And Efficiency Of Algorithms. Results: The Outcome Of
The Result Has Assesses Based On Correct And Incorrect Data Which Are Exactly
Classified By A Classification Methods. The Best Performance Of These Techniques Have
Been Obtained By Svm And Logistic Techniques With The Highest Accuracy. Conclusions:
Classification Of The Detection Process Is Conducted And The Output Were Analyzed With
The Comparison Of Accuracy Among Machine Learning Techniques And The Results
Were Given Based On The Data, Respectively. This Technique Will Better Help Us
Diagnose Lung Cancer And May Save Many Lives In The Future.


Volume 12, Issue 3 - Serial Number 3
ICMMNT-2021 International Virtual Conference on Materials, Manufacturing and Nanotechnology, 30th June, 2021.
June 2021
Pages 1460-1468