Cervical cancer is a potentially life-threatening disease marked by health practitioners. The late diagnosis and treatment, being quite challenging, stake the precious lives of patients. In both developed and undeveloped… Click to show full abstract
Cervical cancer is a potentially life-threatening disease marked by health practitioners. The late diagnosis and treatment, being quite challenging, stake the precious lives of patients. In both developed and undeveloped states, the formal screening for disease identification suffers due to its medical cost, unavailable health facilities, society norms, and late appearance of symptoms. Machine intelligence is cost-effective, computationally inexpensive, and early diagnosis of several types of diseases, including cervical cancer. The patients are not required to pass through contemporary and tedious medical procedures, and early diagnosis of cervical cancer is quite handy with machine-intelligent solutions. The problem with the current machine classification methods for disease identification is the reliance on a single classifier’s prediction accuracy. The adoption of single classification methods doesn’t ensure the optimum prediction due to bias, over-fitting, mishandling of noisy data, and outliers. This research study proposes an Ensemble classification method based on majority voting for an accurate diagnosis addressing the patient’s medical conditions or symptoms. The study experiments a wide range of available classifiers, namely Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Naive Bayes (NB), Multiple Perceptron (MP), J48 Trees, and Logistic Regression (LR) classifiers. The study records a significant enhancement in prediction accuracy of 94% that outperforms the prediction accuracies of single classification methods tested on the same benchmarked datasets. Thus, the proposed model bestows a second opinion to health practitioners for disease identification and timely treatment.
               
Click one of the above tabs to view related content.