Prediction and Detection of Cervical Malignancy Using Machine Learning Models

Abstract

Objective: Human papillomavirus and other predicting factors are responsible causing cervical cancer, and early prediction and diagnosis is the solution for preventing this condition. The objective is to find out and analyze the predictors of cervical cancer and to study the issues of unbalanced datasets using various Machine Learning (ML) algorithm-based models. Methods: A multi-stage sampling strategy was used to recruit 501 samples for the study. The educational intervention was the video-assisted counseling which is consisted of two educational methods: a documentary film and face-to- face interaction with women followed by reminders. Following the collection of baseline data from these subjects, they were encouraged to undergo Pap smear screening. Women having abnormal Pap tests were sent for biopsy. Machine learning classification methods such as Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), Multi-layer Perceptron (MLP) and Naive Bayes(NB) were used to evaluate the unbalanced input and target datasets. Result: Merely 398 women out of 501 showed an interest to participate in the study, but only 298 stated a willingness for cervical screening. Atypical malignant cells were discovered on the cervix of 26 women who had abnormal pap tests. These women had guided for further tests, such as a cervical biopsy, and seven women had been diagnosed with cervical cancer. LR in models 1, 2, and 4 showed 88% to 94% sensitivity with 84% to 89% accuracy, respectively for cervical cancer prediction, whereas DT in models 3, 5, and 6 algorithms exhibited 83% to 84% sensitivity with 84% to 88% accuracy, respectively. The NB and LR algorithms produced the highest area under the ROC curve for testing dataset, but all models performed similarly for training data. Conclusion: In current study , Logistic Regression and Decision Tree algorithms were identified as the best-performed ML algorithm classifiers to detect the significant predictors.

Meticulous Review: Cutting-Edge Cervix Cancer Stratification Using Image Processing And Machine Learning

“…Cancer remains the major leading cause for death among women across the globe [1], [2]. There is a significant prevalence of cervical cancer patients in developing nations such as India and China [3].…”

“…Based on the Statistics derived from the WHO Global Health Estimates-2019 [4], [5], [6], out of 656 300 000 total population of females in India, 4 191 000 females died due to cervical cancer [7]. Even though cervical cancer falls into a category of cancers that can be readily prevented through vaccination [2] and has an extended pre-malignant phase [8], [9], [10] which can be utilized for detection and treatment of the disease, lack of awareness is the key reason for this mortality rate in developing countries [11], [9], [12], [13], [14]. Cervical cancer is developed in the cervix area of the vagina the entrance of the uterus in women [3].…”

“…These algorithms implement various probabilistic, statistical and optimization techniques that allow the system to review/ learn from past records and to identify the complex patterns/solutions from the large, complex and noisy structured semi-structured or unstructured datasets [31], [19]. Augmenting machine learning with image processing techniques facilitates automization of pap-smear analysis and generates authentic and accurate results in a faster way [15], [19], [6], [32], [2]. Machine learning algorithms such as Artificial Neural Network (ANN) [33], [13], [5], [6], Neural Network (NN), Support Vector Machine (SVM) [17], [5], Linear Discriminant Analysis (LDA) [24], [20], K-nearest neighbor (KNN) [5], Decision Trees [34], [20], [13], Random Forest (RF) [18], [17], [6], Gray Level Cooccurrence Matrix (GLCM) [33], C5.0, Multivariate Adaptive Regression Splines (MARS), spatial fuzzy clustering algorithms [35], Probabilistic Neural Networks (PNNs), Classification and Regression Trees (CART), Genetic Algorithm, and Hierarchical clustering algorithm are being used at various stages of automatic cervical cancer detection [12], [36], [37], [5], [38], [32].…”

Investigation of factors influencing low physical activity levels in community-dwelling older adults with chronic pain: a cross-sectional study

“…Machine learning analysis has not yet been used in survey research on CP populations, but it could provide a better predictive model. A growing number of studies have demonstrated that ANN have better predictive accuracy than traditional regression analysis 14 , 15 . This study seeks to validate the accuracy of using MLP as a model for predicting physical activity levels among community-dwelling older adults with CP, and to compare it with a conventionally used logistic regression (LR) model.…”