Building a predictive model to assist in the diagnosis of cervical cancer

Aim: Cervical cancer is still one of the most common gynecologic cancers in the world. Since cervical cancer is a potentially preventive cancer, earlier detection is the most effective technique for decreasing the worldwide incidence of the illness. Materials and methods: This research presents a novel ensemble technique for predicting cervical cancer risk. Specifically, the authors introduce a voting classifier that aggregates prediction probabilities from multiple machine-learning models: logistic regression, K-nearest neighbor, decision tree, XGBoost and multilayer perceptron. Results: The average accuracy, precision, recall and f1-score of the voting classifier were 96.6, 97.4, 95.9 and 96.6, respectively. Furthermore, the voting algorithm gains average high values for all evaluation metrics (accuracy, precision, recall and f1-score). The f1-score of the algorithm is 96%, which demonstrates the robustness of the model. Conclusion: The findings suggest that the probability of having cervical cancer can be accurately predicted utilizing the voting technique.

Students’ Knowledge about Cervical Cancer Prevention in Poland

Background and Objectives: In Poland, the rates of morbidity and mortality due to cervical cancer are amongst the highest in Europe. A significant percentage of newly diagnosed cases of cervical cancer are at an advanced stage. Unfortunately, only about 20% of Polish women take part in cervical cancer screening. The aim of the study was to assess students’ knowledge of cervical cancer risk factors and prevention. Materials and Methods: The study was provided to Polish students from various universities and faculties between May 2020 and November 2020. The questionnaire was designed specifically for this study and was validated. The chi-square test was used to compare the responses between subgroups. Results: The study was carried out on a group of 995 students (80.6% women, 19% men, 0.4% no data), (average age 21.9 years). Most students knew that the main risk factor for cervical cancer is human papillomavirus (HPV) infection (82% of all responders; 86% of medical students; 73% of non-medical students; p < 0.001). Only 40% of students knew that in Poland the Population Prevention and Early Diagnosis Program is carried out on women aged 25–59 years every three years. Most students correctly indicated that cervical cancer screening in Poland is performed using cervical cytology and were familiar with the basis of cytology. Only 57% of students knew that there are no specific early symptoms of cervical cancer. A total of 78% of all respondents knew that HPV vaccination reduces the risk of cervical cancer. Medical students and students who are sexually active demonstrated a better knowledge of cervical cancer. Conclusions: The Polish students had some knowledge of cervical cancer risk factors and primary and secondary prevention. Significantly better knowledge was demonstrated by medical students. Some efforts should be made to ensure that young people, who are not associated with medicine are better educated about cervical cancer in order to reduce the overall incidence and improve early detection rates.

A prospective case-control study on the association of intrauterine devices and cervical cancer risk; data from two educational centers

Introduction: Cervical cancer is the second most common type of cancer among women all over the world. Objectives: This study was conducted to demonstrate the effect of intrauterine devices (IUDs) on cervical cancer and precancerous lesions development. Patients and Methods: This study was conducted in two different hospitals in Isfahan on 200 samples, since 100 of them had results indicating cervical cancer, and the rest had no abnormal lesions. For both groups, a questionnaire was filled out for IUD users and some related risk factors such as age, parity, abortions, smoking, previous Pap smear results contained sexually transmitted diseases (STDs) infections and the contraception method. Results: In this study, more cases of IUD use were recorded in the control group. We found that the use of natural methods did not prevent the development of precancerous lesions. In the results of the Pap smear, a large number were recorded as having a history of human papillomavirus (HPV). Additionally, a high percentage of cervical cancer patients’ smoking or passive smoking. We also recorded that 53% had more than two children, while the percentages of women at the birth of their first child and who did not have an abortion were almost equal in the two groups. Conclusion: Our analysis demonstrated that IUD use is a contraceptive method with the capability of lowering the risk of cervical cancer progression. There is also an association between HPV infection, smoking, age, the number of parity and the usage of natural birth control methods with the development of cancerous lesion development.

Indonesian Self-Risk Assessment for Cervical Cancer (SiNara): Instrument Development and Validation

Background: Women’s ignorance of cervical cancer risk factors has caused low participation in the screening of the disease. Women can independently assess cervical cancer risk factors in themselves through a risk assessment instrument. However, no instruments were found that assessed cervical cancer risk based on the characteristics of Indonesian women.Purpose: This study aimed to develop and validate an Indonesian self-risk instrument for cervical cancer.Methods: The instrument was developed based on scale development following the guidelines by DeVellis (2017). A cross-sectional study was implemented to validate the instrument. A total of 20 women were involved in the pre-testing, and as many as 200 women were included in the instrument testing. Based on the scale development guidelines, data collection was initiated with a literature review to determine the instrument construct and item pool. A total of 29 articles were used in the formulation of the item pool and resulted in 38 items for validity and reliability testing. Content validity ratio (CVR) and content validity index (CVI) were used to test the content validity of the instrument, which was reviewed by three experts. Exploratory factor analysis (EFA) with principal component analysis (PCA) method and Kuder-Richardson 20 (KR-20) were used to evaluate construct validity and internal consistency reliability, respectively.Results: A total of 26 items met the content validity and 21 items met the construct validity evaluation, with five items being removed because they had a loading factor value of <0.4. After the validity were evaluated, the instrument was reduced from 38 items to 21 items. The internal consistency reliability with Kuder-Richardson 20 (KR-20) was 0.807.Conclusion: The Indonesian self-risk assessment for cervical cancer (SiNara) instrument is of good validity and reliability. However, it needs to be tested in other settings using larger samples to measure its psychometric properties as well as its applicability and acceptability.

Cervical Cancer Diagnosis Model Using Extreme Gradient Boosting and Bioinspired Firefly Optimization

Cervical cancer is frequently a deadly disease, common in females. However, early diagnosis of cervical cancer can reduce the mortality rate and other associated complications. Cervical cancer risk factors can aid the early diagnosis. For better diagnosis accuracy, we proposed a study for early diagnosis of cervical cancer using reduced risk feature set and three ensemble-based classification techniques, i.e., extreme Gradient Boosting (XGBoost), AdaBoost, and Random Forest (RF) along with Firefly algorithm for optimization. Synthetic Minority Oversampling Technique (SMOTE) data sampling technique was used to alleviate the data imbalance problem. Cervical cancer Risk Factors data set, containing 32 risks factor and four targets (Hinselmann, Schiller, Cytology, and Biopsy), is used in the study. The four targets are the widely used diagnosis test for cervical cancer. The effectiveness of the proposed study is evaluated in terms of accuracy, sensitivity, specificity, positive predictive accuracy (PPA), and negative predictive accuracy (NPA). Moreover, Firefly features selection technique was used to achieve better results with the reduced number of features. Experimental results reveal the significance of the proposed model and achieved the highest outcome for Hinselmann test when compared with other three diagnostic tests. Furthermore, the reduction in the number of features has enhanced the outcomes. Additionally, the performance of the proposed models is noticeable in terms of accuracy when compared with other benchmark studies for cervical cancer diagnosis using reduced risk factors data set.

Cervical cancer risk and access: Utilizing three statistical tools to assess Haitian women in South Florida

Although decreasing rates of cervical cancer in the U.S. are attributable to health policy, immigrant women, particularly Haitians, experience disproportionate disease burden related to delayed detection and treatment. However, risk prediction and dynamics of access remain largely underexplored and unresolved in this population. This study seeks to assess cervical cancer risk and access of unscreened Haitian women. Extracted and merged from two studies, this sample includes n = 346 at-risk Haitian women in South Florida, the largest U.S. enclave of Haitians (ages 30–65 and unscreened in the previous three years). Three approaches (logistic regression [LR]; classification and regression trees [CART]; and random forest [RF]) were employed to assess the association between screening history and sociodemographic variables. LR results indicated women who reported US citizenship (OR = 3.22, 95% CI = 1.52–6.84), access to routine care (OR = 2.11, 95%CI = 1.04–4.30), and spent more years in the US (OR = 1.01, 95%CI = 1.00–1.03) were significantly more likely to report previous screening. CART results returned an accuracy of 0.75 with a tree initially splitting on women who were not citizens, then on 43 or fewer years in the U.S., and without access to routine care. RF model identified U.S. years, citizenship, and access to routine care as variables of highest importance indicated by greatest mean decreases in Gini index. The model was .79 accurate (95% CI = 0.74–0.84). This multi-pronged analysis identifies previously undocumented barriers to health screening for Haitian women. Recent US immigrants without citizenship or perceived access to routine care may be at higher risk for disease due to barriers in accessing U.S. health-systems.