Screening for the prevention and early detection of cervical cancer: protocol for systematic reviews to inform Canadian recommendations

Cervical cancer survival prediction by machine learning algorithms: a systematic review

BACKGROUND

Cervical cancer is a common malignant tumor of the female reproductive system and is considered a leading cause of mortality in women worldwide. The analysis of time to event, which is crucial for any clinical research, can be well done with the method of survival prediction. This study aims to systematically investigate the use of machine learning to predict survival in patients with cervical cancer.

METHOD

An electronic search of the PubMed, Scopus, and Web of Science databases was performed on October 1, 2022. All articles extracted from the databases were collected in an Excel file and duplicate articles were removed. The articles were screened twice based on the title and the abstract and checked again with the inclusion and exclusion criteria. The main inclusion criterion was machine learning algorithms for predicting cervical cancer survival. The information extracted from the articles included authors, publication year, dataset details, survival type, evaluation criteria, machine learning models, and the algorithm execution method.

RESULTS

A total of 13 articles were included in this study, most of which were published from 2018 onwards. The most common machine learning models were random forest (6 articles, 46%), logistic regression (4 articles, 30%), support vector machines (3 articles, 23%), ensemble and hybrid learning (3 articles, 23%), and Deep Learning (3 articles, 23%). The number of sample datasets in the study varied between 85 and 14946 patients, and the models were internally validated except for two articles. The area under the curve (AUC) range for overall survival (0.40 to 0.99), disease-free survival (0.56 to 0.88), and progression-free survival (0.67 to 0.81), respectively from (lowest to highest) received. Finally, 15 variables with an effective role in predicting cervical cancer survival were identified.

CONCLUSION

Combining heterogeneous multidimensional data with machine learning techniques can play a very influential role in predicting cervical cancer survival. Despite the benefits of machine learning, the problem of interpretability, explainability, and imbalanced datasets is still one of the biggest challenges. Providing machine learning algorithms for survival prediction as a standard requires further studies.

Determinants of Acquisition, Persistence, and Clearance of Oncogenic Cervical Human Papillomavirus Infection in the Philippines Using a Multi-Omics Approach: DEFEAT HPV Study Protocol

HPV infection is one of the most studied risk factors in cervical cancer-the second most common cancer site and cause of death due to cancer in the Philippines. However, there is a lack of population-based epidemiological data on cervical HPV infection in the Philippines. Local reports on co-infections with other lower genital tract pathogens, commonly reported globally, are also lacking, which emphasizes the need to increase efforts in targeting HPV prevalence, genotype, and distribution. Hence, we aim to determine the molecular epidemiology and natural history of HPV infection among reproductive-age Filipino women using a community-based prospective cohort design. Women from rural and urban centers will be screened until the target sample size of 110 HPV-positive women (55 from rural sites and 55 from urban sites) is reached. Cervical and vaginal swabs will be collected from all screened participants. For HPV-positive patients, HPV genotypes will be determined. One hundred ten healthy controls will be selected from previously screened volunteers. The cases and controls will comprise the multi-omics subset of participants and will be followed up after 6 and 12 months for repeat HPV screening. Metagenomic and metabolomic analyses of the vaginal swabs will also be performed at baseline, after 6 months, and after 12 months. The results of this study will update the prevalence and genotypic distribution of cervical HPV infection among Filipino women, determine whether the current vaccines used for HPV vaccination programs capture the most prevalent high-risk HPV genotypes in the country, and identify vaginal community state types and bacterial taxa associated with the natural history of cervical HPV infection. The results of this study will be used as the basis for developing a biomarker that can help predict the risk of developing persistent cervical HPV infection in Filipino women.

Comparison of Ki67 index and P16 expression in different grades of cervical squamous intraepithelial lesions

Background

the assessment of P16 expression and Ki-67 proliferative index is now proposed as an adjunct test for the diagnosis of high-risk precursor lesions for cervical cancer. The aim of the present study was to elucidate the quality expression of P16 and quantification Ki-67 index in different types of cervical intraepithelial neoplasia and also to determine the cutoff for Ki67 index to predict the severity of CIN lesions.

Methods

This cross-sectional study was conducted on patients with colposcopic indication. Selected samples with different CIN grades were examined for P16 and Ki-67 index by immunohistochemical (IHC) methods.

Results

All LSIL (CIN I) cases were negative for P16, while in 58.7% of HSIL cases (CIN 2/3), P16 was positive. The mean Ki67 index in the present study was 3.13 ± 2.65 in the upper two/third of the squamous epithelium in the LSIL group and 19.04 ±36.40 in the HSIL group, which was statistically significant. Also, the mean Ki67 index in full thickness squamous epithelium in HSIL group was significantly higher than LSIL. The sensitivity of P16 and Ki67 index in our study was 58.73%, 66.67% and the specificity was 100% and 100%, respectively.

Conclusion

Assessment of P16 expression and Ki67 index can be used to distinguish low grade (CIN1) intraepithelial lesion from high grade (CIN2/3) intraepithelial or precancerous lesions.

Evaluation of the diagnostic accuracy of the cervical biopsy under colposcopic vision

This study was conducted to evaluate the diagnostic accuracy of the cervical biopsy under colposcopic vision. This retrospective study was performed on 190 women, who were selected from a total of 412 cases referring for colposcopy in one year. All patients underwent colposcopy and loop electrosurgical excision procedure (LEEP). After the investigation of demographic characteristics and data confirmation, colposcopic characteristics were examined. Then, the diagnostic indicators and diagnostic accuracy of the cervical biopsy under colposcopic vision were determined. The mean age of patients was 35.51± 5.91 years. In smokers, the percentage of cancer and CIN3 cases was higher than in normal individuals, and this difference was statistically significant in terms of the frequency of cancerous lesions (P = 0.2). A comparison of colposcopic biopsy with LEEP has shown that the frequency of advanced cases in LEEP has been detected more, and the correlation coefficient (kappa) indicated the weak agreement between the findings of colposcopically directed biopsy (CDB) and LEEP methods. (k = 0.23). The diagnostic accuracy of the cervical biopsy under colposcopic vision for cervical cancer is effectively high. It is recommended that this procedure be performed to diagnose cancerous lesions; however, contrary to what is seen in colposcopy, malignant cases may be spreading and follow-up of patients can affect therapeutic performance.

Identification of a Ferroptosis-Related Prognostic Gene PTGS2 Based on Risk Modeling and Immune Microenvironment of Early-Stage Cervical Cancer

Background

Cervical cancer (CC) has long been a concern, as a gynecological cancer type of high-risk. At present, there are few studies on the early detection of CC at the genetic level. The breakthrough is to recognize CC patients tending to have a worse prognosis by checking the expression pattern of ferroptosis-related genes, which enjoy a great potential of being applied to cancer treatment.

Methods

Data used in this study was obtained from a series of public online databases, integrated with ferroptosis-related gene collection stored from the FerrDb database and GeneCards database. The least absolute shrinkage and selection operator- (LASSO-) penalized analysis was taken for modeling, and before, univariate Cox regression analysis got done to shrink the candidates' range. Several analyses were made for the evaluation of the efficacy of the new model, based on CC patients' overall survival (OS). Tumor microenvironment- (TME-) related analyses were conducted by various algorithms on different populations, comprising CIBERSORT, ssGSEA, XCELL, etc. Nonnegative matrix factorization (NMF) clustering got applied to find that ferroptosis-marker genes affect prognosis more than “driver” and “suppressor”. Hub-gene PTGS2 was screened out by protein-protein interaction analysis and real-time qPCR after ferroptosis induction, and ELISA was conducted for further verification on the correlation between ferroptosis and M1 polarization.

Results

The twenty-five ferroptosis-related genes model can estimate the prognosis of patients independently of other clinical factors, and the low-risk score group shows higher expression of immune-enhancing cells, noteworthily for M1 macrophages. It is experimentally validated that the M1 marker TNF-α significantly increased after coculturing M1 macrophages and SiHa cells processed with ferroptosis inductor before. The key gene to the model, PTGS2, presented to be a risk factor in cervical cancer, and its low-expression group has stronger immune activity and higher tumor mutation burden, with the significantly highly mutated gene TENM2 in it showing high drug sensitivity and neoantigen for patients with its mutant-type. Meanwhile, it influences macrophage polarization.

Conclusion

Prognosis of early-stage cervical cancer patients can be exactly predicted on ferroptosis-related genes. Among model genes, PTGS2 may have a major impact by affecting macrophage polarization and mutation effects.

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.

Liquid Biopsy in Cervical Cancer: Hopes and Pitfalls

Simple Summary

Cervical cancer is the fourth most common cancer in women worldwide, and its incidence is variably distributed between developed and less-resourced countries, in which socio-economic issues and religious beliefs often limit the widespread diffusion and the access to screening campaigns. In the “liquid biopsy” era, the application of non-invasive and repeatable techniques to the identification of diagnostic, prognostic, and predictive biomarkers might facilitate the management of this disease and, hopefully, improve its outcome. The purpose of this review is to explore the progress status of liquid biopsy in cervical cancer patients. Several methods are described, which include the analysis of circulating tumor cells, the search for pathogenic mutations on circulating tumor DNA, as well as the identification of circulating RNAs, focusing on their potential clinical applications and current limitations.

Abstract

Cervical cancer (CC) is the fourth most common cancer in women worldwide, with about 90% of cancer-related deaths occurring in developing countries. The geographical influence on disease evolution reflects differences in the prevalence of human papilloma virus (HPV) infection, which is the main cause of CC, as well as in the access and quality of services for CC prevention and diagnosis. At present, the most diffused screening and diagnostic tools for CC are Papanicolaou test and the more sensitive HPV-DNA test, even if both methods require gynecological practices whose acceptance relies on the woman’s cultural and religious background. An alternative (or complimentary) tool for CC screening, diagnosis, and follow-up might be represented by liquid biopsy. Here, we summarize the main methodologies developed in this context, including circulating tumor cell detection and isolation, cell tumor DNA sequencing, coding and non-coding RNA detection, and exosomal miRNA identification. Moreover, the pros and cons of each method are discussed, and their potential applications in diagnosis and prognosis of CC, as well as their role in treatment monitoring, are explored. In conclusion, it is evident that despite many advances obtained in this field, further effort is needed to validate and standardize the proposed methodologies before any clinical use.