Artificial intelligence for cervical cancer screening: Scoping review, 2009-2022

BACKGROUND

The intersection of artificial intelligence (AI) with cancer research is increasing, and many of the advances have focused on the analysis of cancer images.

OBJECTIVES

To describe and synthesize the literature on the diagnostic accuracy of AI in early imaging diagnosis of cervical cancer following Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR).

SEARCH STRATEGY

Arksey and O'Malley methodology was used and PubMed, Scopus, and Google Scholar databases were searched using a combination of English and Spanish keywords.

SELECTION CRITERIA

Identified titles and abstracts were screened to select original reports and cross-checked for overlap of cases.

DATA COLLECTION AND ANALYSIS

A descriptive summary was organized by the AI algorithm used, total of images analyzed, data source, clinical comparison criteria, and diagnosis performance.

MAIN RESULTS

We identified 32 studies published between 2009 and 2022. The primary sources of images were digital colposcopy, cervicography, and mobile devices. The machine learning/deep learning (DL) algorithms applied in the articles included support vector machine (SVM), random forest classifier, k-nearest neighbors, multilayer perceptron, C4.5, Naïve Bayes, AdaBoost, XGboots, conditional random fields, Bayes classifier, convolutional neural network (CNN; and variations), ResNet (several versions), YOLO+EfficientNetB0, and visual geometry group (VGG; several versions). SVM and DL methods (CNN, ResNet, VGG) showed the best diagnostic performances, with an accuracy of over 97%.

CONCLUSION

We concluded that the use of AI for cervical cancer screening has increased over the years, and some results (mainly from DL) are very promising. However, further research is necessary to validate these findings.

Barriers to adherence to cytology exam: a case study in low-income Colombian women

BACKGROUND

Cervical cytology is essential for the early detection of cervical cancer. However, in Colombia, only 50% of women with subsidized health insurance were screened in 2019, compared to 100% of women with contributory insurance. This disparity highlights significant barriers that must be addressed. This study aimed to identify the factors that contribute to or hinder adherence to cervical cytology screening among low-income women with subsidized health insurance in a public primary care network in Cali, Colombia, from 2014 to 2018.

METHODS

In a qualitative case study, the experience of women and health care and administrative personnel was recovered. Forty-seven women participated in seven focus group discussions. Five other women using the program participated in in-depth interviews. Finally, we interviewed eight people from the healthcare area and the health services administration. The qualitative data collected underwent content analysis, guided by the theoretical framework of Social Determinants of Health. Within this framework, five interconnected dimensions that influence adherence were incorporated.

RESULTS

Adherence is a multifactorial phenomenon, and in relation to attendance at cervical cytology, the analysis delved into the mechanisms that affect it in a low-income context. Barriers to adherence were identified across multiple dimensions, including social and economic factors, health conditions, and patient-related factors, among both adherent and non-adherent women. Among adherent women, barriers and facilitators related to the healthcare team and system, as well as patient-related factors, were identified.

CONCLUSIONS

The findings of this research can be useful in developing personalized interventions and strategies to improve adherence and screening outcomes in low-income settings. It is necessary to increase the resources of health insurance entities to establish effective communication channels with women who attend the cervical cancer prevention program.

Women's critical experiences with the pap smear for the development of cervical cancer screening devices

Global cervical cancer incidence and mortality have remained a major public health problem. Depending on the quality and coverage of preventive programs, and the capacity of health care systems, different screening tests are used, with the Pap smear being the most widely implemented. Several difficulties have been reported in accessing timely detection, causing late cervical cancer diagnosis. Trying to close these gaps, new screening devices have been developed in recent years; however, there is a lack of knowledge about whether or not women perspective has been included in the design process and technological development of these devices. This scoping review aimed to describe and synthesize scientific literature on women's critical experiences with Pap smears to prospectively contribute to the design, development, and scale-up of cervical cancer screening devices. The electronic databases Web of Science, Scopus, PubMed, PsycINFO and SciELO were searched for relevant studies published between 2012 and 2021; finally, 18 qualitative studies were included. Experiences were classified into four categories: fear and embarrassment, speculum pain and discomfort, outcome distress and health service barriers. Critical experiences before, during, and after the test were analyzed in turn. In particular, during the test, women reported pain associated with the use of the speculum. The acceptability of new screening devices will largely depend on comfort during the test and timely delivery of results. This review provides a useful qualitative synthesis, not only to advance the design of novel devices but also for future implementation research in cervical screening services.

Innovative prototypes for cervical cancer prevention in low-income primary care settings: A human-centered design approach

This article presents the design process of innovative prototypes for cervical cancer prevention in primary care centers located in low-income settings in Cali, Colombia, using the Human-Centered Design (HCD). The project was developed in collaboration with a public healthcare network comprised of 38 urban and rural centers with women between the ages of 25 and 65 years, healthcare providers of the cancer program, healthcare administrators and the general manager of said network. Our HCD process involved five stages: research, need synthesis, ideation and co-design process, prototyping and in-context usability testing. In practice, some of the stages are overlapped and iterated throughout the design process. We conducted observations, open-ended interviews and conversations, multi-stakeholder workshops, focus groups, systematic text condensation analyses and tests in real contexts. As a result, we designed four prototypes: (1) 'Encanto': An educational manicure service, (2) 'No le des la espalda a la citología': A media-based strategy, (3) An educational wireless queuing device in the waiting room, and (4) Citobot: A cervical cancer early detection device, system, and method. The tests carried out with each prototype showed their value, limitations and possibilities in terms of subsequent development and validation through public health research or clinical research. We recognize that a longer-term evaluation is required in order to determine whether the prototypes will be used regularly, integrated into cervical cancer screening services and effectively improve access to cytology as a screening test. We conclude that HCD is a useful for design-based prevention in the field of cervical cancer. The integration of this approach with public health research would allow the generation of evidence during to the formulation of policies and programs as well as optimize existing interventions and, ultimately, facilitate the scalability and financing of what actually works.