Investigating the decrease in participation in the Dutch cervical cancer screening programme: The role of personal and organisational characteristics

Public health nurse perspectives on predicting nonattendance for cervical cancer screening through classification, ensemble, and deep learning models

OBJECTIVES

Women's attendance to cervical cancer screening (CCS) is a major concern for healthcare providers in community. This study aims to use the various algorithms that can accurately predict the most barriers of women for nonattendance to CS.

DESIGN

The real-time data were collected from women presented at OPD of primary health centers (PHCs). About 1046 women's data regarding attendance and nonattendance to CCS were included. In this study, we have used three models, classification, ensemble, and deep learning models, to compare the specific accuracy and AU-ROC for predicting non-attenders for CC.

RESULTS

The current model employs 22 predictors, with soft voting in ensemble models showing slightly higher specificity (96%) and sensitivity (93%) than weighted averaging. Bagging excels with the highest accuracy (98.49%), specificity (97.3%), and ideal sensitivity (100%) with an AUC of 0.99. Classification models reveal Naive Bayes with higher specificity (97%) but lower sensitivity (91%) than Logistic Regression. Random Forest and Neural Network achieve the highest accuracy (98.49%), with an AUC of 0.98. In deep learning, LSTM has an accuracy of 95.68%, higher specificity (97.60%), and lower sensitivity (93.42%) compared to other models. MLP and NN showed the highest AUC values of 0.99.

CONCLUSION

Employing ensemble and deep learning models proved most effective in predicting barriers to nonattendance in cervical screening.

Impact of health-related behavioral factors on participation in a cervical cancer screening program: the lifelines population-based cohort

BACKGROUND

Regular participation in cervical cancer screening is critical to reducing mortality. Although certain sociodemographic factors are known to be associated with one-time participation in screening, little is known about other factors that could be related to regular participation. Therefore, this study evaluated the association between health-related behavioral factors and regular participation in cervical cancer screening.

METHODS

The Lifelines population-based cohort was linked to data for cervical cancer screening from the Dutch Nationwide Pathology Databank. We included women eligible for all four screening rounds between 2000 and 2019, classifying them as regular (4 attendances), irregular (1-3 attendances), and never participants. Multinomial logistic regression was performed to evaluate the association between behavioral factors and participation regularity, with adjustment made for sociodemographic factors.

RESULTS

Of the 48,325 included women, 55.9%, 35.1%, and 9% were regular, irregular, and never screening participants. After adjustment for sociodemographic factors, the likelihood of irregular or never screening participation was increased by smoking, obesity, marginal or inadequate sleep duration, alcohol consumption and low physical activity, while it was decreased by hormonal contraception use.

CONCLUSION

An association exists between unhealthy behavioral factors and never or irregular participation in cervical cancer screening.

Sociodemographic Characteristics and Screening Outcomes of Women Preferring Self-Sampling in the Dutch Cervical Cancer Screening Programme: A Population-Based Study

BACKGROUND

In the Netherlands, lower high-risk human papillomavirus (hrHPV) positivity but higher cervical intraepithelial neoplasia (CIN) 2+ detection were found in self-collected compared with clinician-collected samples. To investigate the possible reason for these differences, we compared sociodemographic and screening characteristics of women and related these to screening outcomes.

METHODS

We extracted data from PALGA on all primary hrHPV screens and associated follow-up tests for 857,866 screened women, invited in 2017 and 2018. We linked these data with sociodemographic data from Statistics Netherlands. Logistic regression was performed for hrHPV positivity and CIN 2+/3+ detection.

RESULTS

Out of the 857,866 women, 6.8% chose to use a self-sampling device. A higher proportion of self-sampling users was ages 30 to 35 years, was not previously screened, was living in a one-person household, or was the breadwinner in the household. After adjustment for these factors self-sampling had lower hrHPV positivity (aOR, 0.65; 95% CI, 0.63-0.68)) as compared with clinician-collected sampling, as well as lower odds of CIN 2+ (aOR, 0.76; 95% CI, 0.70-0.82) and CIN 3+ (aOR, 0.86; 95% CI, 0.78-0.95) detection.

CONCLUSIONS

It is likely that the observed differences between the two sampling methods are not only related to sociodemographic differences, but related to differences in screening test accuracy and/or background risk.

IMPACT

Self-sampling can be used for targeting underscreened women, as a more convenient screening tool. Further investigation is required to evaluate how to implement self-sampling, when it is used as a primary instrument in routine screening. See related commentary by Arbyn et al., p. 159.

Organized Breast and Cervical Cancer Screening: Attendance and Determinants in Rural China

To evaluate the attendance and determinants of organized cervical and breast cancer (two-cancer) screening, especially higher-level factors, we conducted a cross-sectional survey in central China from June 2018 to November 2019 among 1949 women (age ≥ 35 years). We examined organizer-level factors, provider-level factors, receiver-lever factors and attendance and participation willingness of screening. The results indicate that the attendance and participation willingness of organized two-cancer screening was 61.19% and 77.15%, respectively. After adjustment for potential confounders, women who received screening notification were more likely to have greater participation willingness and higher attendance than those who received no notification (adjusted odds ratio [aOR] = 1.59, 95% confidence interval [CI]: 1.27-1.99; aOR = 98.03, 95% CI: 51.44-186.82, respectively). Compared with being notified about screening by GPs, being notified by community women's leaders and other community leaders were more likely to lead to greater willingness to participate again (aOR = 2.86, 95% CI: 1.13-7.24; aOR = 3.27, 95% CI: 1.26-8.48, respectively) and recommending screening to others (aOR = 2.18, 95% CI: 1.02-4.65; aOR = 4.14, 95% CI: 1.84-9.30, respectively). The results suggest that notification of women about screening by community leaders is an important organizer-level factor. As a part of public health services, the design and implementation of optimal cancer screening strategies may require public-sector involvement at the organizer level instead of a one-man show by the health sector.

Experiences and preferences towards collecting a urine and cervicovaginal self-sample among women attending a colposcopy clinic

•

In a colposcopy referral population, the majority of women consider self-collection of a urine sample and a cervicovaginal self-sample acceptable and easy to collect in a home-based setting.

•

Urine collection is worth investigating as a potential screening method to possibly improve attendance rates in cervical cancer screening.

The effectiveness of cervical cancer screening is hampered by low attendance rates. The collection of a urine sample is hypothesized to engage non-attenders in cervical cancer screening. The aim of this prospective cohort study was to evaluate experiences of women on urine collection and cervicovaginal self-sampling in a home-based setting and preferences for future cervical cancer screening. This study included 140 women, with a median age of 40 years, who were planned for a large loop excision of the transformation zone (LLETZ) procedure. All women collected a urine sample using conventional urine cups and a cervicovaginal self-sample prior to the LLETZ in a home-based setting. Following sample collection, women filled in a questionnaire. Results showed that the instructions of urine collection and cervicovaginal self-sampling were considered clear (95%, 95%CI: 88–98; 92%, 95%CI: 83–96, respectively). Women considered urine collection compared to cervicovaginal self-sampling to be more acceptable (p < 0.001), and to provide more reliable results (p < 0.001). The three highest reported preferred sampling methods for future cervical cancer screening were: urine collection (n = 39, 28%, 95%CI: 19–39), clinician-taken cervical scrape (n = 32, 23%, 95%CI: 15–34), and equal preference for urine collection, clinician-taken cervical scrape and cervicovaginal self-sampling (n = 30, 21%, 95%CI: 14–32). In conclusion, urine collection and cervicovaginal self-sampling are acceptable sampling methods, considered easy to collect in a home-based setting, and moreover, considered trustworthy. Although these results are promising, more research is required to determine if urine collection also lowers the barrier for non-attendees and, thereby, increases the attendance rates of cervical cancer screening.