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

Abstract

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.