{"title":"Public health nurse perspectives on predicting nonattendance for cervical cancer screening through classification, ensemble, and deep learning models.","authors":"Seeta Devi, Rupali Gangarde, Shubhangi Deokar, Sayyed Faheemuddin Muqeemuddin, Sanidhya Rajendra Awasthi, Sameer Shekhar, Raghav Sonchhatra, Sonopant Joshi","doi":"10.1111/phn.13334","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Design: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusion: </strong>Employing ensemble and deep learning models proved most effective in predicting barriers to nonattendance in cervical screening.</p>","PeriodicalId":54533,"journal":{"name":"Public Health Nursing","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Public Health Nursing","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/phn.13334","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NURSING","Score":null,"Total":0}
引用次数: 0
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.
期刊介绍:
Public Health Nursing publishes empirical research reports, program evaluations, and case reports focused on populations at risk across the lifespan. The journal also prints articles related to developments in practice, education of public health nurses, theory development, methodological innovations, legal, ethical, and public policy issues in public health, and the history of public health nursing throughout the world. While the primary readership of the Journal is North American, the journal is expanding its mission to address global public health concerns of interest to nurses.