RESUMEN
OBJECTIVES: Surveys can assist in screening oral diseases in populations to enhance the early detection of disease and intervention strategies for children in need. This paper aims to develop short forms of child-report and proxy-report survey screening instruments for active dental caries and urgent treatment needs in school-age children. METHODS: This cross-sectional study recruited 497 distinct dyads of children aged 8-17 and their parents between 2015 to 2019 from 14 dental clinics and private practices in Los Angeles County. We evaluated responses to 88 child-reported and 64 proxy-reported oral health questions to select and calibrate short forms using Item Response Theory. Seven classical Machine Learning algorithms were employed to predict children's active caries and urgent treatment needs using the short forms together with family demographic variables. The candidate algorithms include CatBoost, Logistic Regression, K-Nearest Neighbors (KNN), Naïve Bayes, Neural Network, Random Forest, and Support Vector Machine. Predictive performance was assessed using repeated 5-fold nested cross-validations. RESULTS: We developed and calibrated four ten-item short forms. Naïve Bayes outperformed other algorithms with the highest median of cross-validated area under the ROC curve. The means of best testing sensitivities and specificities using both child-reported and proxy-reported responses were 0.84 and 0.30 for active caries, and 0.81 and 0.31 for urgent treatment needs respectively. Models incorporating both response types showed a slightly higher predictive accuracy than those relying on either child-reported or proxy-reported responses. CONCLUSIONS: The combination of Item Response Theory and Machine Learning algorithms yielded potentially useful screening instruments for both active caries and urgent treatment needs of children. The survey screening approach is relatively cost-effective and convenient when dealing with oral health assessment in large populations. Future studies are needed to further leverage the customize and refine the instruments based on the estimated item characteristics for specific subgroups of the populations to enhance predictive accuracy.
Asunto(s)
Caries Dental , Humanos , Caries Dental/diagnóstico , Caries Dental/epidemiología , Caries Dental/terapia , Estudios Transversales , Teorema de Bayes , Encuestas y Cuestionarios , Aprendizaje AutomáticoRESUMEN
BACKGROUND: African American women are disproportionately at risk for HIV infection. To increase women's readiness to consider taking pre-exposure prophylaxis (PrEP), we conducted a pilot study of Women Prepping for PrEP Plus (WP3+). Adapted from an evidence-based HIV risk reduction intervention for African American couples who are HIV-serodiscordant, WP3+ is a group-based culturally congruent program designed for African American women without HIV. METHODS: Women were screened for eligibility; if eligible, they were invited to participate in the four-session WP3+ group. Participants completed surveys at baseline (n = 47) and post-implementation (n = 28); surveys assessed demographics, HIV and PrEP knowledge, depression and posttraumatic stress (PTS) symptoms, substance use, sexual risk behaviors, health care-related discrimination, and social support. In a process evaluation, a subset of women completed qualitative interviews at baseline (n = 35) and post-implementation (n = 18); the interviews were designed to converge with (e.g., on HIV and PrEP knowledge) and expand upon (e.g., unmeasured perceived impacts of WP3+) quantitative measures. To triangulate with the quantitative data, deductive qualitative analysis concentrated on women's knowledge and awareness of PrEP and HIV, their relationship dynamics and challenges, and their considerations (e.g., barriers, facilitators) related to taking PrEP; inductive analysis focused on women's experiences in the intervention. RESULTS: Participants in the WP3+ intervention reported: improved proportion of condom use in the past 90 days (p < .01) and in a typical week (p < .05); reduced PTS symptoms (p < .05); increased HIV knowledge (p < .0001) and awareness of PrEP (p < .001); and greater consideration of using PrEP (p < .001). In interviews, participants expressed not only increased knowledge but also appreciation for learning how to protect themselves against HIV, communicate with their partners, and take charge of their health, and they expressed greater receptiveness to using PrEP as a result of the knowledge and skills they gained. CONCLUSIONS: The WP3+ pilot study demonstrated preliminary efficacy and acceptability as an HIV-prevention program for African American women. A controlled trial is needed to confirm its efficacy for increasing PrEP use among African American women.