{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T12:02:02Z","timestamp":1784635322542,"version":"3.55.0"},"reference-count":36,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["J Dent Res"],"abstract":"<jats:p>Dental caries is a highly prevalent chronic condition requiring accurate tools to identify at-risk patients and guide preventive care. Most existing caries risk models provide only binary predictions and overlook time-to-event information. Considering that modern caries management relies on risk assessment during routine dental examinations, we developed RT2C, a survival model based on a recurrent neural network (RNN). This model supports caries risk management by assessing the likelihood (Caries Management by Risk Assessment [CAMBRA]) that a patient will be diagnosed with new caries by the next visit. It also estimates the time until this event occurs, using structured longitudinal dental data. Data were extracted from 4 dental organizations, comprising 466,782 patients and 1,062,553 examination visits (D0120, D0150, D0145) between 2019 and 2023. Structured electronic dental record (EDR) data included demographics, dental care history, clinical findings, and the CAMBRA\u2013caries risk assessment (CRA). Patients were split into development (326,748 patients; 744,624 visits), validation (46,678; 106,616), and test (93,356; 211,313) sets, with similar event rates (~20%). The RT2C model used a bidirectional gated recurrent unit network to capture temporal dependencies across visits and estimate individualized survival probabilities. Model performance was compared against a Cox proportional hazards model and a random survival forest using the concordance index (C-index), integrated Brier score, and calibration analysis. Subgroup analyses evaluated generalizability across insurance types, age groups, racial groups, and CRA-based risk groups. The RT2C model achieved the highest concordance index on the held-out test set (0.883\u2009\u00b1\u20090.08), outperforming the CRA-only and traditional survival baselines. Performance remained consistent across demographic and clinical subgroups, demonstrating robustness and fairness across diverse populations. RT2C models visit-indexed risk trajectories and predicted new caries occurrence by the subsequent visit, aligning with the preventive framework of CAMBRA. By integrating longitudinal EDR data, it adds value to existing CRA tools and supports proactive, personalized caries management.<\/jats:p>","DOI":"10.1177\/00220345261462463","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T12:02:01Z","timestamp":1784376121000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["RT2C: Predicting Time-to-New Caries with Structured Dental Data Using RNN"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1923-0730","authenticated-orcid":false,"given":"X.","family":"Liu","sequence":"first","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center in Houston, Houston, TX, USA"},{"name":"School of Public Health, University of Texas Health Science Center in Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K.K.","family":"Kookal","sequence":"additional","affiliation":[{"name":"School of Dentistry, University of Texas Health Science Center in Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Brandon","sequence":"additional","affiliation":[{"name":"Willamette Dental Group and Skourtes Institute, Hillsboro, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D.B.","family":"Rindal","sequence":"additional","affiliation":[{"name":"HealthPartners Institute, Bloomington, MN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J.","family":"Mullins","sequence":"additional","affiliation":[{"name":"Willamette Dental Group and Skourtes Institute, Hillsboro, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8950-697X","authenticated-orcid":false,"given":"J.M.","family":"White","sequence":"additional","affiliation":[{"name":"School of Dentistry, University of California, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.F.","family":"Walji","sequence":"additional","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center in Houston, Houston, TX, USA"},{"name":"School of Dentistry, University of Texas Health Science Center in Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2644-4908","authenticated-orcid":false,"given":"L.","family":"Rasmy","sequence":"additional","affiliation":[{"name":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center in Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Bangar S et al. 2022. Caries risk documentation and prevention: eMeasures for dental electronic health records. Appl Clin Inform. 13(1):80\u201390. https:\/\/doi.org\/10.1055\/s-0041-1740920","DOI":"10.1055\/s-0041-1740920"},{"key":"e_1_3_2_3_1","doi-asserted-by":"crossref","unstructured":"Brandon RG et al. 2022. Development of quality measures to assess tooth decay outcomes from electronic health record data. J Public Health Dent. 83(1):33\u201342. https:\/\/doi.org\/10.1111\/jphd.12545","DOI":"10.1111\/jphd.12545"},{"key":"e_1_3_2_4_1","doi-asserted-by":"crossref","unstructured":"Bernabe E et al. 2025. Trends in the global regional and National Burden of Oral Conditions from 1990 to 2021: a Systematic Analysis for the Global Burden of Disease Study 2021. The Lancet. 405(10482). https:\/\/doi.org\/10.1016\/s0140-6736(24)02811-3","DOI":"10.1016\/S0140-6736(24)02811-3"},{"key":"e_1_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Bratthall D H\u00e4nsel Petersson G. 2005. Cariogram: a multifactorial risk assessment model for a multifactorial disease. Community Dent Oral Epidemiol. 33(4):256\u2013264. https:\/\/doi.org\/10.1111\/j.1600-0528.2005.00233.x","DOI":"10.1111\/j.1600-0528.2005.00233.x"},{"key":"e_1_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Brons-Piche E Eckert GJ Fontana M. 2019. Predictive Validity of a Caries Risk Assessment Model at a Dental School. Journal of Dental Education. 83(2):144\u2013150. https:\/\/doi.org\/10.21815\/jde.019.017","DOI":"10.21815\/JDE.019.017"},{"key":"e_1_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph23010112"},{"key":"e_1_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Duan S et al. 2021. A predictive nomogram: a cross-sectional study on a simple-to-use model for screening 12-year-old children for severe caries in middle schools. BMC Oral Health. 21(1):457. https:\/\/doi.org\/10.1186\/s12903-021-01819-2","DOI":"10.1186\/s12903-021-01819-2"},{"key":"e_1_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Featherstone JDB Chaffee BW. 2018. The evidence for caries management by risk assessment (CAMBRA\u00ae). Adv Dent Res. 29(1):9\u201314. https:\/\/doi.org\/10.1177\/0022034517736500","DOI":"10.1177\/0022034517736500"},{"key":"e_1_3_2_10_1","doi-asserted-by":"crossref","unstructured":"Gao XL et al. 2010. Building caries risk assessment models for children. J Dent Res. 89(6):637\u2013643. https:\/\/doi.org\/10.1177\/0022034510364489","DOI":"10.1177\/0022034510364489"},{"key":"e_1_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Jagannatha AN Yu H. 2016. Bidirectional RNN for medical event detection in electronic health records. Proc Conf. 2016:473\u2013482. https:\/\/doi.org\/10.18653\/v1\/n16-1056","DOI":"10.18653\/v1\/N16-1056"},{"key":"e_1_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Kang IA Ngnamsie Njimbouom S Lee KO Kim JD. 2022. DCP: prediction of dental caries using machine learning in personalized medicine. Appl Sci. 12(6):3043. https:\/\/doi.org\/10.3390\/app12063043","DOI":"10.3390\/app12063043"},{"key":"e_1_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Kumar SV et al. 2018. Assessing the validity of existing dental sealant quality measures. J Am Dent Assoc. 149(9):756\u2013764.e1. https:\/\/doi.org\/10.1016\/j.adaj.2018.05.001","DOI":"10.1016\/j.adaj.2018.05.001"},{"key":"e_1_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Lucchi P et al. 2024. Introducing the Index of Caries Risk (ICR): a comparative study on a novel tool for caries risk assessment in pediatric patients. Children. 11(10):1166. https:\/\/doi.org\/10.3390\/children11101166","DOI":"10.3390\/children11101166"},{"key":"e_1_3_2_15_1","doi-asserted-by":"crossref","unstructured":"Luo Y et al. 2021. Nomogram prediction of caries risk among schoolchildren age 7 years based on a cohort study in Shanghai. J Int Med Res. 49(11):3000605211060175. https:\/\/doi.org\/10.1177\/03000605211060175","DOI":"10.1177\/03000605211060175"},{"key":"e_1_3_2_16_1","doi-asserted-by":"crossref","unstructured":"Neumann A et al. 2019. Number of pregnant women at four dental clinics and the care they received: a dental quality eMeasure evaluation. J Dent Educ. 83(10):1158\u20131165. https:\/\/doi.org\/10.21815\/jde.019.123","DOI":"10.21815\/JDE.019.123"},{"key":"e_1_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Ng TCH et al. 2024. Updates on caries risk assessment\u2014a literature review. Dent J (Basel). 12(10):312. https:\/\/doi.org\/10.3390\/dj12100312","DOI":"10.3390\/dj12100312"},{"key":"e_1_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Nigo M et al. 2024. Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records. Nat Commun. 15(1):2036. https:\/\/doi.org\/10.1038\/s41467-024-46211-0","DOI":"10.1038\/s41467-024-46211-0"},{"key":"e_1_3_2_19_1","doi-asserted-by":"crossref","unstructured":"Park YH Kim SH Choi YY. 2021. Prediction models of early childhood caries based on machine learning algorithms. Int J Environ Res Public Health. 18(16):8613. https:\/\/doi.org\/10.3390\/ijerph18168613","DOI":"10.3390\/ijerph18168613"},{"key":"e_1_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Paul P Kalghatgi S Dalvi T Magdum SS. 2025. Advancing dental risk profiling: a literature review of the Cariogram model. Cureus. 17(3):e80069. https:\/\/doi.org\/10.7759\/cureus.80069","DOI":"10.7759\/cureus.80069"},{"key":"e_1_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Ramos-Gomez F et al. 2021. Using a machine learning algorithm to predict the likelihood of presence of dental caries among children aged 2 to 7. Dent J (Basel). 9(12):141. https:\/\/doi.org\/10.3390\/dj9120141","DOI":"10.3390\/dj9120141"},{"key":"e_1_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Rasmy L et al. 2021a. Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. NPJ Digit Med. 4(1):86. https:\/\/doi.org\/10.1038\/s41746-021-00455-y","DOI":"10.1038\/s41746-021-00455-y"},{"key":"e_1_3_2_23_1","unstructured":"Rasmy L et al. 2021b. Simple recurrent neural networks is all we need for clinical events predictions using EHR data [preprint]. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2110.00998"},{"key":"e_1_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Rasmy L et al. 2022. Recurrent neural network models (CovRNN) for predicting outcomes of patients with COVID-19 on admission to hospital: model development and validation using electronic health record data. Lancet Digit Health. 4(6):e415\u2013e425. https:\/\/doi.org\/10.1016\/s2589-7500(22)00049-8","DOI":"10.1016\/S2589-7500(22)00049-8"},{"key":"e_1_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Sadegh-Zadeh SA et al. 2022. Dental caries risk assessment in children 5 years old and under via machine learning. Dent J (Basel). 10(9):164. https:\/\/doi.org\/10.3390\/dj10090164","DOI":"10.3390\/dj10090164"},{"key":"e_1_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Su N Lagerweij MD van der Heijden GJMG. 2021. Assessment of predictive performance of caries risk assessment models based on a systematic review and meta-analysis. J Dent. 110:103664. https:\/\/doi.org\/10.1016\/j.jdent.2021.103664","DOI":"10.1016\/j.jdent.2021.103664"},{"key":"e_1_3_2_27_1","unstructured":"Sundararajan M Taly A Yan Q. 2017. Axiomatic Attribution for Deep Networks. arXiv:170301365 [cs]. https:\/\/arxiv.org\/abs\/1703.01365"},{"key":"e_1_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Toledo Reyes L et al. 2023. Early Childhood Predictors for Dental Caries: A Machine Learning Approach. Journal of Dental Research. 102(9):999\u20131006. https:\/\/doi.org\/10.1177\/00220345231170535","DOI":"10.1177\/00220345231170535"},{"key":"e_1_3_2_29_1","doi-asserted-by":"crossref","unstructured":"Tokede B et al 2026. Visit-level quality measurement reveals missed opportunities and overuse in preventive oral health care. J Am Dent Assoc. 157(2):175\u2013183. https:\/\/doi.org\/10.1016\/j.adaj.2025.09.019","DOI":"10.1016\/j.adaj.2025.09.019"},{"key":"e_1_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Vickers AJ van Calster B Steyerberg EW. 2019. A simple step-by-step guide to interpreting decision curve analysis. Diagn Progn Res. 3:18. https:\/\/doi.org\/10.1186\/s41512-019-0064-7","DOI":"10.1186\/s41512-019-0064-7"},{"key":"e_1_3_2_31_1","doi-asserted-by":"crossref","unstructured":"Wang X et al. 2025. Risk prediction models for dental caries in children and adolescents: a systematic review and meta-analysis. BMJ Open. 15(3):e088253. https:\/\/doi.org\/10.1136\/bmjopen-2024-088253","DOI":"10.1136\/bmjopen-2024-088253"},{"key":"e_1_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Wen PYF Chen MX Zhong YJ Dong QQ Wong HM. 2021. Global burden and inequality of dental caries 1990 to 2019. J Dent Res. 101(4):392\u2013399. https:\/\/doi.org\/10.1177\/00220345211056247","DOI":"10.1177\/00220345211056247"},{"key":"e_1_3_2_33_1","doi-asserted-by":"crossref","unstructured":"White JM et al. 2019. Developing and testing electronic health record-derived caries indices. Caries Res. 53(6):650\u2013658. https:\/\/doi.org\/10.1159\/000499700","DOI":"10.1159\/000499700"},{"key":"e_1_3_2_34_1","doi-asserted-by":"crossref","unstructured":"White JM et al. 2020. Tracking oral health in a standardized evidence-based prevention-focused dental care system. J Public Health Dent. 80(Suppl 2):S35\u2013S43. https:\/\/doi.org\/10.1111\/jphd.12413","DOI":"10.1111\/jphd.12413"},{"key":"e_1_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Wickramasinghe D Usgodaarachchi U. 2022. Identifying high-risk children for dental caries in school settings: a simple predictive model. Ceylon Med J. 67(4):157\u2013163. https:\/\/doi.org\/10.4038\/cmj.v67i4.9744","DOI":"10.4038\/cmj.v67i4.9744"},{"key":"e_1_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Wu S et al. 2018. Modeling asynchronous event sequences with RNNs. J Biomed Inform. 83:167\u2013177. https:\/\/doi.org\/10.1016\/j.jbi.2018.05.016","DOI":"10.1016\/j.jbi.2018.05.016"},{"key":"e_1_3_2_37_1","unstructured":"Yan X et al. 2023. Prediction model of dental caries in 12-year-old children in Sichuan Province based on machine learning. Hua Xi Kou Qiang Yi Xue Za Zhi. 41(6):686\u2013693. https:\/\/doi.org\/10.7518\/hxkq.2023.2023124"}],"container-title":["Journal of Dental Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00220345261462463","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/00220345261462463","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00220345261462463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T11:18:24Z","timestamp":1784632704000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/00220345261462463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,18]]},"references-count":36,"alternative-id":["10.1177\/00220345261462463"],"URL":"https:\/\/doi.org\/10.1177\/00220345261462463","relation":{},"ISSN":["0022-0345","1544-0591"],"issn-type":[{"value":"0022-0345","type":"print"},{"value":"1544-0591","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,18]]},"article-number":"00220345261462463"}}