A prediction model for the long-term survival of primary molars after Vitapex pulpectomy

Background: Although pulpectomy is recognized as the standard treatment for severe pulp pathologies, objective and quantifiable measures to predict primary molar survival after pulpectomy are limited. The aim of this study was to develop a predictive model for the long-term survival of primary molars after Vitapex pulpectomy using machine learning. Methods: This retrospective cohort study analyzed data from 212 pulpectomized primary molars. The DeepHit prediction model was developed based on significant prognostic factors identified through univariate Cox regression analysis. Calibration of the prediction model was evaluated, and further external validation was performed on 101 pulpectomized primary molars from multicenter cohorts. Results: Age at initial treatment, Frankl behavior score, arch type, presence of mucosal fistula, periapical lesion, and single-visit pulp treatment were significantly associated with survival rates. The weighted mean Brier score was 0.20, and an overall concordance index (C-index) was 0.73, indicating strong predictive accuracy. Conclusions: The DeepHit prediction model for primary molar pulpectomy in children under 9 years of age was successfully developed and showed clinical potential for predicting pulpectomy outcomes.

Primary molars; Vitapex pulpectomy; Survival analysis; Machine learning; Prediction model

[1] Kratunova E, Silva D. Pulp therapy for primary and immature permanent teeth: an overview. General Dentistry. 2018; 66: 30–38.

[2] Society of Pediatric Dentistry, Chinese Stomatological Association. Clinical guidelines for pulp therapies of primary teeth. Chinese Journal of Stomatology. 2021; 56: 840–848. (In Chinese)

[3] Coll JA, Vargas K, Marghalani AA, Chen CY, AlShamali S, Dhar V, et al. A systematic review and meta-analysis of nonvital pulp therapy for primary teeth. Pediatric Dentistry. 2020; 42: 256–461.

[4] Dou G, Wang D, Zhang S, Ma W, Xu M, Xia B. A retrospective study on the long-term outcomes of pulpectomy and influencing factors in primary teeth. Journal of Dental Sciences. 2022; 17: 771–779.

[5] Chen X, Liu X, Zhong J. Clinical and radiographic evaluation of pulpectomy in primary teeth: a 18-months clinical randomized controlled trial. Head & Face Medicine. 2017; 13: 12.

[6] Xie Y, Wang Y, Ma Q, Li J, Chen Y, Yang R, et al. Survival analysis of pulpectomy in primary molars performed under dental general anaesthesia: a two-year retrospective study. BMC Oral Health. 2022; 22: 597.

[7] He SY, Li JY, Dai SS, Yang YH, Wen YF, Guo QY, et al. Survival analysis and risk factors of pulpectomy among children with severe early childhood caries treated under general anesthesia: a retrospective study. International Journal of Environmental Research and Public Health. 2023; 20: 1191.

[8] Chen Y, Li H, Li M, Yang L, Sun Q, Chen K. Analysis of survival and factors associated with failure of primary tooth pulpectomies performed under general anaesthesia in children from South China. International Journal of Paediatric Dentistry. 2020; 30: 225–233.

[9] Nakornchai S, Banditsing P, Visetratana N. Clinical evaluation of 3Mix and Vitapex as treatment options for pulpally involved primary molars. International Journal of Paediatric Dentistry. 2010; 20: 214–221.

[10] Chen Z, Li M, Chen Y, Xie Y, Chen X, Qiu H, et al. Survival analysis of primary molars following pulpectomy performed under dental general anesthesia: a five-year retrospective study. BMC Oral Health. 2024; 24: 1202.

[11] Gomes AP, Costa B, Marques R, Nunes V, Coelho C. Kaplan-Meier survival analysis: practical insights for clinicians. Acta Medica Portuguesa. 2024; 37: 280–285.

[12] Lee C, Yoon J, Schaar MV. Dynamic-DeepHit: a deep learning approach for dynamic survival analysis with competing risks based on longitudinal data. IEEE Transactions on Biomedical Engineering. 2020; 67: 122–133.

[13] Ryu JY, Lee MY, Lee JH, Lee BH, Oh KS. DeepHIT: a deep learning framework for prediction of hERG-induced cardiotoxicity. Bioinformatics. 2020; 36: 3049–3055.

[14] Lee C, Zame W, Yoon J, van der Schaar M. DeepHit: a deep learning approach to survival analysis with competing risks. Proceedings of the AAAI Conference on Artificial Intelligence. 2018; 32: 2314–2321.

[15] Yuan S, Liu Q, Huang X, Tan S, Bai Z, Yu J, et al. Development of an individualized dementia risk prediction model using deep learning survival analysis incorporating genetic and environmental factors. Alzheimer’s Research & Therapy. 2024; 16: 278.

[16] Feng J, Zhang H, Li F. Investigating the relevance of major signaling pathways in cancer survival using a biologically meaningful deep learning model. BMC Bioinformatics. 2021; 22: 47.

[17] Casas MJ, Kenny DJ, Johnston DH, Judd PL. Long-term outcomes of primary molar ferric sulfate pulpotomy and root canal therapy. Pediatric Dentistry. 2004; 26: 44–48.

[18] Ozalp N, Saroğlu I, Sönmez H. Evaluation of various root canal filling materials in primary molar pulpectomies: an in vivo study. American Journal of Dentistry. 2005; 18: 347–350.

[19] Van Buuren S, Groothuis-Oudshoorn K. MICE: multivariate imputation by chained equations in R. Journal of Statistical Software. 2011; 45: 1–67.

[20] Bao L, Wang YT, Zhuang JL, Liu AJ, Dong YJ, Chu B, et al. Machine learning-based overall survival prediction of elderly patients with multiple myeloma from multicentre real-life data. Frontiers in Oncology. 2022; 12: 922039.

[21] Nurko C, Garcia-Godoy F. Evaluation of a calcium hydroxide/iodoform paste (Vitapex) in root canal therapy for primary teeth. Journal of Clinical Pediatric Dentistry. 1999; 23: 289–294.

[22] Diéguez-Pérez M, Ticona-Flores JM. Three-dimensional analysis of the pulp chamber and coronal tooth of primary molars: an in vitro study. International Journal of Environmental Research and Public Health. 2022; 19: 9279.

[23] Ahmed HMA, Musale PK, El Shahawy OI, Dummer PMH. Application of a new system for classifying tooth, root and canal morphology in the primary dentition. International Endodontic Journal. 2020; 53: 27–35.

[24] Peretz B, Nisan S, Herteanu L, Blumer S. Root resorption patterns of primary mandibular molars and location of the premolar successors: a radiographic evaluation. Pediatric Dentistry. 2013; 35: 426–429.

[25] Arai Y, English JD, Ono N, Ono W. Effects of antiresorptive medications on tooth root formation and tooth eruption in paediatric patients. Orthodontics & Craniofacial Research. 2023; 26: 29–38.

[26] Songvejkasem M, Auychai P, Chankanka O, Songsiripradubboon S. Survival rate and associated factors affecting pulpectomy treatment outcome in primary teeth. Clinical and Experimental Dental Research. 2021; 7: 978–986.

[27] American Academy of Pediatric Dentistry. Prescribing dental radiographs for infants, children, adolescents, and individuals with special health care needs. Pediatric Dentistry. 2018; 40: 213–215.