Predicting late dropout from nursing education or early dropout from the profession. Jos H.A.M. Kox a,b, ⁎ , Joost S. van der Zwan a , Johanna H. Groenewoud a , Jos Runhaar b , Sita M.A. Bierma-Zeinstra b,c , Ellen J.M. Bakker a,d , Harald S. Miedema a , Allard J. van der Beek d , Cécile R.L. Boot d , Pepijn D.D.M. Roelofs a,b,e a Rotterdam University of Applied Sciences, Research Centre Innovations in Care, P.O. Box 25035, 3001, HA, Rotterdam, the Netherlands b Erasmus University Medical Centre, Department of General Practice, P.O. Box 2040, 3000, CA, Rotterdam, the Netherlands c Erasmus MC University Medical Center Rotterdam, Department of Orthopaedics, PO Box 2040, 3000, CA, Rotterdam, the Netherlands d Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Public and Occupational Health, Amsterdam Public Health Research Institute, P.O. Box 7057, 1007, MB, Amsterdam, the Netherlands e University Medical Center Groningen, University of Groningen, Department of Health Sciences, Community and Occupational Medicine, A. Deusinglaan 1, 9713, AV, Groningen, the Netherlands ABSTRACT ARTICLE INFO Keywords: Prediction model Dropout Nursing students Novice nurses Backward binary multiple logistic regression analyses Aim: To identify predictors of late academic or early career dropout, and derive a simple model for identifying nursing students and novice nurses with significant increased dropout risk. Background: Dropout from nursing school and the nursing profession is of great concern for students, educators, as well as graduated nurses. Nurse shortages are a major problem in healthcare worldwide (Drennan & Ross, 2019). Retention of nursing students and novice nurses can contribute to reducing the deficits (Smith-Wacholz et al., 2019). Little is known about the predictors of dropout among nursing students in the later years of their degree programme (late drop- out) and early nurse dropout from the profession. Design: Prospective cohort study with three years of follow-up, among 406 third-year nursing students of the Bachelor of Nursing programme of Rotterdam University of Applied Sciences. Methods: Data were collected between May 2016 and February 2019 using a self-administered questionnaire. Back- ward binary multiple logistic regression analyses were used to build a prediction model for dropout. Results: Dropout from nursing education and at the start of the nursing career totalled 12%. Twelve factors, including male sex (OR 3.76, 95% CI 1.41–10.04), age (OR 1.06, 95% CI 1.00–1.12), migration background (OR 2.42, 95% CI 1.10–5.32), clinical placement setting (including mental healthcare; OR 0.18, 95% CI 0.04–0.83), musculoskeletal symptoms (OR 1.20, 95% CI 1.02–1.42) and psychosocial work characteristics (including exposure to violence; OR 3.13, 95% CI 1.25–7.81) were statistically significant predictors in our dropout model. The explained variance of the final model was 26%. Conclusion: The study highlights the importance of taking musculoskeletal and mental health symptoms, psychosocial work characteristics, as well as sex, age and migration background into consideration as predictors for dropout among nursing students and novice nurses. This study is a first step towards a predictive model that helps identifying high-risk groups. Video to this article can be found online at https://doi.org/10.1016/ j.sctalk.2022.100106. Science Talks 5 (2023) 100106 ⁎ Corresponding author at: Rotterdam University of Applied Sciences, Research Centre Innovations in Care, P.O. Box 25035, 3001, HA, Rotterdam, the Netherlands. E-mail address: j.h.a.m.kox@hr.nl (J.H.A.M. Kox). http://dx.doi.org/10.1016/j.sctalk.2022.100106 Received 22 November 2022; Accepted 28 November 2022 Available online xxxx 2772-5693/© 2022 The Author. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). Contents lists available at ScienceDirect Science Talks journal homepage: www.elsevier.es/sctalk