Abstract
The purpose of this study was to explore and identify patterns of risk predictors of maltreatment recurrence using predictive risk modeling (PRM). This study used the administrative dataset from the National Child Maltreatment Information System recorded by Korean CPS (Child Protective Service) workers. The information, including recurrent maltreatment, was collected in 2012; then, those reported cases were followed for 2 years through 2014. The data included information about child, family, caregiver, maltreatment, and service characteristics and consisted of male (50.22%) and female (49.78%) children with an average age of 9 years (n = 4319). We examined the association of risk factors with recurrence using conditional inference trees (CTREE): a tree-based data mining algorithm for classification that allows the exploration of the interconnection between hypothesized risk factors. Study findings showed that a history of prior CPS involvement was the first decision point in the decision tree structure of recurrence. The effect of other risk factors depended on the presence of prior CPS involvement. In the absence of prior CPS involvement, cases with (a) a single-parent status and (b) a caregiver’s alcohol abuse living in other types of households (two-parent households, kinship care, and children without parents) were associated with recurrence. In the presence of prior CPS involvement, cases with out-of-home care or others (long- or short-term foster care and emergency placement) in the final decision of child placement (a) where in-home care in the initial decision of child placement within the presence of physical abuse and (b) where social isolation without physical abuse was related to recurrence. Cases with (a) a male caregiver and (b) a female caregiver with social isolation and without social isolation yet employed were at high risk for recurrence under the circumstance of in-home care in the final decision of child placement. This exploratory study found multiple connections among the factors in the prediction of recurrence. The CTREE helps unravel the complexity embedded in maltreatment recurrence by capturing its patterns. This information can deepen our knowledge of associations between risk factors in the prediction of recurrence and be used as a reference to inform child maltreatment policy and prevention.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
The confusion matrix can be expressed in the table below. True positive (TP) indicates a test result that the predicted and actual values are positive. False-negative (FN): the predicted value is negative, while the actual value is positive. False-positive (FP): the predicted value is positive, while the actual value is negative. Finally, true negative (TN) indicates that predicted and actual values are negative (Awad & Khanna, 2015).
Predicted
Actual
True positive (TP)
False negative (FN)
False positive (FP)
True negative (TN)
Classification accuracy, the proportion of the total number of correctly predicted cases, is calculated by the formula: TP + TN / TP + FN + FP + TN.
References
Awad, M., & Khanna, R. (2015). Efficient learning machines: Theories, concepts, and applications for engineers and system designers. Springer Nature. https://doi.org/10.1007/978-1-4302-5990-9
Bae, H. O. & Kang, J. (2020). Characteristics and correlates of child maltreatment recurrence: Comparison of single recurrence and multiple time recurrence. Journal of the Korean Society of Welfare, 69(3), 145–171. https://doi.org/10.24300/jkscw.2020.145
Bae, H. O., Solomon, P. L., & Gelles, R. J. (2007). Abuse type and substantiation status varying by recurrence. Children and Youth Services Review, 29, 856–869. https://doi.org/10.1016/j.childyouth.2007.01.002
Bae, H. O., Solomon, P. L., & Gelles, R. J. (2009). Multiple child maltreatment recurrence relative to single recurrence and no recurrence. Children and Youth Services Review, 31, 617–624. https://doi.org/10.1016/j.childyouth.2008.11.005
Belsky, J. (1993). Etiology of child maltreatment: A developmental-ecological analysis. Psychological Bulletin, 114, 413–434. https://doi.org/10.1037/0033-2909.114.3.413
Casanueva, C., Tueller, S., Dolan, M., Testa, M., Smith, K., & Day, O. (2015). Examining predictors of re-reports and recurrence of child maltreatment using two national data sources. Children and Youth Services Review, 48, 1–13. https://doi.org/10.1016/j.childyouth.2014.10.006
Centers for Disease Control & Prevention. (2014). Essentials for childhood: Steps to create safe, stable, nurturing relationships and environments for all children. https://www.cdc.gov/violenceprevention/pdf/essentials-for-childhood-framework508.pdf
Connell, C. M., Vanderploeg, J. J., Katz, K. H., Caron, C., Saunders, L., & Tebes, J. K. (2009). Maltreatment following reunification: Predictors of subsequent child protective services contact after children return home. Child Abuse & Neglect, 33(4), 218–228. https://doi.org/10.1016/j.chiabu.2008.07.005
Crookston, N. L., & Finley, A. O. (2008). yaImpute: An R package for kNN imputation. Journal of Statistical Software, 23(10), 1–16. https://doi.org/10.18637/jss.v023.i10
Cuccaro-Alamin, S., Foust, R., Vaithianathan, R., & Putnam-Hornstein, E. (2017). Risk assessment and decision making in child protective services: Predictive risk modeling in context. Children and Youth Services Review, 79, 291–298. https://doi.org/10.1016/j.childyouth.2017.06.027
DePanfilis, D., & Zuravin, S. J. (1999). Predicting child maltreatment recurrences duringtreatment. Child Abuse & Neglect, 23, 729–743. https://doi.org/10.1016/S0145-2134(99)00046-0
Drake, B., & Jonson-Reid, M. (2000). Substantiation and early decision points in publicchild welfare: A conceptual consideration. Child Maltreatment, 5, 227–235. https://doi.org/10.1177/1077559500005003003
Drake, B., Jonson-Reid, M., Ocampo, M. G., Morrison, M., & Dvalishvili, D. (2020). A practical framework for considering the use of predictive risk modeling in child welfare. The ANNALS of the American Academy of Political and Social Science, 692, 162–181. https://doi.org/10.1177/0002716220978200
Eastman, A. L., Mitchell, M. N., & Putnam-Hornstein, E. (2016). Risk of re-report: A latent class analysis of infants reported for maltreatment. Child Abuse & Neglect, 55, 22–31. https://doi.org/10.1016/j.chiabu.2016.03.002
Farrington, D. P. (1998). Predictors, causes, and correlates of male youth violence. Crime and Justice, 24, 421–475. https://doi.org/10.1086/449284
Fluke, J. D., Shusterman, G. R., Hollinshead, D. M., & Yuan, Y. Y. T. (2008). Longitudinal analysis of repeated child abuse reporting and victimization: Multistate analysis of associated factors. Child Maltreatment, 13, 76–88. https://doi.org/10.1177/1077559507311517
Fluke, J. D., Yuan, Y., & Edwards, M. (1999). Recurrence of maltreatment: An application of the national child abuse and neglect data system (NCANDS). Child Abuse & Neglect, 23, 633–650. https://doi.org/10.1016/S0145-2134(99)00039-3
Font, S. A., & Berger, L. M. (2015). Child maltreatment and children’s developmental trajectories in early to middle childhood. Child Development, 86, 536–556. https://doi.org/10.1111/cdev.12322
Fuller, T. L. (2005). Child safety at reunification: A case-control study of maltreatment recurrence following return home from substitute care. Children and Youth Services Review, 27, 1293–1306. https://doi.org/10.1016/j.childyouth.2005.01.004
Fuller, T. L., Wells, S. J., & Cotton, E. E. (2001). Predictors of maltreatment recurrence attwo milestones in the life of a case. Children and Youth Services Review, 23, 49–78. https://doi.org/10.1016/S0190-7409(00)00127-4
Gillingham, P. (2017). Predictive risk modelling to prevent child maltreatment: Insights and implications from Aotearoa/New Zealand. Journal of Public Child Welfare, 11, 150–165. https://doi.org/10.1080/15548732.2016.1255697
Hélie, S., Poirier, M. A., & Turcotte, D. (2014). Risk of maltreatment recurrence after exiting substitute care: Impact of placement characteristics. Children and Youth Services Review, 46, 257–264. https://doi.org/10.1016/j.childyouth.2014.09.002
Hosmer, D. W., & Lemeshow, S. (1989). Applied logistic regression. John Wiley & Sons Inc.
Hothorn, T., Hornik, K., & Zeileis, A. (2006). Unbiased recursive partitioning: A conditional inference framework. Journal of Computational and Graphical Statistics, 15, 651–674. https://doi.org/10.1198/106186006X133933
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2017). An introduction to statistical learning (2nd ed). New York: Springer.
Jang, H. S., Kim, K. H., & Kim, K. H. (2016). The characteristics of recurrence on intervention cases of child protective services: Application of survival analysis. Korean Academy of Family Social Work. 54, 225–262. https://doi.org/10.16975/kjfsw.2016..54.007
Jedwab, M., Harrington, D., & Dubowitz, H. (2017). Predictors of substantiated re-reports in a sample of children with initial unsubstantiated reports. Child Abuse & Neglect, 69, 232–241. https://doi.org/10.1016/j.chiabu.2017.04.031
Jonson-Reid, M., Drake, B., Chung, S., & Way, I. (2003). Cross-type recidivism among child maltreatment victims and perpetrators. Child Abuse & Neglect, 27, 899–917. https://doi.org/10.1016/S0145-2134(03)00138-8
Kang, J. Y., & Jang, H. J. (2018). Identification of subgroups of child maltreatment victims and their problematic behaviors: Utilizing maltreatment dimensions. Journal of the Korean society of child welfare (62), 61–91. http://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE07486958
Kang, J. Y., Jang, H. J., Kim, K. H., & Kim, M. K. (2017). A study on the predictors of child maltreatment among young children at home: With an understanding of maltreatment among school-age children. Journal of Korean Council for Children & Rights, 21(2), 177–202. https://doi.org/10.21459/kccr.2017.21.2.177
Kim, K. H. (2006). The effect of family background on physical child abuse. Korea Journal of Child Care and Education, 45, 53–74.
Kim, H., Drake, B., & Jonson-Reid, M. (2020a). Longitudinal understanding of child maltreatment report risks. Child Abuse & Neglect, 104, 104467. https://doi.org/10.1016/j.chiabu.2020.104467
Kim, K. H., Bee, R., & Kim, K. (2020b). Classification of families involved in Korean child protection services and their characteristics by developmental stage. Korean Journal Social Welfare, 72(3), 181–211. http://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE09910342
Kim, K., Yeum, D. M., Jang, H., & Jang, H. S. (2016). Testing validity of child safety and risk assessments for child maltreatment investigation in Korea. Korean Association Of Victimology, 24(3), 151–176.
Kim, S., Lee, B. J., Kim, H. S., Yoo, J. P., & Lee, S. G. (2020c). The effect of child protection services on child maltreatment recurrence. Journal of Korean Council for Children & Rights, 24(3), 463–488. https://doi.org/10.21459/kccr.2020c.24.3.463
Kisely, S., Strathearn, L., & Najman, J. M. (2020). Child maltreatment and mental health problems in 30-year-old adults: A birth cohort study. Journal of Psychiatric Research, 129, 111–117. https://doi.org/10.1016/j.jpsychires.2020.06.009
Korea Ministry of Government Legislation. (2022). Definition of child maltreatment. Retrieved May 2, 2022, from https://www.easylaw.go.kr
Kuhn, M. (2008). Building predictive models in R using the caret package. Journal of Statistical Software, 28(5), 1 - 26. https://doi.org/10.18637/jss.v028.i05
Marshall, D. B., & English, D. J. (2000). Neural network modeling of risk assessment in child protective services. Psychological Methods, 5, 102–124. https://doi.org/10.1037/1082-989X.5.1.102
Ministry of Health & Welfare. (2016). Current status report of child abuse. Ministry of Health and Welfare, and National Child Protection Agency. http://mohw.go.kr
National Center for the Rights of the Child (NCRC). (2020). The number of child maltreatment recurrence cases. Retrieved May 2, 2022, from https://kosis.kr/index/index.do
Putnam-Hornstein, E., Simon, J. D., Eastman, A. L., & Magruder, J. (2015). Risk of re-reporting among infants who remain at home following alleged maltreatment. Child Maltreatment, 20, 92–103. https://doi.org/10.1177/1077559514558586
Pyun, H. S., & Choi, J. K. (2016). The associations among poor single mothers’ economic hardship, depressive symptoms, parenting stress, child abuse and neglect, and their children’s development. Journal of the Korean Society of Child Welfare, 53, 1–23. http://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE07113863
R Core Team (2021). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/
Sledjeski, E. M., Dierker, L. C., Brigham, R., & Breslin, E. (2008). The use of risk assessment to predict recurrent maltreatment: A classification and regression tree analysis (CART). Prevention Science, 9, 28–37. https://doi.org/10.1007/s11121-007-0079-0
Thompson, K. M., Wonderlich, S. A., Crosby, R. D., Ammerman, F. F., Mitchell, J. E., & Brownfield, D. (2001). An assessment of the recidivism rates of substantiated and unsubstantiated maltreatment cases. Child Abuse & Neglect, 25, 1207–1218. https://doi.org/10.1016/S0145-2134(01)00271-X
Torgo, L., & Torgo, M. L. (2013). Package ‘dmwr’. Comprehensive R archive network. http://www2.uaem.mx/r-mirror/web/packages/DMwR/DMwR.pdf
Tucker, M. C., & Rodriguez, C. M. (2014). Family dysfunction and social isolation as moderators between stress and child physical abuse risk. Journal of Family Violence, 29, 175–186. https://doi.org/10.1007/s10896-013-9567-0
Vaithianathan, R., Maloney, T., Putnam-Hornstein, E., & Jiang, N. (2013). Children in the public benefit system at risk of maltreatment: Identification via predictive modeling. American Journal of Preventive Medicine, 45, 354–359. https://doi.org/10.1016/j.amepre.2013.04.022
World Health Organization & International Society for Prevention of Child Abuse & Neglect. (2006). Preventing child maltreatment: A guide to taking action and generating evidence. https://apps.who.int/iris/handle/10665/43499
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics Approval
This study was reviewed by the Research Committee in K-CPS as well as Internal Review Board of the University to which the authors belong and was performed in accordance with the ethical standards as laid down in the 1964 Declaration of Helsinki and its later amendments.
Consent to Participate
Informed consent was obtained from all participants when CPS workers recorded their information in the administrative data.
Conflict of Interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Choi, J., Kim, K. Predictive Risk Modeling for Recurrence of Child Maltreatment Using Cases from the National Child Maltreatment Data System in Korea: Exploratory Data Analysis Using Data Mining Algorithm. Prev Sci 23, 1517–1530 (2022). https://doi.org/10.1007/s11121-022-01446-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11121-022-01446-5