Artificial Intelligence and Child Abuse and Neglect: A Systematic Review

Overview

Journal Children (Basel)

Specialty Health Services

Date 2023 Oct 28

PMID 37892322

Authors

Francesco Lupariello

Luca Sussetto

Sara Di Trani

Giancarlo Di Vella

Affiliations

Soon will be listed here.

Abstract

All societies should carefully address the child abuse and neglect phenomenon due to its acute and chronic sequelae. Even if artificial intelligence (AI) implementation in this field could be helpful, the state of the art of this implementation is not known. No studies have comprehensively reviewed the types of AI models that have been developed/validated. Furthermore, no indications about the risk of bias in these studies are available. For these reasons, the authors conducted a systematic review of the PubMed database to answer the following questions: "what is the state of the art about the development and/or validation of AI predictive models useful to contrast child abuse and neglect phenomenon?"; "which is the risk of bias of the included articles?". The inclusion criteria were: articles written in English and dated from January 1985 to 31 March 2023; publications that used a medical and/or protective service dataset to develop and/or validate AI prediction models. The reviewers screened 413 articles. Among them, seven papers were included. Their analysis showed that: the types of input data were heterogeneous; artificial neural networks, convolutional neural networks, and natural language processing were used; the datasets had a median size of 2600 cases; the risk of bias was high for all studies. The results of the review pointed out that the implementation of AI in the child abuse and neglect field lagged compared to other medical fields. Furthermore, the evaluation of the risk of bias suggested that future studies should provide an appropriate choice of sample size, validation, and management of overfitting, optimism, and missing data.

Citing Articles

Genetics, Epigenetics, and the Environment: Are Precision Medicine, Provider Compassion, and Social Justice Effective Public Health Measures to Mitigate Disease Risk and Severity?.

Iannaccone P, Ryznar R, Van Winkle L Int J Environ Res Public Health. 2024; 21(11).

PMID: 39595789 PMC: 11593770. DOI: 10.3390/ijerph21111522.

Fostering Tomorrow: Uniting Artificial Intelligence and Social Pediatrics for Comprehensive Child Well-being.

Gulsen M, Yalcin S Turk Arch Pediatr. 2024; 59(4):345-352.

PMID: 39110287 PMC: 11332429. DOI: 10.5152/TurkArchPediatr.2024.24076.

References

Adams J, Farst K, Kellogg N . Interpretation of Medical Findings in Suspected Child Sexual Abuse: An Update for 2018. J Pediatr Adolesc Gynecol. 2018; 31(3):225-231. DOI: 10.1016/j.jpag.2017.12.011. View

White I, Royston P, Wood A . Multiple imputation using chained equations: Issues and guidance for practice. Stat Med. 2011; 30(4):377-99. DOI: 10.1002/sim.4067. View

Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau N, Venugopal V . Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet. 2018; 392(10162):2388-2396. DOI: 10.1016/S0140-6736(18)31645-3. View

Esteva A, Kuprel B, Novoa R, Ko J, Swetter S, Blau H . Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542(7639):115-118. PMC: 8382232. DOI: 10.1038/nature21056. View

Brown S . Ethical challenges in child abuse: what is the harm of a misdiagnosis?. Pediatr Radiol. 2021; 51(6):1070-1075. DOI: 10.1007/s00247-020-04845-4. View

Hou J, Imler T, Imperiale T . Current and future applications of natural language processing in the field of digestive diseases. Clin Gastroenterol Hepatol. 2014; 12(8):1257-61. DOI: 10.1016/j.cgh.2014.05.013. View

Courvoisier D, Combescure C, Agoritsas T, Gayet-Ageron A, Perneger T . Performance of logistic regression modeling: beyond the number of events per variable, the role of data structure. J Clin Epidemiol. 2011; 64(9):993-1000. DOI: 10.1016/j.jclinepi.2010.11.012. View

Marshall D, English D . Neural network modeling of risk assessment in child protective services. Psychol Methods. 2000; 5(1):102-24. DOI: 10.1037/1082-989x.5.1.102. View

Landau A, Ferrarello S, Blanchard A, Cato K, Atkins N, Salazar S . Developing machine learning-based models to help identify child abuse and neglect: key ethical challenges and recommended solutions. J Am Med Inform Assoc. 2022; 29(3):576-580. PMC: 8800514. DOI: 10.1093/jamia/ocab286. View

10.

Kissos L, Goldner L, Butman M, Eliyahu N, Lev-Wiesel R . Can artificial intelligence achieve human-level performance? A pilot study of childhood sexual abuse detection in self-figure drawings. Child Abuse Negl. 2020; 109:104755. DOI: 10.1016/j.chiabu.2020.104755. View

11.

Morris M, Song E, Rajesh A, Asaad M, Phillips B . Ethical, Legal, and Financial Considerations of Artificial Intelligence in Surgery. Am Surg. 2022; 89(1):55-60. DOI: 10.1177/00031348221117042. View

12.

Nemeroff C . Paradise Lost: The Neurobiological and Clinical Consequences of Child Abuse and Neglect. Neuron. 2016; 89(5):892-909. DOI: 10.1016/j.neuron.2016.01.019. View

13.

Pears K, Capaldi D . Intergenerational transmission of abuse: a two-generational prospective study of an at-risk sample. Child Abuse Negl. 2002; 25(11):1439-61. DOI: 10.1016/s0145-2134(01)00286-1. View

14.

Annapragada A, Donaruma-Kwoh M, Annapragada A, Starosolski Z . A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records. PLoS One. 2021; 16(2):e0247404. PMC: 7909689. DOI: 10.1371/journal.pone.0247404. View

15.

Schafer J . Multiple imputation: a primer. Stat Methods Med Res. 1999; 8(1):3-15. DOI: 10.1177/096228029900800102. View

16.

Makoroff K, Brauley J, Brandner A, Myers P, Shapiro R . Genital examinations for alleged sexual abuse of prepubertal girls: findings by pediatric emergency medicine physicians compared with child abuse trained physicians. Child Abuse Negl. 2002; 26(12):1235-42. DOI: 10.1016/s0145-2134(02)00419-2. View

17.

Mraovich L, Wilson J . Patterns of child abuse and neglect associated with chronological age of children living in a midwestern county. Child Abuse Negl. 1999; 23(9):899-903. DOI: 10.1016/s0145-2134(99)00055-1. View

18.

Tiyyagura G, Asnes A, Leventhal J, Shapiro E, Auerbach M, Teng W . Development and Validation of a Natural Language Processing Tool to Identify Injuries in Infants Associated With Abuse. Acad Pediatr. 2021; 22(6):981-988. PMC: 9095755. DOI: 10.1016/j.acap.2021.11.004. View

19.

Shahi N, Shahi A, Phillips R, Shirek G, Lindberg D, Moulton S . Using deep learning and natural language processing models to detect child physical abuse. J Pediatr Surg. 2021; 56(12):2326-2332. DOI: 10.1016/j.jpedsurg.2021.03.007. View

20.

Gulshan V, Peng L, Coram M, Stumpe M, Wu D, Narayanaswamy A . Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016; 316(22):2402-2410. DOI: 10.1001/jama.2016.17216. View