Survivors of child sex trafficking (SCST) experience high rates of adverse health outcomes. Amidst the duration of their victimization, survivors regularly seek healthcare yet fail to be identified. This study sought to utilize artificial intelligence (AI) to identify SCST and describe the elements of their healthcare presentation. An AI-supported keyword search was conducted to identify SCST within the electronic medical records (EMR) of ∼1.5 million patients at a large midwestern pediatric hospital. Descriptive analyses were used to evaluate associated diagnoses and clinical presentation. A sex trafficking-related keyword was identified in .18% of patient charts. Among this cohort, the most common associated diagnostic codes were for Confirmed Sexual/Physical Assault; Trauma and Stress-Related Disorders; Depressive Disorders; Anxiety Disorders; and Suicidal Ideation. Our findings are consistent with the myriad of known adverse physical and psychological outcomes among SCST and illuminate the future potential of AI technology to improve screening and research efforts surrounding all aspects of this vulnerable population.
BangB.BakerP. L.CarpinteriA.Van HasseltV. B. (2013). Commercial Sexual Exploitation of Children (1st ed.). Springer Science & Business Media. https://doi.org/10.1007/978-3-319-01878-2
2.
BarnertE.IqbalZ.BruceJ.AnoshiravaniA.KolhatkarG.GreenbaumJ. (2017). Commercial sexual exploitation and sex trafficking of children and adolescents: A narrative review. Academic Pediatrics, 17(8), 825–829. https://doi.org/10.1016/j.acap.2017.07.009
3.
BarrD. (2019). Health Disparities in the United States: Social Class, Race, Ethnicity, and the Social Determinants of Health (2nd ed.). Johns Hopkins University Press.
4.
BochS.SezginE.RuchD.KelleherK.ChisolmD.LinS. (2021). Unjust: The health records of youth with personal/family justice involvement in a large pediatric health system. Health & Justice, 9(1), 20. https://doi.org/10.1186/s40352-021-00147-5
5.
CarrellD. S.HalgrimS.TranD. T.BuistD. S. M.ChubakJ.ChapmanW. W.SavovaG. (2014). Using natural language processing to improve efficiency of manual chart abstraction in research: The case of breast cancer recurrence. American Journal of Epidemiology, 179(6), 749–758. https://doi.org/10.1093/aje/kwt441
6.
CarsonN. J.MullinB.SanchezM. J.LuF.YangK.MenezesM.CookB. L. (2019). Identification of suicidal behavior among psychiatrically hospitalized adolescents using natural language processing and machine learning of electronic health records. PLoS ONE, 14(2), e0211116. https://doi.org/10.1371/journal.pone.0211116
7.
CasassaK.KnightL.MengoC. (2022). Trauma bonding perspectives from service providers and survivors of sex trafficking. A scoping review. Trauma, Violence & Abuse, 23(3), 969–984. https://doi.org/10.1177/1524838020985542
8.
DallaR. (2003). When the bough breaks: Examining intergenerational parent-child relational patterns among street-level sex workers and their parents and children. Applied Developmental Science, 7(4), 216–228. https://doi.org/10.1207/s1532480xads0704_1
9.
DallaR.XiaY.KennedyH. (2003). You just give them what they want and pray they don’t kill you” Street level sex workers’ reports of victimization, personal resources and coping strategies. Violence Against Women, 9(11), 1367–1394. https://doi.org/10.1177/1077801203255679
10.
DuffP.ShovellerJ.ChettiarJ.FengC.NicolettiR.ShannonK. (2015). Sex work and motherhood: Social and structural barriers to health and social services for pregnant and parenting street and off-street sex workers. Health Care for Women International, 36(9), 1039–1055. https://doi.org/10.1080/07399332.2014.989437
11.
EdinburghL.Pape-BlabolilJ.HarpinS. B.SaewycE. (2015). Assessing exploitation experiences of girls and boys seen at a Child Advocacy Center. Child Abuse & Neglect, 46, 47–59. https://doi.org/10.1016/j.chiabu.2015.04.016
12.
GoldbergA. P.MooreJ. L.HouckC.KaplanD. M.BarronC. E. (2017). Domestic minor sex trafficking patients: A retrospective analysis of medical presentation. Journal of Pediatric and Adolescent Gynecology, 30(1), 109–115. https://doi.org/10.1016/j.jpag.2016.08.010
13.
Gonzalez-HernandezG.SarkerA.O’ConnorK.SavovaG. (2017). Capturing the patient’s perspective: A review of advances in natural language processing of health-related text. Yearbook of Medical Informatics, 26(1), 214–227. https://doi.org/10.15265/IY-2017-029
14.
GreenbaumJ.Crawford-JakubiakJ. E.ChristianC. W.FlahertyE. G.LeventhalJ. M.LukefahrJ. L.SegeR. D.MacMillanH.NolanC. M.ValleyL. A.HurleyT. P. (2015). Child sex trafficking and commercial sexual exploitation: Health care needs of victims. Pediatrics, 135(3), 566–574. https://doi.org/10.1542/peds.2014-4138
15.
GreenbaumJ.McClureR. C.StareB.BarnesW.CastlesC.CullitonE. (2021). Documenting ICD codes and other sensitive information in electronic health records: Guidelines for healthcare professional who encounter patients with a history of human trafficking or other forms of violence. HEAL Trafficking, International Centre for Missing and Exploited Children. https://healtrafficking.org/wp-content/uploads/2021/02/Documenting-ICD-Codes-01.29.20.pdf
16.
HaleemA.JavaidM.KhanI. H. (2019). Current status and applications of Artificial Intelligence (AI) in medical field: An overview. Current Medicine Research and Practice, 9(6), 231–237. https://doi.org/10.1016/j.cmrp.2019.11.005
17.
HershbergerA. R.SandersJ.ChickC.JessupM.HanlinH.CydersM. A. (2018). Predicting running away in girls who are victims of commercial sexual exploitation. Child Abuse & Neglect, 79, 269–278. https://doi.org/10.1016/j.chiabu.2018.02.023
18.
IsraelB.EngE.SchulzA.ParkerE. (2005). Methodologies in Community-Based Participatory Research for Health. Jossey-Bass.
19.
JaecklS.LaughonK. (2020). Sex trafficking of minors in the United States: A perspective for nurses. OJIN: The Online Journal of Issues in Nursing, 25(3). https://doi.org/10.3912/ojin.vol25no03man05
20.
KehlK. L.ElmarakebyH.NishinoM.Van AllenE. M.LepistoE. M.HassettM. J.JohnsonB. E.SchragD. (2019). Assessment of deep Natural Language Processing in ascertaining oncologic outcomes from radiology reports. JAMA Oncology, 5(10), 1421–1429, https://doi.org/10.1001/jamaoncol.2019.1800
21.
KennyM. C.HelpingstineC.LongH.PerezL.HarringtonM. C. (2019). Increasing child serving professionals’ awareness and understanding of the commercial sexual exploitation of children. Journal of Child Sexual Abuse, 28(4), 417–434. https://doi.org/10.1080/10538712.2018.1563264
22.
KoleckT. A.TatonettiN. P.BakkenS.MithaS.HendersonM. M.GeorgeM.MiaskowskiC.SmaldoneA.TopazM. (2021). Identifying symptom information in clinical notes using natural language processing. Nursing Research, 70(3), 173–183.
23.
LeeJ.YangS.Holland-HallC.SezginE.GillM.LinwoodS.HuangY.HoffmanJ. (2022). Prevalence of sensitive terms in clinical notes using natural language processing techniques: Observational study. Journal of Medical Internet Research Medical Informatics, 10(6), e38482.
24.
LingA. Y.KurianA. W.Caswell-JinJ. L.SledgeG. W.ShahN. H.TamangS. R. (2019). Using natural language processing to construct a metastatic breast cancer cohort from linked cancer registry and electronic medical records data. JAMIA Open, 2(4), 528–537. https://doi.org/10.1093/jamiaopen/ooz040
25.
McCoyT. H.CastroV. M.RobersonA. M.SnapperL. A.PerlisR. H. (2016). Improving prediction of suicide and accidental death after discharge from general hospitals with natural language processing. JAMA Psychiatry, 73(10), 1064–1071, https://doi.org/10.1001/jamapsychiatry.2016.2172
26.
MoosavinasabS.SezginE.SunH.HoffmanJ.HuangY.LinS. (2021). DeepSuggest: Using neural networks to suggest related keywords for a comprehensive search of clinical notes. ACI Open, 05(01), e1–e12. https://doi.org/10.1055/s-0041-1729982
27.
MurnanA.BatesS.HolowaczE. (2020). Understanding the risk and protective factors among children of mothers engaged in street-level prostitution. Children and Youth Services Review, 112, 104899. https://doi.org/10.1016/j.childyouth.2020.104899
28.
MurnanA.HolowaczE. (2020). A qualitative exploration of mother-child relationships in mothers with histories of substance use and street-level prostitution. Journal of Child and Family Studies, 29(11), 3225–3238. https://doi.org/10.1007/s10826-020-01836-9
29.
MurnanA.WuQ.SlesnickN. (2018). The impact of parenting on child mental health among children of prostituting mothers. Children and Youth Services Review, 89, 212–217. https://doi.org/10.1016/j.childyouth.2018.04.042
30.
NaramoreR.BrightM. A.EppsN.HardtN. S. (2017). Youth arrested for trading sex have the highest rates of childhood adversity: A statewide study of juvenile offenders. Sexual Abuse: A Journal of Research and Treatment, 29(4), 396–410. https://doi.org/10.1177/1079063215603064
31.
National Research Council (2014). Confronting commercial sexual exploitation and sex trafficking of minors in the United States. A guide for the health care sector. In Confronting commercial sexual exploitation and sex trafficking of Minors in the United States. National Academic Press.
32.
OngC. J.OrfanoudakiA.ZhangR.CaprasseF. P. M.HutchM.MaL.FardD.BalogunO.MillerM. I.MinnigM.SaglamH.PrescottB.GreerD. M.SmirnakisS.BertsimasD. (2020). Machine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports. PLoS ONE, 15(6), e0234908–e0234916. https://doi.org/10.1371/journal.pone.0234908
33.
RaffertyY. (2016). Challenges to the rapid identification of children who have been trafficked for commercial sexual exploitation. Child Abuse & Neglect, 52, 158–168. https://doi.org/10.1016/j.chiabu.2015.11.015
34.
RichardsT.ReidJ. A. (2015). Gender stereotyping and sex trafficking: Comparative review of research on male and female sex tourism. Journal of Crime and Justice, 38(3), 414–433. https://doi.org/10.1080/0735648x.2014.1000560
35.
VianiN.BotelleR.KerwinJ.YinL.PatelR.StewartR.VelupillaiS. (2021). A natural language processing approach for identifying temporal disease onset information from mental healthcare text. Scientific Reports, 11(1), 757–812. https://doi.org/10.1038/s41598-020-80457-0
36.
WashingtonH. (2006). Medical Apartheid: The Dark History of Medical Experimentation on Black Americans from Colonial Times to the Present. Harlem Moon.
37.
ZengZ.DengY.LiX.NaumannT.LuoY. (2019). Natural Language processing for EHR-based Computational Phenotyping. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 16(1), 139–153. https://doi.org/10.1109/tcbb.2018.2849968
