Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Machine learning for identifying caregiving adversities associated with greatest risk for mental health problems in children

Nature Mental Health volume 3, pages 71–82 (2025)Cite this article

Subjects

Abstract

Developmental and experiential heterogeneity associated with caregiving-related early adversities (crEAs) poses a major challenge to identifying replicable, generalizable findings. Here conditional random forests evaluated the importance of unique crEA experiences for estimating risks to mental health in 306 children, 6–12 years of age, with heterogeneous crEA experiences (different forms of caregiver-involved abuse and/or neglect or permanent/substantial parent–child separation). The better that crEAs improved the accuracy of symptom estimates in held-out, never-before-seen children, the more important and generalizable they were considered. Here we show that earlier timing and longer duration of crEAs was especially important for elevated general psychopathology (p-factor scores). The mere presence (versus absence) of crEAs was more valuable for estimating symptom risk than were specific adversities in a broad sample. Specific adversities became more important when only looking within the crEA-exposed subsample, with adversities of an interpersonal-affective nature being the most likely to increase transdiagnostic symptom risk. Concurrent consistent caregiving also had high importance, motivating consideration of later-occurring environmental experiences in future studies of early adversity.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Descriptive characteristics of crEAs.
Fig. 2: crEAs and p-factor scores.
Fig. 3: Concurrent caregiving contexts should be considered when estimating mental health risk.

Similar content being viewed by others

Data availability

The data are shared on the NIMH Data Archive Repository (data collection ID 2803; https://nda.nih.gov/). Given the sensitivity of the early adversity information, raw sociodemographic and experiential data cannot be shared publicly to protect the privacy of the participants.

Code availability

Code and result files for primary analyses are shared publicly via the Open Science Foundation repository for this project (https://osf.io/q6gz8).

References

  1. Humphreys, K. L. & Salo, V. C. Expectable environments in early life. Curr. Opin. Behav. Sci. 36, 115–119 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  2. Nikolaidis, A. et al. Heterogeneity in caregiving-related early adversity: creating stable dimensions and subtypes. Dev. Psychopathol. 34, 621–634 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  3. Nelson, C. A., Bhutta, Z. A., Harris, N. B., Danese, A. & Samara, M. Adversity in childhood is linked to mental and physical health throughout life. Brit. Med. J. 371, m3048 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  4. Gee, D. G. Early adversity and development: parsing heterogeneity and identifying pathways of risk and resilience. Am. J. Psychiatry 178, 998–1013 (2021).

    Article  PubMed  Google Scholar 

  5. Danese, A. & Lewis, S. J. New directions in research on childhood adversity. Br. J. Psychiatry 220, 107–108 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  6. Karstoft, K.-I. & Armour, C. What we talk about when we talk about trauma: content overlap and heterogeneity in the assessment of trauma exposure. J. Trauma. Stress 36, 71–82 (2023).

    Article  PubMed  Google Scholar 

  7. Smith, K. E. & Pollak, S. D. Rethinking concepts and categories for understanding the neurodevelopmental effects of childhood adversity. Perspect. Psychol. Sci. 16, 67–93 (2021).

    Article  PubMed  Google Scholar 

  8. Strobl, C., Malley, J. & Tutz, G. An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests. Psychol. Methods 14, 323–348 (2009).

    Article  PubMed  PubMed Central  Google Scholar 

  9. Navarro, M. C. et al. Machine learning assessment of early life factors predicting suicide attempt in adolescence or young adulthood. JAMA Netw. Open 4, e211450 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  10. Khan, A. et al. Childhood maltreatment, depression, and suicidal ideation: critical importance of parental and peer emotional abuse during developmental sensitive periods in males and females. Front. Psychiatry https://doi.org/10.3389/fpsyt.2015.00042(2015).

  11. Schalinski, I. et al. Environmental adversities and psychotic symptoms: the impact of timing of trauma, abuse, and neglect. Schizophr. Res. 205, 4–9 (2019).

    Article  PubMed  Google Scholar 

  12. Vannucci, A. et al. Interpersonal early adversity demonstrates dissimilarity from early socioeconomic disadvantage in the course of human brain development: a meta-analysis. Neurosci. Biobehav. Rev. 150, 105210 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  13. Kotov, R. et al. The Hierarchical Taxonomy of Psychopathology (HiTOP): a dimensional alternative to traditional nosologies. J. Abnorm. Psychol. 126, 454–477 (2017).

    Article  PubMed  Google Scholar 

  14. Caspi, A. et al. The p factor: one general psychopathology factor in the structure of psychiatric disorders. Clin. Psychol. Sci. 2, 119–137 (2014).

    Article  PubMed  PubMed Central  Google Scholar 

  15. Weissman, D. G. et al. Altered neural processing of threat-related information in children and adolescents exposed to violence: a transdiagnostic mechanism contributing to the emergence of psychopathology. J. Am. Acad. Child Adolesc. Psychiatry 59, 1274–1284 (2020).

    Article  PubMed  Google Scholar 

  16. Cicchetti, D. & Rizley, R. Developmental perspectives on the etiology, intergenerational transmission, and sequelae of child maltreatment. New Dir. Child Adolesc. Dev. 1981, 31–55 (1981).

    Article  Google Scholar 

  17. Gunnar, M. R. & Howland, M. A. Calibration and recalibration of stress response systems across development: implications for mental and physical health. Adv. Child Dev. Behav. 63, 35–69 (2022).

    Article  PubMed  Google Scholar 

  18. Ridout, K. K. et al. Early life adversity and telomere length: a meta-analysis. Mol. Psychiatry 23, 858–871 (2018).

    Article  PubMed  Google Scholar 

  19. Tottenham, N. Neural meaning making, prediction, and prefrontal-subcortical development following early adverse caregiving. Dev. Psychopathol. 32, 1563–1578 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  20. Smyke, A. T., Zeanah, C. H., Fox, N. A., Nelson, C. A. & Guthrie, D. Placement in foster care enhances quality of attachment among young institutionalized children. Child Dev. 81, 212–223 (2010).

    Article  PubMed  PubMed Central  Google Scholar 

  21. McLaughlin, K. A. et al. Causal effects of the early caregiving environment on development of stress response systems in children. Proc. Natl Acad. Sci. USA 112, 5637–5642 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  22. Egeland, B. Taking stock: childhood emotional maltreatment and developmental psychopathology. Child Abuse Negl. 33, 22–26 (2009).

    Article  PubMed  Google Scholar 

  23. Fields, A. et al. Adaptation in the face of adversity: decrements and enhancements in children’s cognitive control behavior following early caregiving instability. Dev. Sci. https://doi.org/10.1111/desc.13133 (2021).

  24. Ellis, B. J., Sheridan, M. A., Belsky, J. & McLaughlin, K. A. Why and how does early adversity influence development? Toward an integrated model of dimensions of environmental experience. Dev. Psychopathol. https://doi.org/10.1017/S0954579421001838 (2022).

  25. Johnson, D. et al. Associations of early-life threat and deprivation with executive functioning in childhood and adolescence: a systematic review and meta-analysis. JAMA Pediatr. https://doi.org/10.1001/jamapediatrics.2021.2511 (2021).

  26. McLaughlin, K. A. & Sheridan, M. A. Beyond cumulative risk: a dimensional approach to childhood adversity. Curr. Dir. Psychol. Sci. 25, 239–245 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  27. Pechtel, P., Lyons-Ruth, K., Anderson, C. M. & Teicher, M. H. Sensitive periods of amygdala development: the role of maltreatment in preadolescence. NeuroImage 97, 236–244 (2014).

    Article  PubMed  Google Scholar 

  28. Zhu, J., Anderson, C. M., Ohashi, K., Khan, A. & Teicher, M. H. Potential sensitive period effects of maltreatment on amygdala, hippocampal and cortical response to threat. Mol. Psychiatry https://doi.org/10.1038/s41380-023-02002-5 (2023).

  29. Baldwin, J. R., Reuben, A., Newbury, J. B. & Danese, A. Agreement between prospective and retrospective measures of childhood maltreatment: a systematic review and meta-analysis. JAMA Psychiatry 76, 584–593 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  30. Gabard-Durnam, L. J. & McLaughlin, K. A. Do sensitive periods exist for exposure to adversity. Biol. Psychiatry 85, 789–791 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  31. Callaghan, B. L. & Tottenham, N. The stress acceleration hypothesis: effects of early-life adversity on emotion circuits and behavior. Curr. Opin. Behav. Sci. 7, 76–81 (2016).

    Article  PubMed  Google Scholar 

  32. Dunn, E. C. et al. Time-dependent effects of exposure to physical and sexual violence on psychopathology symptoms in late childhood: in search of sensitive periods in development. J. Am. Acad. Child Adolesc. Psychiatry 59, 283–295.e4 (2020).

    Article  PubMed  Google Scholar 

  33. Gee, D. G. Caregiving influences on emotional learning and regulation: applying a sensitive period model. Curr. Opin. Behav. Sci. 36, 177–184 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  34. Humphreys, K. L. & Zeanah, C. H. Deviations from the expectable environment in early childhood and emerging psychopathology. Neuropsychopharmacology 40, 154–170 (2015).

    Article  PubMed  Google Scholar 

  35. Debnath, R., Tang, A., Zeanah, C. H., Nelson, C. A. & Fox, N. A. The long-term effects of institutional rearing, foster care intervention and disruptions in care on brain electrical activity in adolescence. Dev. Sci. 23, e12872 (2020).

    Article  PubMed  Google Scholar 

  36. Diagnostic and Statistical Manual of Mental Disorders (American Psychiatric Association, 2022).

  37. Lawler, J. M., Koss, K. J. & Gunnar, M. R. Bidirectional effects of parenting and child behavior in internationally adopting families. J. Fam. Psychol. 31, 563 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  38. Chodura, S., Lohaus, A., Symanzik, T., Heinrichs, N. & Konrad, K. Foster parents’ parenting and the social-emotional development and adaptive functioning of children in foster care: a PRISMA-guided literature review and meta-analysis. Clin. Child Fam. Psychol. Rev. 24, 326–347 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  39. Masten, A. S., Lucke, C. M., Nelson, K. M. & Stallworthy, I. C. Resilience in development and psychopathology: multisystem perspectives. Annu. Rev. Clin. Psychol. 17, 521–549 (2021).

    Article  PubMed  Google Scholar 

  40. Somerville, L. H. Searching for signatures of brain maturity: what are we searching for?. Neuron 92, 1164–1167 (2016).

    Article  PubMed  Google Scholar 

  41. Brieant, A. et al. Characterizing the dimensional structure of early-life adversity in the Adolescent Brain Cognitive Development (ABCD) study. Dev. Cogn. Neurosci. 61, 101256 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  42. Kim, H. & Drake, B. Cumulative prevalence of onset and recurrence of child maltreatment reports. J. Am. Acad. Child Adolesc. Psychiatry 58, 1175–1183 (2019).

    Article  PubMed  Google Scholar 

  43. Harden, B. J., Buhler, A. & Parra, L. J. Maltreatment in infancy: a developmental perspective on prevention and intervention. Trauma Violence Abuse 17, 366–386 (2016).

    Article  PubMed  Google Scholar 

  44. Child Maltreatment 2015 (US Department of Health and Human Services, Administration for Children and Families, Administration on Children, Youth and Families, Children’s Bureau, 2017); http://www.acf.hhs.gov/programs/cb/research-data-technology/statistics-research/child-maltreatment

  45. Cicchetti, D., Toth, S. L. & Manly, J. T. Maternal Maltreatment Classification Interview (Hope Family Center, 2003).

  46. Barnett, D., Manley, J. T. & Cicchetti, D. in Child Abuse, Child Development, and Social Policy (eds. Cicchetti, D. & Toth, S.) 7–73 (Ablex, 1993).

  47. Ghosh-Ippen, C. et al. Traumatic Events Screening Inventory—Parent Report Revised (The National Child Traumatic Stress Network, 2002).

  48. Scopel Hoffmann, M. et al. Reliability and validity of bifactor models of dimensional psychopathology in youth. J. Psychopathol. Clin. Sci. 131, 407–421 (2022).

    Article  PubMed  Google Scholar 

  49. Caspi, A., Houts, R. M., Fisher, H. L., Danese, A. & Moffitt, T. E. The general factor of psychopathology (p): choosing among competing models and interpreting p. Clin. Psychol. Sci 12, 53–82 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  50. Clark, D. A. et al. The general factor of psychopathology in the adolescent brain cognitive development (ABCD) study: a comparison of alternative modeling approaches. Clin. Psychol. Sci. 9, 169–182 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  51. Michelini, G. et al. Delineating and validating higher-order dimensions of psychopathology in the Adolescent Brain Cognitive Development (ABCD) study. Transl. Psychiatry 9, 1–15 (2019).

    Article  Google Scholar 

  52. Brislin, S. J. et al. Differentiated nomological networks of internalizing, externalizing, and the general factor of psychopathology (‘p factor’) in emerging adolescence in the ABCD study. Psychol. Med. 52, 3051–3061 (2022).

    Article  PubMed  Google Scholar 

  53. Allegrini, A. G. et al. The p factor: genetic analyses support a general dimension of psychopathology in childhood and adolescence. J. Child Psychol. Psychiatry 61, 30–39 (2020).

    Article  PubMed  Google Scholar 

  54. Sprooten, E., Franke, B. & Greven, C. U. The p-factor and its genomic and neural equivalents: an integrated perspective. Mol. Psychiatry 27, 38–48 (2022).

    Article  PubMed  Google Scholar 

  55. R Core Team. R: A Language and Environment for Statistical Computing (R Foundation for Statistical Computing, 2024).

  56. Constantinou, M. & Fonagy, P. Evaluating bifactor models of psychopathology using model-based reliability indices. Preprint at PsyArXiv https://doi.org/10.1037/pas0000741 (2019).

  57. Heinrich, M. et al. On the meaning of the “p factor” in symmetrical bifactor models of psychopathology: recommendations for future research from the bifactor-(S−1) perspective. Assessment 30, 487–507 (2023).

    Article  PubMed  Google Scholar 

  58. Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).

    Article  Google Scholar 

  59. Hothorn, T., Hornik, K. & Zeileis, A. Unbiased recursive partitioning: a conditional inference framework. J. Comput. Graph. Stat. 15, 651–674 (2006).

    Article  Google Scholar 

  60. Scheinost, D. et al. Ten simple rules for predictive modeling of individual differences in neuroimaging. NeuroImage 193, 35–45 (2019).

    Article  PubMed  Google Scholar 

  61. Nikolaidis, A. et al. Bagging improves reproducibility of functional parcellation of the human brain. NeuroImage 214, 116678 (2020).

    Article  PubMed  Google Scholar 

  62. O’Connor, D., Lake, E. M. R., Scheinost, D. & Constable, R. T. Resample aggregating improves the generalizability of connectome predictive modelling. NeuroImage 236, 118044 (2021).

    Article  PubMed  Google Scholar 

  63. Yarkoni, T. & Westfall, J. Choosing prediction over explanation in psychology: lessons from machine learning. Perspect. Psychol. Sci. J. Assoc. Psychol. Sci. 12, 1100–1122 (2017).

    Article  Google Scholar 

  64. Debeer, D. & Strobl, C. Conditional permutation importance revisited. BMC Bioinf. 21, 307 (2020).

    Article  Google Scholar 

  65. Betz, L. T., Rosen, M., Salokangas, R. K. R. & Kambeitz, J. Disentangling the impact of childhood abuse and neglect on depressive affect in adulthood: a machine learning approach in a general population sample. J. Affect. Disord. 315, 17–26 (2022).

    Article  PubMed  Google Scholar 

  66. Dinga, R., Schmaal, L., Penninx, B. W. J. H., Veltman, D. J. & Marquand, A. F. Controlling for effects of confounding variables on machine learning predictions. Preprint at bioRxiv https://doi.org/10.1101/2020.08.17.255034 (2020).

Download references

Acknowledgements

We express our deep appreciation to the families participating in this study. The authors gratefully acknowledge current and former lab members who assisted with data collection and coding. This work was supported by the National Institute of Mental Health: R01MH091864-10 (co-principal investigators: N.T. and M.P.M.) and the National Institutes of Health Blueprint and BRAIN Initiative Diversity Specialized Predoctoral to Postdoctoral Advancement in Neuroscience (D-SPAN) Award: F99NS134207-01 (principal Iinvestigator: A.V.).

Author information

Author notes

  1. Ian J. Douglas

    Present address: Data Insights, LLC, Austin, TX, USA

  2. These authors contributed equally: Michael P. Milham, Nim Tottenham.

Authors and Affiliations

  1. Columbia University, Department of Psychology, Schermerhorn Hall, New York, NY, USA

    Anna Vannucci, Andrea Fields, Charlotte Heleniak, Ian J. Douglas & Nim Tottenham

  2. Columbia University Irving Medical Center, New York, NY, USA

    Paul A. Bloom

  3. Western Washington University, Department of Psychology, Bellingham, WA, USA

    Chelsea Harmon

  4. Child Mind Institute, New York, NY, USA

    Aki Nikolaidis & Michael P. Milham

  5. Icahn School of Medicine at Mt. Sinai, New York, NY, USA

    Lisa Gibson

  6. Duke University, Durham, NC, USA

    Nicolas L. Camacho

  7. University of California, Riverside, CA, USA

    Tricia Choy

  8. Teachers College, Columbia University, New York, NY, USA

    Syntia S. Hadis

  9. Genesis Research, Hoboken, NJ, USA

    Michelle VanTieghem

  10. University of Delaware, Department of Psychological and Brain Sciences, Newark, DE, USA

    Mary Dozier

Authors
  1. Anna Vannucci
    View author publications

    Search author on:PubMed Google Scholar

  2. Andrea Fields
    View author publications

    Search author on:PubMed Google Scholar

  3. Charlotte Heleniak
    View author publications

    Search author on:PubMed Google Scholar

  4. Paul A. Bloom
    View author publications

    Search author on:PubMed Google Scholar

  5. Chelsea Harmon
    View author publications

    Search author on:PubMed Google Scholar

  6. Aki Nikolaidis
    View author publications

    Search author on:PubMed Google Scholar

  7. Ian J. Douglas
    View author publications

    Search author on:PubMed Google Scholar

  8. Lisa Gibson
    View author publications

    Search author on:PubMed Google Scholar

  9. Nicolas L. Camacho
    View author publications

    Search author on:PubMed Google Scholar

  10. Tricia Choy
    View author publications

    Search author on:PubMed Google Scholar

  11. Syntia S. Hadis
    View author publications

    Search author on:PubMed Google Scholar

  12. Michelle VanTieghem
    View author publications

    Search author on:PubMed Google Scholar

  13. Mary Dozier
    View author publications

    Search author on:PubMed Google Scholar

  14. Michael P. Milham
    View author publications

    Search author on:PubMed Google Scholar

  15. Nim Tottenham
    View author publications

    Search author on:PubMed Google Scholar

Contributions

All authors accept responsibility for the content of the manuscript. Specific author contributions are as following: A.V.: conceptualization (lead); writing—original draft (lead); data curation (lead); formal analysis (lead); data collection (supporting); creation, testing and implementation of code (lead); validation—reproducibility of research outputs (lead); and data visualization (lead). A.F.: data collection (supporting), data curation (supporting) and writing—review and editing (supporting). C.H.: data collection (supporting), data curation (supporting), project administration (supporting) and writing—review and editing (supporting). P.A.B.: data collection (supporting) and writing—review and editing (supporting). C.H.: data collection (supporting) and writing—review and editing (supporting). A.N.: data analysis (supporting) and writing—review and editing (supporting). I.J.D.: formal analysis (supporting); creation, testing and implementation of code (supporting); validation—reproducibility of research outputs (supporting); and data visualization (supporting). L.G.: data collection (supporting), data curation (equal) and writing—review and editing (supporting). N.L.C.: data collection (supporting), project administration (supporting) and writing—review and editing (supporting). T.C.: data collection (supporting), project administration (supporting) and writing—review and editing (supporting). S.S.H.: data collection (supporting), project administration (supporting) and writing—review and editing (supporting). M.V.: data collection (supporting). M.D.: writing—review and editing (supporting). M.P.M.: conceptualization (lead/equal), funding acquisition (lead/equal), methodology (lead/equal), writing—review and editing (supporting) and project administration (supporting). N.T.: conceptualization (lead/equal), writing—original draft (supporting), funding acquisition (lead), methodology (lead/equal), project administration (lead), resources (lead), supervision (lead) and data visualization (supporting).

Corresponding author

Correspondence to Anna Vannucci.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Mental Health thanks Jungmeen Kim-Spoon and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Methods Text, Supplementary Tables 1–7, Supplementary Figs. 1–8 and References.

Reporting Summary

Source data

Source Data Fig. 1

Statistical source data.

Source Data Fig. 2

Statistical source data.

Source Data Fig. 3

Statistical source data.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) 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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Vannucci, A., Fields, A., Heleniak, C. et al. Machine learning for identifying caregiving adversities associated with greatest risk for mental health problems in children. Nat. Mental Health 3, 71–82 (2025). https://doi.org/10.1038/s44220-024-00355-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s44220-024-00355-6

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing