Display options
Cite
Karasch O, Schmitz-Buhl M, Mennicken R, et al. Identification of risk factors for involuntary psychiatric hospitalization: using environmental socioeconomic data and methods of machine learning to improve prediction. BMC Psychiatry. 2020;20(1):401doi: 10.1186/s12888-020-02803-w.
Karasch, O., Schmitz-Buhl, M., Mennicken, R., Zielasek, J., & Gouzoulis-Mayfrank, E. (2020). Identification of risk factors for involuntary psychiatric hospitalization: using environmental socioeconomic data and methods of machine learning to improve prediction. BMC psychiatry, 20(1), 401. https://doi.org/10.1186/s12888-020-02803-w
Karasch, O, et al. "Identification of risk factors for involuntary psychiatric hospitalization: using environmental socioeconomic data and methods of machine learning to improve prediction." BMC psychiatry vol. 20,1 (2020): 401. doi: https://doi.org/10.1186/s12888-020-02803-w
Karasch O, Schmitz-Buhl M, Mennicken R, Zielasek J, Gouzoulis-Mayfrank E. Identification of risk factors for involuntary psychiatric hospitalization: using environmental socioeconomic data and methods of machine learning to improve prediction. BMC Psychiatry. 2020 Aug 08;20(1):401. doi: 10.1186/s12888-020-02803-w. PMID: 32770970; PMCID: PMC7414567.
Copy Download .nbib Format: NLM
Share it on

BMC Psychiatry. 2020 Aug 08;20(1):401. doi: 10.1186/s12888-020-02803-w.

Identification of risk factors for involuntary psychiatric hospitalization: using environmental socioeconomic data and methods of machine learning to improve prediction.

BMC psychiatry

O Karasch, M Schmitz-Buhl, R Mennicken, J Zielasek, E Gouzoulis-Mayfrank

Affiliations

  1. LVR-Institute for Healthcare Research, Wilhelm-Griesinger-Strasse 23, 51109, Cologne (Köln), Germany.
  2. LVR Clinics Cologne, Cologne, Germany.
  3. LVR Clinical Group Department, Cologne, and FOM University of Applied Sciences, Essen, Germany.
  4. LVR-Institute for Healthcare Research, Wilhelm-Griesinger-Strasse 23, 51109, Cologne (Köln), Germany. [email protected].
  5. LVR Clinics Cologne, Cologne, Germany. [email protected].

PMID: 32770970 PMCID: PMC7414567 DOI: 10.1186/s12888-020-02803-w

Abstract

BACKGROUND: The purpose of this study was to identify factors associated with a high risk of involuntary psychiatric in-patient hospitalization both on the individual level and on the level of mental health services and the socioeconomic environment that patients live in.

METHODS: The present study expands on a previous analysis of the health records of 5764 cases admitted as in-patients in the four psychiatric hospitals of the Metropolitan City of Cologne, Germany, in the year 2011 (1773 cases treated under the Mental Health Act and 3991 cases treated voluntarily). Our previous analysis had included medical, sociodemographic and socioeconomic data of every case and used a machine learning-based prediction model employing chi-squared automatic interaction detection (CHAID). Our current analysis attempts to improve the previous one through (1) optimizing the machine learning procedures (use of a different type of decision-tree prediction model (Classification and Regression Trees (CART) and application of hyperparameter tuning (HT)), and (2) the addition of patients' environmental socioeconomic data (ESED) to the data set.

RESULTS: Compared to our previous analysis, model fit was improved. Main diagnoses of an organic mental or a psychotic disorder (ICD-10 groups F0 and F2), suicidal behavior upon admission, admission outside of regular service hours and absence of outpatient treatment prior to admission were confirmed as powerful predictors of detention. Particularly high risks were shown for (1) patients with an organic mental disorder, specifically if they were retired, admitted outside of regular service hours and lived in assisted housing, (2) patients with suicidal tendencies upon admission who did not suffer from an affective disorder, specifically if it was unclear whether there had been previous suicide attempts, or if the affected person lived in areas with high unemployment rates, and (3) patients with psychosis, specifically those who lived in densely built areas with a large proportion of small or one-person households.

CONCLUSIONS: Certain psychiatric diagnoses and suicidal tendencies are major risk factors for involuntary psychiatric hospitalization. In addition, service-related and environmental socioeconomic factors contribute to the risk for detention. Identifying modifiable risk factors and particularly vulnerable risk groups should help to develop suitable preventive measures.

Keywords: Area-deprivation; Decision-tree analysis; Environmental socioeconomic data; Involuntary admission; Machine learning; Mental health act; Urbanization

References

  1. J Psychiatr Res. 2018 Oct;105:147-152 - PubMed
  2. Psychiatr Prax. 2015 Apr;42(3):133-9 - PubMed
  3. Schizophr Bull. 2012 Nov;38(6):1118-23 - PubMed
  4. BMC Psychiatry. 2018 Dec 29;18(1):401 - PubMed
  5. Int J Law Psychiatry. 2016 Jul-Aug;47:53-9 - PubMed
  6. J Emerg Med. 2016 Mar;50(3):449-57 - PubMed
  7. JAMA Psychiatry. 2016 Jul 1;73(7):657-64 - PubMed
  8. Int J Environ Res Public Health. 2015 Nov 20;12(11):14898-915 - PubMed
  9. Health Inf Manag. 1997 Mar-May;27(1):31-8 - PubMed
  10. BMJ. 2005 Sep 17;331(7517):599 - PubMed
  11. Lancet Psychiatry. 2019 Dec;6(12):1039-1053 - PubMed
  12. Soc Psychiatry Psychiatr Epidemiol. 2004 Oct;39(10):804-9 - PubMed
  13. J Epidemiol Community Health. 2015 Jun;69(6):523-9 - PubMed
  14. World Psychiatry. 2013 Oct;12(3):187-97 - PubMed
  15. Lancet Psychiatry. 2019 May;6(5):403-417 - PubMed
  16. Int J Soc Psychiatry. 2014 Nov;60(7):672-80 - PubMed
  17. Soc Psychiatry Psychiatr Epidemiol. 2017 Aug;52(8):979-987 - PubMed
  18. Br J Psychiatry. 2014 Mar;204(3):174-5 - PubMed
  19. Soc Psychiatry Psychiatr Epidemiol. 2006 Dec;41(12):981-8 - PubMed
  20. Psychiatr Serv. 2009 Nov;60(11):1543-6 - PubMed
  21. Acta Biomed. 2018 Jul 18;89(6-S):17-28 - PubMed
  22. Int J Integr Care. 2009 Sep 09;9:e90 - PubMed
  23. Eur Psychiatry. 2011 May;26(4):244-51 - PubMed
  24. Br J Psychiatry. 2020 Sep;217(3):477-483 - PubMed
  25. PLoS One. 2019 May 16;14(5):e0216929 - PubMed
  26. Eur Psychiatry. 2004 Apr;19(2):67-71 - PubMed
  27. Psychiatr Q. 2013 Mar;84(1):73-80 - PubMed
  28. Br J Psychiatry. 1995 Dec;167(6):770-6 - PubMed
  29. BMC Psychiatry. 2019 Apr 29;19(1):127 - PubMed
  30. Int J Environ Res Public Health. 2015 Apr 22;12(4):4354-79 - PubMed
  31. J Psychiatr Ment Health Nurs. 2018 Apr;25(3):188-200 - PubMed
  32. Curr Psychiatry Rep. 2019 Jul 1;21(8):63 - PubMed
  33. Asian J Psychiatr. 2018 Jun;35:141-145 - PubMed
  34. Soc Psychiatry Psychiatr Epidemiol. 2002 Jul;37(7):341-5 - PubMed
  35. Ann Gen Psychiatry. 2017 Jan 25;16:3 - PubMed
  36. Schizophr Bull. 2018 Jan 13;44(1):114-125 - PubMed
  37. J Adv Nurs. 2014 Nov;70(11):2651-62 - PubMed
  38. Schizophr Res. 2010 Jan;116(1):75-89 - PubMed
  39. Cad Saude Publica. 2013 Nov;29(11):2347-52 - PubMed
  40. Sci Adv. 2019 Jul 24;5(7):eaax0903 - PubMed
  41. Int J Law Psychiatry. 2013 Mar-Apr;36(2):136-43 - PubMed
  42. Prog Neuropsychopharmacol Biol Psychiatry. 2012 Dec 3;39(2):288-94 - PubMed
  43. Arch Psychiatr Nurs. 2014 Aug;28(4):272-6 - PubMed
  44. Artif Intell Med. 2019 Aug;99:101704 - PubMed
  45. Br J Psychiatry. 2004 Feb;184:163-8 - PubMed
  46. Soc Psychiatry Psychiatr Epidemiol. 2002 Oct;37(10):460-4 - PubMed
  47. BMC Psychiatry. 2020 Mar 30;20(1):138 - PubMed
  48. J Occup Rehabil. 2020 Sep;30(3):308-317 - PubMed
  49. Br J Psychiatry. 2016 Aug;209(2):157-61 - PubMed
  50. Soc Psychiatry Psychiatr Epidemiol. 2017 Dec;52(12):1451-1461 - PubMed
  51. Nord J Psychiatry. 2012 Jun;66(3):178-82 - PubMed
  52. Dtsch Arztebl Int. 2017 Feb 24;114(8):121-127 - PubMed
  53. Z Evid Fortbild Qual Gesundhwes. 2011;105(5):360-4 - PubMed
  54. Prog Neuropsychopharmacol Biol Psychiatry. 2011 Jan 15;35(1):137-45 - PubMed
  55. Int J Law Psychiatry. 2018 Mar - Apr;57:17-23 - PubMed

MeSH terms

Publication Types