Literature DB >> 33653425

Using machine learning to predict suicide in the 30 days after discharge from psychiatric hospital in Denmark.

Tammy Jiang1, Anthony J Rosellini2, Erzsébet Horváth-Puhó3, Brian Shiner4, Amy E Street5, Timothy L Lash6, Henrik T Sørensen7, Jaimie L Gradus1.   

Abstract

BACKGROUND: Suicide risk is high in the 30 days after discharge from psychiatric hospital, but knowledge of the profiles of high-risk patients remains limited. AIMS: To examine sex-specific risk profiles for suicide in the 30 days after discharge from psychiatric hospital, using machine learning and Danish registry data.
METHOD: We conducted a case-cohort study capturing all suicide cases occurring in the 30 days after psychiatric hospital discharge in Denmark from 1 January 1995 to 31 December 2015 (n = 1205). The comparison subcohort was a 5% random sample of all persons born or residing in Denmark on 1 January 1995, and who had a first psychiatric hospital admission between 1995 and 2015 (n = 24 559). Predictors included diagnoses, surgeries, prescribed medications and demographic information. The outcome was suicide death recorded in the Danish Cause of Death Registry.
RESULTS: For men, prescriptions for anxiolytics and drugs used in addictive disorders interacted with other characteristics in the risk profiles (e.g. alcohol-related disorders, hypnotics and sedatives) that led to higher risk of postdischarge suicide. In women, there was interaction between recurrent major depression and other characteristics (e.g. poisoning, low income) that led to increased risk of suicide. Random forests identified important suicide predictors: alcohol-related disorders and nicotine dependence in men and poisoning in women.
CONCLUSIONS: Our findings suggest that accurate prediction of suicide during the high-risk period immediately after psychiatric hospital discharge may require a complex evaluation of multiple factors for men and women.

Entities:  

Keywords:  Suicide; machine learning; postdischarge suicide; psychiatric hospital; suicide prediction

Mesh:

Year:  2021        PMID: 33653425      PMCID: PMC8457342          DOI: 10.1192/bjp.2021.19

Source DB:  PubMed          Journal:  Br J Psychiatry        ISSN: 0007-1250            Impact factor:   9.319


  34 in total

1.  Analysis of case-cohort designs.

Authors:  W E Barlow; L Ichikawa; D Rosner; S Izumi
Journal:  J Clin Epidemiol       Date:  1999-12       Impact factor: 6.437

2.  Predictive value of stroke discharge diagnoses in the Danish National Patient Register.

Authors:  Pernille Lühdorf; Kim Overvad; Erik B Schmidt; Søren P Johnsen; Flemming W Bach
Journal:  Scand J Public Health       Date:  2017-07-13       Impact factor: 3.021

3.  Gender and risk factors for suicide: evidence for heterogeneity in predisposing mechanisms in a psychological autopsy study.

Authors:  Alexander McGirr; Monique Séguin; Johanne Renaud; Chawki Benkelfat; Martin Alda; Gustavo Turecki
Journal:  J Clin Psychiatry       Date:  2006-10       Impact factor: 4.384

4.  The Danish Civil Registration System.

Authors:  Carsten Bøcker Pedersen
Journal:  Scand J Public Health       Date:  2011-07       Impact factor: 3.021

5.  Noncontraceptive estrogens and mortality: long-term follow-up of women in the Walnut Creek Study.

Authors:  D B Petitti; J A Perlman; S Sidney
Journal:  Obstet Gynecol       Date:  1987-09       Impact factor: 7.661

6.  Predictive value of pediatric thrombosis diagnoses in the Danish National Patient Registry.

Authors:  Ruta Tuckuviene; Soeren Risom Kristensen; Jon Helgestad; Anette Luther Christensen; Soeren Paaske Johnsen
Journal:  Clin Epidemiol       Date:  2010-08-09       Impact factor: 4.790

7.  Developing a practical suicide risk prediction model for targeting high-risk patients in the Veterans health Administration.

Authors:  Ronald C Kessler; Irving Hwang; Claire A Hoffmire; John F McCarthy; Maria V Petukhova; Anthony J Rosellini; Nancy A Sampson; Alexandra L Schneider; Paul A Bradley; Ira R Katz; Caitlin Thompson; Robert M Bossarte
Journal:  Int J Methods Psychiatr Res       Date:  2017-07-04       Impact factor: 4.035

8.  Using Administrative Data to Predict Suicide After Psychiatric Hospitalization in the Veterans Health Administration System.

Authors:  Ronald C Kessler; Mark S Bauer; Todd M Bishop; Olga V Demler; Steven K Dobscha; Sarah M Gildea; Joseph L Goulet; Elizabeth Karras; Julie Kreyenbuhl; Sara J Landes; Howard Liu; Alex R Luedtke; Patrick Mair; William H B McAuliffe; Matthew Nock; Maria Petukhova; Wilfred R Pigeon; Nancy A Sampson; Jordan W Smoller; Lauren M Weinstock; Robert M Bossarte
Journal:  Front Psychiatry       Date:  2020-05-06       Impact factor: 4.157

9.  Meta-analysis of suicide rates in the first week and the first month after psychiatric hospitalisation.

Authors:  Daniel Chung; Dusan Hadzi-Pavlovic; Maggie Wang; Sascha Swaraj; Mark Olfson; Matthew Large
Journal:  BMJ Open       Date:  2019-03-23       Impact factor: 2.692

10.  Are suicide deaths under-reported? Nationwide re-evaluations of 1800 deaths in Scandinavia.

Authors:  Ingvild Maria Tøllefsen; Karin Helweg-Larsen; Ingemar Thiblin; Erlend Hem; Marianne C Kastrup; Ullakarin Nyberg; Sidsel Rogde; Per-Henrik Zahl; Gunvor Østevold; Øivind Ekeberg
Journal:  BMJ Open       Date:  2015-11-25       Impact factor: 2.692

View more
  2 in total

1.  Suicide prediction among men and women with depression: A population-based study.

Authors:  Tammy Jiang; Dávid Nagy; Anthony J Rosellini; Erzsébet Horváth-Puhó; Katherine M Keyes; Timothy L Lash; Sandro Galea; Henrik T Sørensen; Jaimie L Gradus
Journal:  J Psychiatr Res       Date:  2021-08-11       Impact factor: 5.250

2.  Predictors of nonfatal suicide attempts within 30 days of discharge from psychiatric hospitalization: Sex-specific models developed using population-based registries.

Authors:  Rachel L Zelkowitz; Tammy Jiang; Erzsébet Horváth-Puhó; Amy E Street; Timothy L Lash; Henrik T Sørensen; Anthony J Rosellini; Jaimie L Gradus
Journal:  J Affect Disord       Date:  2022-03-16       Impact factor: 6.533

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.