Suicide Risk Assessment in Hospitals

Desjardins, Isabelle; Cats-Baril, William L.; Maruti, Sanchit; Freeman, Kalev; Althoff, Robert R.

doi:10.4088/jcp.15m09881

Cited by 17 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In several cases, the development and testing of clinical prediction models were evaluated against traditional statistics [ 6 , 55 ], showing superiority of ML in the classification of risk. Reports likewise compared ML-guided decision tree models to clinician-based predictions (i.e., of hospitalization following a suicide attempt (SA) or predicting likelihood of a suicide risk outcome) to guide triage [ 6 , 55 , 59 , 76 , 78 , 96 ]. Importantly, ML-guided risk stratification models outperformed those relying on clinician-based prediction methods alone.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence and Suicide Prevention: A Systematic Review of Machine Learning Investigations

Bernert

Hilberg

Melia

et al. 2020

IJERPH

138

View full text Add to dashboard Cite

Suicide is a leading cause of death that defies prediction and challenges prevention efforts worldwide. Artificial intelligence (AI) and machine learning (ML) have emerged as a means of investigating large datasets to enhance risk detection. A systematic review of ML investigations evaluating suicidal behaviors was conducted using PubMed/MEDLINE, PsychInfo, Web-of-Science, and EMBASE, employing search strings and MeSH terms relevant to suicide and AI. Databases were supplemented by hand-search techniques and Google Scholar. Inclusion criteria: (1) journal article, available in English, (2) original investigation, (3) employment of AI/ML, (4) evaluation of a suicide risk outcome. N = 594 records were identified based on abstract search, and 25 hand-searched reports. N = 461 reports remained after duplicates were removed, n = 316 were excluded after abstract screening. Of n = 149 full-text articles assessed for eligibility, n = 87 were included for quantitative synthesis, grouped according to suicide behavior outcome. Reports varied widely in methodology and outcomes. Results suggest high levels of risk classification accuracy (>90%) and Area Under the Curve (AUC) in the prediction of suicidal behaviors. We report key findings and central limitations in the use of AI/ML frameworks to guide additional research, which hold the potential to impact suicide on broad scale.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence and Suicide Prevention: A Systematic Review of Machine Learning Investigations

Bernert

Hilberg

Melia

et al. 2020

IJERPH

138

View full text Add to dashboard Cite

show abstract

“…Desjardins et. al [ 35 ]. constructed a suicide risk assessment tool using a neural network model, with 94% accuracy compared to expert psychiatric assessments.…”

Section: Resultsmentioning

confidence: 99%

Applications of artificial intelligence to improve patient flow on mental health inpatient units - Narrative literature review

Cecula

Dawoodbhoy

et al. 2021

Heliyon

View full text Add to dashboard Cite

Background Despite a growing body of research into both Artificial intelligence and mental health inpatient flow issues, few studies adequately combine the two. This review summarises findings in the fields of AI in psychiatry and patient flow from the past 5 years, finds links and identifies gaps for future research. Methods The OVID database was used to access Embase and Medline. Top journals such as JAMA, Nature and The Lancet were screened for other relevant studies. Selection bias was limited by strict inclusion and exclusion criteria. Research 3,675 papers were identified in March 2020, of which a limited number focused on AI for mental health unit patient flow. After initial screening, 323 were selected and 83 were subsequently analysed. The literature review revealed a wide range of applications with three main themes: diagnosis (33%), prognosis (39%) and treatment (28%). The main themes that emerged from AI in patient flow studies were: readmissions (41%), resource allocation (44%) and limitations (91%). The review extrapolates those solutions and suggests how they could potentially improve patient flow on mental health units, along with challenges and limitations they could face. Conclusion Research widely addresses potential uses of AI in mental health, with some focused on its applicability in psychiatric inpatients units, however research rarely discusses improvements in patient flow. Studies investigated various uses of AI to improve patient flow across specialities. This review highlights a gap in research and the unique research opportunity it presents.

show abstract

“…La Joint Comission (JC) estimó que en 2018 el número global de suicidios de pacientes hospitalizados en los Estados Unidos osciló entre 48 y 65 por año (Williams et al, 2018). El suicidio intrahospitalario consumado es uno de los eventos centinela (SE por sus siglas en inglés sentinel event) más reportados ante la JC (Desjardins et al, 2016;Sakinofsky, 2014;Ballard et al, 2008). Un SE es un suceso inesperado (no relacionado directamente con el curso natural de la enfermedad, por ejemplo, una cirugía en un lugar anatómico erróneo) que resulta en muerte, daño permanente o daño temporal severo con requerimiento de una inter-vención para mantener la vida.…”

Section: Introductionunclassified

“…Un SE es un suceso inesperado (no relacionado directamente con el curso natural de la enfermedad, por ejemplo, una cirugía en un lugar anatómico erróneo) que resulta en muerte, daño permanente o daño temporal severo con requerimiento de una inter-vención para mantener la vida. El suicidio intrahospitalario se define como el suicidio de cualquier paciente en un entorno hospitalario o dentro de las 72 horas posteriores al egreso (Desjardins et al, 2016;Williams et al, 2018). Usualmente, se considera que en el medio hospitalario el paciente está bajo un mayor grado de control y seguridad.…”

Section: Introductionunclassified

“…Las muertes por suicidio intrahospitalario tienen una especial relevancia debido tanto al impacto en las familias y en el personal de salud, como a las implicaciones legales que puede traer a las instituciones (Desjardins et al, 2016;Sakinofsky, 2014). Algunos estudios muestran que el suicidio es prevenible mediante intervenciones oportunas, basadas en la obtención de datos poblacionales específicos y confiables.…”

Section: Introductionunclassified

See 1 more Smart Citation

Factores de riesgo suicida intra-hospitalario: Un estudio de casos y controles

Otero¹,

Vergel

Paredes

et al. 2022

RPPC

View full text Add to dashboard Cite

Risk factors for inpatient suicide: A case-control study Abstract: The aim of this work was to study the factors associated with suicide risk in patients with general illness who are hospitalized in a high complexity institution. A case-control study with patients hospitalized due to general illness was conducted in 2018 including 115 cases and 155 controls. Independent variables were sex, age, previous suicide attempt, medical diagnosis, psychiatric disorder and uncontrolled pain. The variables associated with suicide risk during hospitalization were male sex and previous suicide attempt (OR 2.21 and 4.08 respectively). Not having a diagnosis of depression and younger age were protective factors (OR 0.05 and 0.95 respectively). This study is one of the few focused on inpatient suicide risk in Latin America. Our findings suggest that the inclusion of young male patients in strategies aimed at preventing inpatient suicide should be a priority.Keywords: Suicide risk; suicidal behavior; inpatient suicide; general hospital; Latin America; Colombia. Resumen: El objetivo de este trabajo fue estudiar los factores asociados a riesgo suicida en pacientes con enfermedad general en una institución de alta complejidad. Se realizó un estudio de casos y controles en pacientes hospitalizados por enfermedad general en 2018, se incluyeron 115 casos y 155 controles. Las variables independientes fueron sexo, edad, intento suicida previo, diagnóstico médico, trastorno psiquiátrico y dolor no controlado. Las variables asociadas a riesgo suicida durante la hospitalización fueron sexo masculino y antecedente de intento suicida (OR 2.21 y 4.08 respectivamente). No tener diagnóstico de depresión y una menor edad fueron factores protectores (OR 0.05 y 0.95 respectivamente). Este estudio es de los pocos enfocado en riesgo suicida intrahospitalario en Latinoamérica. Los hallazgos sugieren que se debe priorizar la inclusión de pacientes jóvenes de sexo masculino en las estrategias encaminadas a la prevención de suicidio intra-hospitalario. Palabras clave: Riesgo suicida; comportamiento suicida; suicidio intrahospitalario; hospital general; Latinoamérica; Colombia.

show abstract

Suicide Risk Assessment in Hospitals

Cited by 17 publications

References 14 publications

Artificial Intelligence and Suicide Prevention: A Systematic Review of Machine Learning Investigations

Artificial Intelligence and Suicide Prevention: A Systematic Review of Machine Learning Investigations

Applications of artificial intelligence to improve patient flow on mental health inpatient units - Narrative literature review

Factores de riesgo suicida intra-hospitalario: Un estudio de casos y controles

Contact Info

Product

Resources

About