Método Clúster – Red neuronal artificial para valoración y diagnóstico temprano de ideación suicida en adolescentes escolarizados
Cargando...
Archivos
Fecha
2023
Autores
De la hoz Granadillo, Efraín Javier
Reyes Ruiz, Lizeth
Sánchez Villegas, Milgen
Título de la revista
ISSN de la revista
Título del volumen
Editor
Interamerican Society of Psychology
Resumen
El suicidio es considerado un problema de salud donde los adolescentes presentan mayor riesgo. Este trabajo desarrolló un método de valoración y pronóstico para el diagnóstico temprano de la ideación suicida en adolescentes escolarizados a través de técnicas multivariadas análisis de clúster y redes neuronales artificiales. Se analizaron variables relacionadas con pensamientos, planes y manifestaciones suicidas en (n=638) adolescentes. El análisis de clúster permitió identificar el 73.2% de los adolescentes con ideación suicida baja, 18.5% ideación suicida media y 8,3% con alta ideación suicida. Se diseñó una red neuronal con capacidad de clasificación correcta del 95,5%. El método propuesto tiene capacidad de discriminar y diagnosticar la ideación suicida en adolescentes escolarizados. Estos resultados buscan aportar a la construcción y desarrollo de iniciativas enfocadas a la detección temprana e intervención desde la implementación de políticas educativas y públicas para la prevención del suicidio en la adolescencia.
Worldwide, suicide is considered a health problem where adolescents are most at risk. This work developed a method to assess and predict an early diagnosis of suicidal ideation among school adolescents through multivariate techniques: cluster analysis and artificial neural networks. Variables related to suicidal thoughts, plans and manifestation were analyzed in (n=638) adolescents. Cluster analysis identified 73.2% of adolescents with low suicidal ideation, 18.5% with medium suicidal ideation and 8.3% with high suicidal ideation. A neural network was designed with a correct classification capacity of 95.5%. The proposed method can discriminate and diagnose suicidal ideation in school adolescents. These results seek to create and develop initiatives focused on early detection and intervention to implementing educational and public policies preventing suicide among adolescents.
Worldwide, suicide is considered a health problem where adolescents are most at risk. This work developed a method to assess and predict an early diagnosis of suicidal ideation among school adolescents through multivariate techniques: cluster analysis and artificial neural networks. Variables related to suicidal thoughts, plans and manifestation were analyzed in (n=638) adolescents. Cluster analysis identified 73.2% of adolescents with low suicidal ideation, 18.5% with medium suicidal ideation and 8.3% with high suicidal ideation. A neural network was designed with a correct classification capacity of 95.5%. The proposed method can discriminate and diagnose suicidal ideation in school adolescents. These results seek to create and develop initiatives focused on early detection and intervention to implementing educational and public policies preventing suicide among adolescents.
Descripción
Palabras clave
Ideación suicida, Ideas suicidas, Riesgo suicida, Suicidio, Adolescentes, Análisis multivariado, Suicide ideation, Suicide risk, Suicide, Adolescents, Multivariate analysis
