Servicios Personalizados
Revista
Articulo
Indicadores
- Citado por SciELO
- Accesos
Links relacionados
- Similares en SciELO
Compartir
Psicologia, Saúde & Doenças
versión impresa ISSN 1645-0086
Resumen
TORRES, Jaqueline et al. Artificial neural networks and satisfaction for compassion in health professionals. Psic., Saúde & Doenças [online]. 2023, vol.24, n.1, pp.189-198. Epub 30-Jun-2023. ISSN 1645-0086. https://doi.org/10.15309/23psd240116.
This study aims to build a model of prediction of satisfaction by compassion among health professionals who care for critical and chronic patients, through the creation of an artificial neural network. The resulting neural network has seven layers with 12 neurons in the input layer, represented by sociodemographic characteristics; 20, 10, 10, 5 and 4 neurons in the intermediate layers; and 1 neuron in the output layer representing “Satisfaction by Compassion”. The logistic function was used as a transfer function for neurons in the first 5 layers, where the activation of the last layer was linear. The Non-Dominant Genetic Classification Algorithm was adopted in its second version. The simulations were carried out with MATLAB® software version R2017a. The best result was presented by the inclusion of 12 variables, with a final accuracy of 94.5%. The artificial neural network built is an innovative tool for studying the quality of professional life.
Palabras clave : Artificial intelligence; Compassion fatigue; Quality of life; Occupational health; Job satisfaction.