Predictor Selection for Case Complexity Based on Routine Data for Needs-Based and Competence-Based Staff Planning.
Stud Health Technol Inform
; 315: 332-336, 2024 Jul 24.
Article
em En
| MEDLINE
| ID: mdl-39049278
ABSTRACT
Due to nursing staff shortage and growing nursing care demand, resource allocation and optimal task distribution have become primary concerns of nursing management. Grade mix analysis based on nursing interventions and nurse qualifications from routine patient documentation can support this. Case complexity is a key linking factor of nursing interventions, workload, and grade mix. This study determined case complexity predictors based on one year of routine patient documentation (n = 3,373 cases) from a Swiss hospital and predicted the patient clinical complexity level via weighted cumulative logistic regression models. Significant predictors were sex, age, pre-admission residence, admission type, self- care index, pneumonia risk, and number of nursing interventions. The models' accuracy is limited yet appropriate for applications such as needs- and competence- based staff-planning. After calibration via in-hospital data it could support nursing management in these tasks. The next step is now to test the model in a clinical setting.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Recursos Humanos de Enfermagem Hospitalar
Limite:
Female
/
Humans
/
Male
País como assunto:
Europa
Idioma:
En
Ano de publicação:
2024
Tipo de documento:
Article