ISEP - DM – Engenharia Biomédica
Permanent URI for this collection
Browse
Browsing ISEP - DM – Engenharia Biomédica by Author "Carreira, Ana Rita Afonso"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
- Hospital long-term care discharge clusters: a nationwide study using Clustering and Decision Tree methodsPublication . Carreira, Ana Rita Afonso; Marreiros, Maria Goreti CarvalhoIntroduction: The ageing of the population structure leads to higher needs of long-term care (LTC). In order to adapt LTC and its associated policies it is important to establish the appropriate setting of personalised care. Hence, it is important to understand the associated factors that lead patients to the LTC use. The objective of this study is to assess clusters of hospitalised patients with higher proportion of discharges to LTC (LTCD) in Portugal, as well as to test the clustering method as a solution for an early identification of potential users, using different approaches. Methods: A nationwide Portuguese study was performed, using inpatient data from Portuguese hospitals with discharges between 2012 and 2017. The variables used in this study were age, sex, principal diagnosis, comorbidities (identified using secondary diagnoses), admission type and hospital transfer. The main outcome of this analysis is being discharged to long-term and maintenance units (Unidades de Longa Duração e Manutenção - ULDM). Different approaches were applied to categorise principal diagnosis for each inpatient episode, using ICD-9-CM and ICD-10-CM main groups, ICD-9-CM and ICD-10-CM more detailed categories, Clinical Classification Software (CCS) and CCS Refined (CCSR). Subsequently, hierarchical clustering techniques were applied to determine the number of clusters in each dataset and decision tree methods were used to characterize each cluster. Results: A total of 4427 inpatient episodes (0.23%) were discharged to LTC. Across the different methods to characterise principal diagnosis, the clusters with the highest proportion of discharges to LTC ranged between 0.7% and 60.8%. Conclusion: There is great variability of the clustering results when comparing the different approaches of categorising principal diagnosis. The “quality” of the principal diagnosis categorisation overcomes the “quantity” (i.e. number of categories). This can have important implications for health system policies and hospital management Nevertheless, clustering methods showed to be good options to identify high-risk groups.