Limits...
Risk Factors for Emergency Department Short Time Readmission in Stratified Population.

Besga A, Ayerdi B, Alcalde G, Manzano A, Lopetegui P, Graña M, González-Pinto A - Biomed Res Int (2015)

Bottom Line: The variables with the greatest discriminating power were age, comorbidity, reasons for consultation, social factors, and drug treatments.It is possible to predict readmissions in stratified groups with high accuracy and to identify the most important factors influencing the event.Therefore, it will be possible to develop interventions to improve the quality of care provided to ED patients.

View Article: PubMed Central - PubMed

Affiliation: Emergency Department, Álava University Hospital, 01010 Vitoria, Spain ; Biomedical Research Networking Center in Mental Health (CIBERSAM), 10001 Madrid, Spain ; Faculty of Medicine, University of the Basque Country (UPV/EHU), 01010 Vitoria, Spain.

ABSTRACT

Background: Emergency department (ED) readmissions are considered an indicator of healthcare quality that is particularly relevant in older adults. The primary objective of this study was to identify key factors for predicting patients returning to the ED within 30 days of being discharged.

Methods: We analysed patients who attended our ED in June 2014, stratified into four groups based on the Kaiser pyramid. We collected data on more than 100 variables per case including demographic and clinical characteristics and drug treatments. We identified the variables with the highest discriminating power to predict ED readmission and constructed classifiers using machine learning methods to provide predictions.

Results: Classifier performance distinguishing between patients who were and were not readmitted (within 30 days), in terms of average accuracy (AC). The variables with the greatest discriminating power were age, comorbidity, reasons for consultation, social factors, and drug treatments.

Conclusions: It is possible to predict readmissions in stratified groups with high accuracy and to identify the most important factors influencing the event. Therefore, it will be possible to develop interventions to improve the quality of care provided to ED patients.

No MeSH data available.


Related in: MedlinePlus

Ordered by their importance, the 20 variables with the greatest predictive value for readmission in the heart failure group.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4664798&req=5

fig2: Ordered by their importance, the 20 variables with the greatest predictive value for readmission in the heart failure group.

Mentions: Figures 1–4 show, in decreasing order of importance, the 20 variables with the greatest predictive value for readmissions for each of the stratification groups (CM, HF, COPD, and DM). It is worth noting that there is a relatively small overlap between the sets of variables with significant differences and those with the greatest power for discriminating between readmitted and nonreadmitted patients. For example, in the CM group (Figure 1), only age and medication reconciliation appear in both sets. The variables with the greatest discriminating power were age, comorbidity, reasons for consultation, social factors, and drug treatments.


Risk Factors for Emergency Department Short Time Readmission in Stratified Population.

Besga A, Ayerdi B, Alcalde G, Manzano A, Lopetegui P, Graña M, González-Pinto A - Biomed Res Int (2015)

Ordered by their importance, the 20 variables with the greatest predictive value for readmission in the heart failure group.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4664798&req=5

fig2: Ordered by their importance, the 20 variables with the greatest predictive value for readmission in the heart failure group.
Mentions: Figures 1–4 show, in decreasing order of importance, the 20 variables with the greatest predictive value for readmissions for each of the stratification groups (CM, HF, COPD, and DM). It is worth noting that there is a relatively small overlap between the sets of variables with significant differences and those with the greatest power for discriminating between readmitted and nonreadmitted patients. For example, in the CM group (Figure 1), only age and medication reconciliation appear in both sets. The variables with the greatest discriminating power were age, comorbidity, reasons for consultation, social factors, and drug treatments.

Bottom Line: The variables with the greatest discriminating power were age, comorbidity, reasons for consultation, social factors, and drug treatments.It is possible to predict readmissions in stratified groups with high accuracy and to identify the most important factors influencing the event.Therefore, it will be possible to develop interventions to improve the quality of care provided to ED patients.

View Article: PubMed Central - PubMed

Affiliation: Emergency Department, Álava University Hospital, 01010 Vitoria, Spain ; Biomedical Research Networking Center in Mental Health (CIBERSAM), 10001 Madrid, Spain ; Faculty of Medicine, University of the Basque Country (UPV/EHU), 01010 Vitoria, Spain.

ABSTRACT

Background: Emergency department (ED) readmissions are considered an indicator of healthcare quality that is particularly relevant in older adults. The primary objective of this study was to identify key factors for predicting patients returning to the ED within 30 days of being discharged.

Methods: We analysed patients who attended our ED in June 2014, stratified into four groups based on the Kaiser pyramid. We collected data on more than 100 variables per case including demographic and clinical characteristics and drug treatments. We identified the variables with the highest discriminating power to predict ED readmission and constructed classifiers using machine learning methods to provide predictions.

Results: Classifier performance distinguishing between patients who were and were not readmitted (within 30 days), in terms of average accuracy (AC). The variables with the greatest discriminating power were age, comorbidity, reasons for consultation, social factors, and drug treatments.

Conclusions: It is possible to predict readmissions in stratified groups with high accuracy and to identify the most important factors influencing the event. Therefore, it will be possible to develop interventions to improve the quality of care provided to ED patients.

No MeSH data available.


Related in: MedlinePlus