Title:Prediction Model of Early Return to Hospital after Discharge Following Acute Ischemic Stroke
Volume: 16
Issue: 4
Author(s): Jiann-Der Lee, Tsong-Hai Lee, Yen-Chu Huang, Meng Lee, Ya-Wen Kuo, Ya-Chi Huang and Ya-Han Hu*
Affiliation:
- Department of Information Management and Institute of Healthcare Information Management, National Chung Cheng University, Chiayi County,Taiwan
Keywords:
Acute ischemic stroke, readmission, supervised learning, classification and regression tree, data mining, healthcare.
Abstract:
Background: Reducing hospital readmissions for stroke remains a significant challenge
to improve outcomes and decrease healthcare costs.
Methods: We analyzed 10,034 adult patients with ischemic stroke, presented within 24 hours of
onset from a hospital-based stroke registry. The risk factors for early return to hospital after discharge
were analyzed using multivariate logistic regression and classification and regression tree
(CART) analyses.
Results: Among the study population, 277 (2.8%) had 3-day Emergency Department (ED) reattendance,
534 (5.3%) had 14-day readmission, and 932 (9.3%) had 30-day readmission. Multivariate
logistic regression revealed that age, nasogastric tube feeding, indwelling urinary catheter,
healthcare utilization behaviour, and stroke severity were major and common risk factors for an
early return to the hospital after discharge. CART analysis identified nasogastric tube feeding and
length of stay for 72-hour ED reattendance, Barthel Index (BI) score, total length of stay in the
Year Preceding the index admission (YLOS), indwelling urinary catheter, and age for 14-day readmission,
and nasogastric tube feeding, BI score, YLOS, and number of inpatient visits in the
year preceding the index admission for 30-day readmission as important factors to classify the patients
into subgroups.
Conclusion: Although CART analysis did not improve the prediction of an early return to the hospital
after stroke compared with logistic regression models, decision rules generated by CART can
easily be interpreted and applied in clinical practice.
