Partitioning Stroke Patients, Determining Related Factors, and Comparing Derived Clusters Based on 12-Month Health Outcomes

Background: (i) Cluster analysis and partitioning samples based on cardio-cerebrovascular histories and length of stay (LOS); (ii) Determining related demographic and medical factors in individual clusters; and (iii) Comparing clusters based on 12-month health outcomes. Methods: The statistical population of the study included 2,293 stroke patients hospitalized in Imam Reza hospital of Kermanshah city from January 1, 2015, to December 31, 2016. After a one-year follow-up, the data collection window was closed on December 31, 2017. The patients’ data were extracted from the electronic hospital information system (HIS). Two-step cluster analysis (TSCA), chi-square, Fisher exact, Kruskal-Wallis, and Mann-Whitney U tests, as well as multinomial logistic regression analysis were the analysis methods. Results: This model suggested five distinct clusters: the patients (i) without any cardio-cerebrovascular history and LOS = 5 days (36.2%); (ii) without any cardio-cerebrovascular history and LOS = 6 days (21.6%); (iii) with cerebrovascular history and LOS = 6 days (18.6%); (iv) with cardiovascular history and LOS = 6 days (16.1%); and (v) with cardio-cerebrovascular history and LOS = 6 days (7.5%). Hypertension, diabetes, and smoking were respectively the most significant modifiable risk factors, while sex, cerebrovascular diseases in the family, and age were respectively the most significant non-modifiable risk factors in high-risk clusters and LOS = 6 days. Compared to Cluster 1 (reference), during a one-year follow-up, a larger number of members in Clusters 3 and 5 were readmitted and/or expired. Conclusion: Considering the modifiable risk factors identified in the current study, providing programs for preventing readmission and potential death caused by stroke for Clusters 3 and 5 seems essential.