Paper ID
1528
Paper Type
short
Description
This study addresses the call to harness big data analytics for more accurate clinical decision making, and is rooted in the context of Congestive Heart Failure (CHF) patients. We aim at identifying CHF patients’ risk levels and disease transitions over time, and present here the clusters that emerged in three consecutive visits. The clusters are classified into five risk levels, based on the mortality rate 30, 90, 180, 365 days post discharge. The primary method was Cluster Evolution Analysis that is able to identify patients’ risk classification, cluster evolution and patients transition over time. The clustering was based on lab results, and we added comorbidities to define the cluster characteristics. A senior cardiologist evaluated the results and stated that the fine clustering allows more accurate identification of patients’ risk groups, likely to result in an improved clinical decision. For example, three high-risk clusters, identified in visit 1, included between 42 to 53 patients out of ~10,000, which could probably be overlooked otherwise. In the next stage, we will identify disease evolution and patient transition between clusters over time.
Recommended Citation
Ramon-Gonen, Roni; Ben-Assuli, Ofir; Heart, Tsipi; Shlomo, Nir; and Klempfner, Robert, "Cluster Evolution Analysis of Congestive Heart Failure Patients" (2019). ICIS 2019 Proceedings. 3.
https://aisel.aisnet.org/icis2019/is_health/is_health/3
Cluster Evolution Analysis of Congestive Heart Failure Patients
This study addresses the call to harness big data analytics for more accurate clinical decision making, and is rooted in the context of Congestive Heart Failure (CHF) patients. We aim at identifying CHF patients’ risk levels and disease transitions over time, and present here the clusters that emerged in three consecutive visits. The clusters are classified into five risk levels, based on the mortality rate 30, 90, 180, 365 days post discharge. The primary method was Cluster Evolution Analysis that is able to identify patients’ risk classification, cluster evolution and patients transition over time. The clustering was based on lab results, and we added comorbidities to define the cluster characteristics. A senior cardiologist evaluated the results and stated that the fine clustering allows more accurate identification of patients’ risk groups, likely to result in an improved clinical decision. For example, three high-risk clusters, identified in visit 1, included between 42 to 53 patients out of ~10,000, which could probably be overlooked otherwise. In the next stage, we will identify disease evolution and patient transition between clusters over time.