Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Oct 14, 2021
Date Accepted: Feb 6, 2022
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Exploring patient multimorbidity and complexity using health insurance claims data: a cluster analysis approach
ABSTRACT
Background:
Although the trend of progressing morbidity is widely recognized, there are numerous challenges regarding the best ways to estimate multimorbidity and patients’ complexity. For multimorbid and/or complex patients, prone to fragmented care and high healthcare utilization, novel estimation approaches are to be developed.
Objective:
To investigate patient multimorbidity and complexity of Swiss residents aged 50+, using clustering methodology in claims data
Methods:
We adopted a clustering methodology based on Random Forests and used 34 pharmacy-cost groups as the only input feature for the procedure. To detect clusters, we applied Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The reasonable hyper-parameters were chosen based on various metrics embedded in the algorithms (out-of-bag misclassification error, normalized stress and cluster persistence), and the clinical relevance of the obtained clusters.
Results:
We adopted a clustering methodology based on Random Forests and used 34 pharmacy-cost groups as the only input feature for the procedure. To detect clusters, we applied Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). The reasonable hyper-parameters were chosen based on various metrics embedded in the algorithms (out-of-bag misclassification error, normalized stress and cluster persistence), and the clinical relevance of the obtained clusters.
Conclusions:
Our study demonstrated that cluster analysis based on pharmacy-cost group information from claims based data is feasible and highlights clinically relevant clusters. Such an approach allows expanding the understanding of multimorbidity beyond simple disease counts and can classify the population into distinct groups with unique healthcare utilization. This study may foster the development of integrated and coordinated care, which is high on the agenda in policymaking, care planning and delivery. Clinical Trial: NA
Citation
