When a patient in a provider network seeks services outside of theircommunity, the community experiences a leakage. Leakage is undesirable as ittypically leads to higher out-of-network cost for patient and increases barrierfor care coordination, which is particularly problematic for Accountable CareOrganization (ACO) as the in-network providers are financially responsible forpatient quality and outcome. We aim to design a data-driven method to identifynaturally occurring provider networks driven by diabetic patient choices, andunderstand the relationship among provider composition, patient composition,and service leakage pattern. We construct a healthcare provider network basedon patients' historical medical insurance claims. A community detectionalgorithm is used to identify naturally occurring communities of collaboratingproviders. Finally, import-export analysis is conducted to benchmark theirleakage pattern and identify further leakage reduction opportunity. The designyields six major provider communities with diverse profiles. Some communitiesare geographically concentrated, while others tend to draw patients withcertain diabetic co-morbidities. Providers from the same healthcare institutionare likely to be assigned to the same community. While most communities havehigh within-community utilization and spending, at 85% and 86% respectively,leakage still persists. Hence, we utilize a metric from import-export analysisto detect leakage, gaining insight on how to minimizing leakage. In conclusion,we identify patient-driven provider organization by surfacing providers whoshare a large number of patients. By analyzing the import-export behavior ofeach identified community using a novel approach and profiling communitypatient and provider composition we understand the key features of having abalanced number of PCP and specialists and provider heterogeneity.
展开▼
