How Continuity in Service Impacts Process Variability: Evidence from a Primary Care Setting

Publication Date



Variability plays an important role in service operations, where customers repeatedly interact with service providers. This raises three vital questions for service design. First, how critical is the process variability in determining outcomes? Second, how much of a role does continuity in service play in managing this variability? Third, since customers are an integral part of any service, what can they do to mitigate this variability? These questions are particularly important in healthcare services, where patients with chronic conditions visit primary care offices repeatedly. Therefore, we investigate this topic in the context of management of diabetes, a chronic disease. We use a detailed, and comprehensive dataset from the Veterans Health Administration, the largest integrated healthcare delivery system in the United States, which permits us to control for potential sources of heterogeneity. We analyze more than 300,000 patients – over an eleven-year period – who suffer from diabetes, a chronic disease whose successful management requires managing glycemic variability. We use an empirical approach to, first, quantify the relationship between glycemic variability and three important health outcomes: inpatient visits, length of stay, and readmission rate. We then estimate the relationship between continuity of care and glycemic variability. Finally, we estimate the mitigation effects of patients' adherence to medical protocols. We find that glycemic variability is related to worsening of all three outcomes. More importantly, we find that continuity of care is related to reductions in glycemic variability. However, we find that this reduction is not linearly improving in continuity, but rather is U-shaped, although the stationary point after which continuity may be detrimental is fairly high. Additionally, we find that one mechanism through which continuity of care may reduce variability is through a patient's adherence to medical protocols. Our findings are validated by extensive robustness checks and sensitivity analyses. Our paper is of interest to managers as it brings attention to within-individual variability that has received relatively little attention within the operations literature. Identifying the amount of continuity of care to provide and which individuals to prioritize are both of interest to practitioners and policymakers as that can help in designing appropriate policies for staffing and work allocation.

Document Type



Continuity of Care, Healthcare Operations, Learning, Empirical Operations


Business Administration, Management, and Operations




SMU Cox: IT & Operations Management (Topic)