Leveraging the E-commerce Footprint for the Analytics of Healthcare Utilization

Abstract

The utilization of healthcare services serves as a barometer for current and future health outcomes. Even in countries with modern healthcare IT infrastructure, however, fragmentation and interoperability issues hinder the (short-term) monitoring of utilization, forcing policymakers to rely on secondary data sources, such as surveys. This deficiency may be particularly problematic during public health crises, when ensuring proper and timely access to healthcare acquires special importance. This article provides evidence suggesting that online pharmacies' digital footprint data may contain a strong signal of healthcare utilization. Our analysis takes advantage of the scenario created by first wave of the Covid-19 pandemic in China, where the virus' spread lead to pervasive and deep reductions of utilization. Relying on a large sample of online pharmacy transactions with full national coverage, we first detect variation that is strongly consistent with the anatomy of utilization reductions across geographies and over time. Such heterogeneous variations across drug classes are consistent with the survey-reported variability of reductions in cross-specialty care. We then validate our claims by contrasting online pharmacy variation against credit-card transactions for medical services. A machine learning prediction exercise based on a random-forests model illustrates that the addition of predictors based on online pharmacy activity significantly improves estimation accuracy. Together, our results suggest that incorporating online pharmacy activity data could advance the analytics of healthcare utilization monitoring.

Note: Funding: None.

Conflict of Interest: None declared

Keywords: Healthcare, Online Drug Retailing, Digital Footprint, Differences-In-Differences-In-Differences

JEL Classification: I1, I14, I18, M3, L3, D60, L86