Evaluation of Provider Clinical Decision Support System Adoption Rates by Patient Race and Sex

BACKGROUND

Clinical decision support (CDS) systems can improve care quality, but their implications for equity remain uncertain. We examined whether provider response to CDS alerts differed by patient race and sex in primary care, and whether differences in alert exposure helped explain any observed variation.

METHODS AND PRINCIPAL FINDINGS

We conducted a retrospective study using EHR data from a New York City academic health system, focusing on alert-based CDS during outpatient primary care. Logistic regression was used to estimate the likelihood of alert engagement by patient race and sex, while adjusting for encounter and provider factors. We used a generalized structural equation model to assess mediation by alert type, decomposing direct and indirect effects of demographics on response.

Direct effects suggest that providers may respond differently to alerts based on patient identity, consistent with interpersonal bias, in which implicit or explicit attitudes shape clinical behavior, and on the context of the visit. Indirect effects highlight disparities in how alerts are assigned across groups, indicating that algorithmic or systemic bias may be embedded within the technology itself. Estimated mediated pathways suggest that even when providers respond uniformly to alerts, unequal exposure can still produce inequitable outcomes.

DISCUSSION

The findings highlight that the type of CDS triggered plays a significant role in differential CDS responses, with provider- and patient-related factors evident in these differences. These findings underscore the need to evaluate not only provider behavior but also the logic and distribution of CDS tools themselves, as both can contribute to disparities in care delivery. Further research should also focus on looking for the potential health impact of the differential response.

AUTHOR SUMMARY

Digital tools meant to standardize care can unintentionally contribute to which patients receiving care. We investigate whether providers’ use of these tools is related to a patient’s identity or influenced by the types of tools provided to them in primary care. Using electronic health record data from a large urban health system, we find that providers’ responses to alerts are shaped not only by patient identity but also by the nature of the alert itself. Direct effects suggest that providers may engage differently with CDS based on patient demographics, indicating potential interpersonal bias. Indirect effects reveal that certain patient groups are more or less likely to receive specific types of alerts, indicating embedded algorithmic or systemic bias. These findings underscore the importance of evaluating both provider behavior and the design of CDS tools when assessing equity in digital health. Even when providers respond consistently, unequal exposure to alerts can produce inequitable outcomes. Our results underscore the need for more transparent and equity-aware CDS design and implementation strategies that consider both human and technological sources of bias.