Targeted quality measurement of health care providers

Assessing the quality of cancer care administered by US health providers presents challenges due to significant heterogeneity in patient populations. Patients undergoing oncology treatment exhibit considerable variation in disease presentation and other crucial characteristics. In this article, we present a framework for institutional quality measurement that addresses this heterogeneity. Our framework follows recent advancements in health outcomes research, conceptualizing quality measurement as a causal inference problem. We use flexible covariate profiles to target specific patient populations and propose methods that progressively integrate weighting and regression modelling. This approach reduces model extrapolation and allows for provider effect modification. We highlight the practical utility of weighting methods that generate stable weights when covariate overlap is limited and alert investigators when case-mix adjustments are infeasible without extrapolation beyond observed data. In our study of cancer-care outcomes, we assess the performance of oncology practices for different profiles that correspond to important types of patients who may receive cancer care. We describe how the methods examined may be particularly important for high-stakes quality measurement, such as public reporting or performance-based payments. These methods have the potential to help inform individual patient health care decisions and contribute to progress toward more personalized quality measurement.