Clinical Decision Support for Surgery: A Mixed Methods Study on Design and Implementation Perspectives From Urologists.

OBJECTIVE: To assess urologist attitudes toward clinical decision support (CDS) embedded into the electronic health record (EHR) and define design needs to facilitate implementation and impact. With recent advances in big data and artificial intelligence (AI), enthusiasm for personalized, data-driven tools to improve surgical decision-making has grown, but the impact of current tools remains limited. METHODS: A sequential explanatory mixed methods study from 2019 to 2020 was performed. First, survey responses from the 2019 American Urological Association Annual Census evaluated attitudes toward an automatic CDS tool that would display risk/benefit data. This was followed by the purposeful sampling of 25 urologists and qualitative interviews assessing perspectives on CDS impact and design needs. Bivariable, multivariable, and coding-based thematic analysis were applied and integrated. RESULTS: Among a weighted sample of 12,366 practicing urologists, the majority agreed CDS would help decision-making (70.9%, 95% CI 68.7%-73.2%), aid patient counseling (78.5%, 95% CI 76.5%-80.5%), save time (58.1%, 95% CI 55.7%-60.5%), and improve patient outcomes (42.9%, 95% CI 40.5%-45.4%). More years in practice was negatively associated with agreement (P <.001). Urologists described how CDS could bolster evidence-based care, personalized medicine, resource utilization, and patient experience. They also identified multiple implementation barriers and provided suggestions on form, functionality, and visual design to improve usefulness and ease of use. CONCLUSION: Urologists have favorable attitudes toward the potential for clinical decision support in the EHR. Smart design will be critical to ensure effective implementation and impact.

Patient Reported vs Claims Based Measures of Health for Modeling Life Expectancy in Men with Prostate Cancer.

PURPOSE: Life expectancy has become a core consideration in prostate cancer care. While multiple prediction tools exist to support decision making, their discriminative ability remains modest, which hampers usage and utility. We examined whether combining patient reported and claims based health measures into prediction models improves performance. MATERIALS AND METHODS: Using SEER (Surveillance, Epidemiology, and End Results)-CAHPS (Consumer Assessment of Healthcare Providers and Systems) we identified men 65 years old or older diagnosed with prostate cancer from 2004 to 2013 and extracted 4 types of data, including demographics, cancer information, claims based health measures and patient reported health measures. Next, we compared the performance of 5 nested competing risk regression models for other cause mortality. Additionally, we assessed whether adding new health measures to established prediction models improved discriminative ability. RESULTS: Among 3,240 cases 246 (7.6%) died of prostate cancer while 631 (19.5%) died of other causes. The National Cancer Institute Comorbidity Index score was associated but weakly correlated with patient reported overall health (p <0.001, r=0.21). For predicting other cause mortality the 10-year area under the receiver operating characteristic curve improved from 0.721 (demographics only) to 0.755 with cancer information and to 0.777 and 0.812 when adding claims based and patient reported health measures, respectively. The full model generated the highest value of 0.820. Models based on existing tools also improved in their performance with the incorporation of new data types as predictor variables (p <0.001). CONCLUSIONS: Prediction models for life expectancy that combine patient reported and claims based health measures outperform models that incorporate these measures separately. However, given the modest degree of improvement, the implementation of life expectancy tools should balance model performance with data availability and fidelity.