Transforming the electronic health record from a documentation application to an automated diet program for personalizing neonatal nutrition and improving feeding administration safety through process improvement.

Delivering adequate nutrition to preterm and sick neonates is critical for growth. Infants in the neonatal intensive care unit (NICU) require additional calories to supplement feedings for higher metabolic demands. Traditionally, clinicians enter free-text diet orders for a milk technician to formulate recipes, and dietitians manually calculate nutrition components to monitor growth. This daily process is complex and labor intensive with potential for error. Our goal was to develop an electronic health record (EHR)-integrated solution for entering feeding orders with automated nutrition calculations and mixing instructions. The EHR-integrated automated diet program (ADP) was created and implemented at a 52-bed level III academic NICU. The configuration of the parenteral nutrition orderable item within the EHR was adapted to generate personalized milk mixing recipes. Caloric, macronutrient, and micronutrient constituents were automatically calculated and displayed. To enhance administration safety, handwritten milk bottle patient labels were substituted with electronically generated and scannable patient labels. The program was further enhanced by calculating fortifier powder displacement factors to improve mixing precision. Order entry was optimized to allow for more complex mixing recipes and include a preference list of frequently ordered feeds. The EHR-ADP's safeguarded features allowed for catching multiple near-missed feeding administration errors. The NICU preterm neonate cohort had an average of 6-day decrease (P = 0.01) in the length of stay after implementation while maintaining the same weight gain velocity. The EHR-ADP may improve safety and efficiency; further improvements and wider utilization are needed to demonstrate the growth benefits of personalized nutrition.

The potential for leveraging machine learning to filter medication alerts.

OBJECTIVE: To evaluate the potential for machine learning to predict medication alerts that might be ignored by a user, and intelligently filter out those alerts from the user's view. MATERIALS AND METHODS: We identified features (eg, patient and provider characteristics) proposed to modulate user responses to medication alerts through the literature; these features were then refined through expert review. Models were developed using rule-based and machine learning techniques (logistic regression, random forest, support vector machine, neural network, and LightGBM). We collected log data on alerts shown to users throughout 2019 at University of Utah Health. We sought to maximize precision while maintaining a false-negative rate <0.01, a threshold predefined through discussion with physicians and pharmacists. We developed models while maintaining a sensitivity of 0.99. Two null hypotheses were developed: H1-there is no difference in precision among prediction models; and H2-the removal of any feature category does not change precision. RESULTS: A total of 3,481,634 medication alerts with 751 features were evaluated. With sensitivity fixed at 0.99, LightGBM achieved the highest precision of 0.192 and less than 0.01 for the pre-defined maximal false-negative rate by subject-matter experts (H1) (P < 0.001). This model could reduce alert volume by 54.1%. We removed different combinations of features (H2) and found that not all features significantly contributed to precision. Removing medication order features (eg, dosage) most significantly decreased precision (-0.147, P = 0.001). CONCLUSIONS: Machine learning potentially enables the intelligent filtering of medication alerts.

A Pragmatic Guide to Establishing Clinical Decision Support Governance and Addressing Decision Support Fatigue: a Case Study.

There is limited guidance available in the literature for establishing clinical decision support (CDS) governance and improving CDS effectiveness in a pragmatic, resource-efficient manner. Here, we describe how University of Utah Health established enterprise CDS governance in 2015 leveraging existing resources. Key components of the governance include a multi-stakeholder CDS Committee that vets new requests and reviews existing content; a requirement that proposed CDS is actually desired by intended recipients; coordination with other governance bodies; basic data analytics to identify high-frequency, low-value CDS and monitor progress; active solicitation of user issues; the transition of alert and reminder content to other, more appropriate areas in the electronic health record; and the judicious use of experimental designs to guide decision-making regarding CDS effectiveness. In the three years since establishing this governance, new CDS has been continuously added while the overall burden of clinician-facing alerts and reminders has been reduced by 53.8%.