Determining pre-procedure fasting alert time using procedural and scheduling data.

Before a medical procedure requiring anesthesia, patients are required to not eat or drink non-clear fluids for 6 h and not drink clear fluids for 2 h. Fasting durations in standard practice far exceed these minimum thresholds due to uncertainties in procedure start time. The aim of this retrospective, observational study was to compare fasting durations arising from standard practice with different approaches for calculating the timepoint at which patients are instructed to stop eating and drinking. Scheduling data for procedures performed in the cardiac catheterization laboratory of an academic hospital in Canada (January 2020 to April 2022) were used. Four approaches utilizing machine learning (ML) and simulation were used to predict procedure start times and calculate when patients should be instructed to start fasting. Median fasting duration for standard practice was 10.08 h (IQR 3.5) for both food and clear fluids intake. The best performing alternative approach, using tree-based ML models to predict procedure start time, reduced median fasting from food/non-clear fluids to 7.7 h (IQR 2) and clear liquids fasting to 3.7 h (IQR 2.4). 97.3% met the minimum fasting duration requirements (95% CI 96.9% to 97.6%). Further studies are required to determine the effectiveness of operationalizing this approach as an automated fasting alert system.

Design Specifications for an Automated System to Deliver Instructions About Preprocedure Fasting.

PURPOSE: Many patients undergoing surgical and other medical procedures requiring sedation or anesthesia receive standardized "no eating or drinking after midnight" instructions. This "standardized" instruction does not change regardless of potential alterations in scheduling that result in significant delays in procedure start times. As a result, the duration of preprocedure fasting often far exceeds recommended requirements. A technological solution that automates the delivery of preprocedure fasting instructions to patients would likely improve the patient experience. The purpose of this study was to determine design specifications for the delivery of notifications to patients as part of an automated system. DESIGN: A qualitative study was conducted with 14 adult participants using the persona-scenario method. METHODS: Participants worked in groups to create realistic but fictitious personas and scenarios that described how individuals like themselves would interact with an automated preprocedure fasting instruction system. Data generated through the development of the scenarios were analyzed to first identify important themes, which were then interpreted into design specifications. FINDINGS: Seven women and seven men, aged 25 to 75, developed 9 persona-scenarios, which captured outpatient and inpatient preprocedure fasting experiences, as well as perspectives of individuals who were not comfortable with technology, or those for which English was not the primary spoken language. Most scenarios described preprocedure fasting instructions delivered by an automated bidirectional short message service system. Two major themes were identified as patient priorities, including: (1) enhancing communication between patients and healthcare providers; and (2) the importance of using simple technology so that a greater number of patients with varying degrees of comfort and capabilities would be able to use the system confidently. A corresponding set of proposed design specifications was devised. CONCLUSIONS: The results of this study provide actionable ways to operationalize patient-centered ideas in the design of an automated preprocedure fasting instruction system.