ABSTRACT
Objective: Common data models provide a standard means of describing data for artificial intelligence (AI) applications, but this process has never been undertaken for medications used in the intensive care unit (ICU). We sought to develop a common data model (CDM) for ICU medications to standardize the medication features needed to support future ICU AI efforts. Materials and Methods: A 9-member, multi-professional team of ICU clinicians and AI experts conducted a 5-round modified Delphi process employing conference calls, web-based communication, and electronic surveys to define the most important medication features for AI efforts. Candidate ICU medication features were generated through group discussion and then independently scored by each team member based on relevance to ICU clinical decision-making and feasibility for collection and coding. A key consideration was to ensure the final ontology both distinguished unique medications and met Findable, Accessible, Interoperable, and Reusable (FAIR) guiding principles. Results: Using a list of 889 ICU medications, the team initially generated 106 different medication features, and 71 were ranked as being core features for the CDM. Through this process, 106 medication features were assigned to 2 key feature domains: drug product-related (n = 43) and clinical practice-related (n = 63). Each feature included a standardized definition and suggested response values housed in the electronic data library. This CDM for ICU medications is available online. Conclusion: The CDM for ICU medications represents an important first step for the research community focused on exploring how AI can improve patient outcomes and will require ongoing engagement and refinement.
ABSTRACT
BACKGROUND AND OBJECTIVES: The appropriate loading dose strategy for phenytoin/fosphenytoin in overweight patients is unknown. A small pharmacokinetic study indicated that overweight patients have a higher volume of distribution and potentially would benefit from using adjusted body weight (AdjBW) instead of actual body weight (ABW) to calculate the loading dose. The purpose of this study was to determine the optimal loading dose strategy of phenytoin in patients whose ABW is greater than 120% of their ideal body weight (IBW) using either ABW or AdjBW for calculation of the loading dose. METHODS: This was a single center, retrospective study which included patients who received a loading dose of phenytoin of at least 10 mg/kg based on ABW, had a phenytoin level drawn <6 h after the end of the dose, and weighed ≥120% of their IBW. Patients were excluded if they received intramuscular phenytoin or fosphenytoin or were prescribed phenytoin prior to the loading dose. Patients were divided into two groups, those who were dosed using their AdjBW versus those dosed using ABW. The primary outcome was achievement of therapeutic phenytoin level of 10-20 mcg/mL. Secondary outcomes included achievement of a subtherapeutic or supratherapeutic level. RESULTS: A total of 195 patients (128 in AdjBW group and 67 in ABW group) met criteria for inclusion. Patients in the AdjBW group weighed more (96.2 kg vs. 91.2 kg, p = 0.04) and received a lower dose in milligrams (1364 vs. 1760, p < 0.0001) and in mg/kg of ABW (14.2 vs. 19.3, p < 0.0001). The primary outcome was achieved in 74% of patients in the AdjBW group and 57% of patients in the ABW group (p = 0.02). Patients in the ABW group were more likely to have a supratherapeutic level (43% vs. 22%, p = 0.003), although adverse reactions did not differ between the groups. DISCUSSION: Patients weighing >120% of their IBW (average body mass index 33.5 kg/m2) who received a 20 mg/kg loading dose based on AdjBW were more likely to achieve a therapeutic phenytoin concentration compared to those dosed based on ABW. Further research is needed to correlate this finding with clinical outcomes, such as resolution of status epilepticus.
