Drug-drug interactions in Neonatal Intensive Care Units: how to overcome a challenge

Impact of clinical pharmacist-led intervention for drug-related problems in neonatal intensive care unit a randomized controlled trial

Introduction: Drug-related problems (DRPs) incidence is higher in neonatal intensive care units (NICUs), compared to other pediatric wards due to aspects like off-label medications, pharmacokinetic/dynamic variability, or organ dysfunction/immaturity. This study aimed to determine whether and to what extent a clinical pharmacist intervention improves medication safety and prevents DRPs [medication errors (MEs), adverse drug reactions (ADRs), drug-drug interactions (DDIs)]. Methods: A prospective, randomized, double blind, controlled study in NICU-admitted neonates was conducted. NICU patients were randomly assigned to the intervention (clinical pharmacist-led) (IG) or control group (standard care such as clinical diagnosis, pharmacotherapy) (CG). The clinical pharmacist was involved in the IG to identify-prevent-intervene MEs, or identify and monitor ADRs and DDIs. The primary outcome was the number of neonates who developed at least one DRP compared with those seen across IG and CG. Secondary outcomes included length of hospital stay, total number of drugs or DRP type. Results: Neonates were randomly assigned to CG (n = 52) or IG (n = 48). In total, 45%, 42%, and 16% of patients had at least 1 MEs, ADRs, and clinically significant DDIs, respectively. The number of patients with at least 1 ME was 28 (53%) and 17 (35%) in the CG and IG (p>0.05). The median (range) number of ME was higher in CG [1 (0-7)] than in IG [0 (0-4)] (p = 0.003). Applying regression analysis, the CG had 2.849 times more MEs than the IG (p<0.001). Furthermore, the number of patients (CG to IG) with at least one detected ADR or clinical DDI was 19 (36%) to 23 (47%) (p>0.05) and 4 (7%) to 12 (25%), respectively (p = 0.028). Conclusion: Clinical pharmacist availability to systematically and standardized identify, prevent and resolve DRPs among NICU patients is effective. Daily detailed clinical pharmacist observations and interventions enables prevention and monitoring of DRPs. Clinical Trial Registration ClinicalTrials.gov, identifier NCT04899960.

Novel Method for Early Prediction of Clinically Significant Drug-Drug Interactions with a Machine Learning Algorithm Based on Risk Matrix Analysis in the NICU

Aims: Evidence for drug–drug interactions (DDIs) that may cause age-dependent differences in the incidence and severity of adverse drug reactions (ADRs) in newborns is sparse. We aimed to develop machine learning (ML) algorithms that predict DDI presence by integrating each DDI, which is objectively evaluated with the scales in a risk matrix (probability + severity). Methods: This double-center, prospective randomized cohort study included neonates admitted to the neonatal intensive care unit in a tertiary referral hospital during the 17-month study period. Drugs were classified by the Anatomical Therapeutic Chemical (ATC) classification and assessed for potential and clinically relevant DDIs to risk analyses with the Drug Interaction Probability Scale (DIPS, causal probability) and the Lexicomp^® DDI (severity) database. Results: A total of 412 neonates (median (interquartile range) gestational age of 37 (4) weeks) were included with 32,925 patient days, 131 different medications, and 11,908 medication orders. Overall, at least one potential DDI was observed in 125 (30.4%) of the patients (2.6 potential DDI/patient). A total of 38 of these 125 patients had clinically relevant DDIs causing adverse drug reactions (2.0 clinical DDI/patient). The vast majority of these DDIs (90.66%) were assessed to be at moderate risk. The performance of the ML algorithms that predicts of the presence of relevant DDI was as follows: accuracy 0.944 (95% CI 0.888–0.972), sensitivity 0.892 (95% CI 0.769–0.962), F1 score 0.904, and AUC 0.929 (95% CI 0.874–0.983). Conclusions: In clinical practice, it is expected that optimization in treatment can be achieved with the implementation of this high-performance web tool, created to predict DDIs before they occur with a newborn-centered approach.