Acidemia versus hypercapnia and risk for severe intraventricular hemorrhage.

In extremely low birth weight (ELBW) infants, levels of hypercapnia (Paco 2) > 60 mm Hg are considered a risk factor for severe intraventricular hemorrhage (IVH). Since cerebral vasoreactivity depends on arterial pH (apH) rather than Paco 2, we hypothesize that the role of mild-to-moderate hypercapnia (45-60 mm Hg) in the occurrence of severe IVH is modulated by the metabolic component of acid-base status. ELBW infants (n = 580, born < 28 wk gestation, and BW < 1,000 g) were separated into "high-base deficit (BD)" (n = 291) and "low-BD" (n = 289) groups if infants' median BD were > 4 mEq/L or ≤4 mEq/L, respectively. Rates of severe IVH were higher in "high-BD" (16%) than "low-BD" (9%) group. Although adjusted risk for severe IVH increased with higher Paco 2 and higher BD, apH was the sole predictor of severe IVH. In ELBW infants, higher degree of acidemia, rather than hypercapnia per se, during the first 48 hours of life, is associated with higher occurrences of severe IVH.

Mining tasks and task characteristics from electronic health record audit logs with unsupervised machine learning.

OBJECTIVE: The characteristics of clinician activities while interacting with electronic health record (EHR) systems can influence the time spent in EHRs and workload. This study aims to characterize EHR activities as tasks and define novel, data-driven metrics. MATERIALS AND METHODS: We leveraged unsupervised learning approaches to learn tasks from sequences of events in EHR audit logs. We developed metrics characterizing the prevalence of unique events and event repetition and applied them to categorize tasks into 4 complexity profiles. Between these profiles, Mann-Whitney U tests were applied to measure the differences in performance time, event type, and clinician prevalence, or the number of unique clinicians who were observed performing these tasks. In addition, we apply process mining frameworks paired with clinical annotations to support the validity of a sample of our identified tasks. We apply our approaches to learn tasks performed by nurses in the Vanderbilt University Medical Center neonatal intensive care unit. RESULTS: We examined EHR audit logs generated by 33 neonatal intensive care unit nurses resulting in 57 234 sessions and 81 tasks. Our results indicated significant differences in performance time for each observed task complexity profile. There were no significant differences in clinician prevalence or in the frequency of viewing and modifying event types between tasks of different complexities. We presented a sample of expert-reviewed, annotated task workflows supporting the interpretation of their clinical meaningfulness. CONCLUSIONS: The use of the audit log provides an opportunity to assist hospitals in further investigating clinician activities to optimize EHR workflows.