Journal of clinical monitoring and computing
-
J Clin Monit Comput · Oct 2022
Lag times to steady state drug delivery by continuous intravenous infusion: direct comparison of peristaltic and syringe pump performance identifies contributions from infusion system dead volume and pump startup characteristics.
Time lags between the initiation of a continuous drug infusion and achievement of a steady state delivery rate present an important safety concern. At least 3 factors contribute to these time lags: (1) dead volume size, (2) the ratio between total system flow and dead volume, and (3) startup delay. While clinicians employ both peristaltic pumps and syringe pumps to propel infusions, there has been no head-to-head comparison of drug delivery between commercially available infusion pumps with these distinct propulsion mechanisms. ⋯ Startup delay and dead volume in carrier-based infusion systems cause substantial time lags to reaching intended delivery rates. Peristaltic and syringe pumps are similarly susceptible to dead volume effects. Startup performance differed between peristaltic and syringe pumps; their relative performance may be dependent on flow rate.
-
J Clin Monit Comput · Oct 2022
Multicenter StudyPredicting hypoglycemia in critically Ill patients using machine learning and electronic health records.
Hypoglycemia is a common occurrence in critically ill patients and is associated with significant mortality and morbidity. We developed a machine learning model to predict hypoglycemia by using a multicenter intensive care unit (ICU) electronic health record dataset. Machine learning algorithms were trained and tested on patient data from the publicly available eICU Collaborative Research Database. ⋯ The best-performing predictive model was the eXtreme gradient boosting model (XGBoost), which achieved an area under the received operating curve (AUROC) of 0.85, a sensitivity of 0.76, and a specificity of 0.76. The machine learning model developed has strong discrimination and calibration for the prediction of hypoglycemia in ICU patients. Prospective trials of these models are required to evaluate their clinical utility in averting hypoglycemia within critically ill patient populations.