Journal of clinical monitoring and computing
-
J Clin Monit Comput · Apr 2024
Early prediction of mortality at sepsis diagnosis time in critically ill patients by using interpretable machine learning.
This study applied machine learning for the early prediction of 30-day mortality at sepsis diagnosis time in critically ill patients. Retrospective study using data collected from the Medical Information Mart for Intensive Care IV database. The data of the patient cohort was divided on the basis of the year of hospitalization, into training (2008-2013), validation (2014-2016), and testing (2017-2019) datasets. 24,377 patients with the sepsis diagnosis time < 24 h after intensive care unit (ICU) admission were included. ⋯ The calibration plot for the model revealed a slope of 1.03 (95% CI 0.94-1.12) and intercept of 0.14 (95% CI 0.04-0.25). The SHAP revealed the top three most significant features, namely age, increased red blood cell distribution width, and respiratory rate. Our study demonstrated the feasibility of using the interpretable machine learning model to predict mortality at sepsis diagnosis time.
-
J Clin Monit Comput · Apr 2024
Optic nerve sheath diameter measurement for prediction of postdural puncture headache.
Intracranial hypotension due to cerebrospinal fluid leak is mainly the causal factor for the pathophysiology of postdural puncture headache (PDPH). In this study, we aimed to evaluate the effectiveness of optic nerve sheath diameter (ONSD) measurement in predicting the development of PDPH in patients undergoing spinal anesthesia. ⋯ The difference between the ONSD values measured before and after spinal anesthesia may be an important parameter for predicting the risk of PDPH development.
-
J Clin Monit Comput · Apr 2024
Observational StudyAssessment of changes in blood volume during lower body negative pressure-induced hypovolemia using bioelectrical impedance analysis.
Lower body negative Pressure (LBNP)-induced hypovolemia is simulating acute hemorrhage by sequestrating blood into lower extremities. Bioelectrical Impedance Analysis (BIA) is based on the electrical properties of biological tissues, as electrical current flows along highly conductive body tissues (such as blood). Changes in blood volume will lead to changes in bioimpedance. This study aims to study changes in upper (UL) and lower (LL) extremities bioimpedance during LBNP-induced hypovolemia. ⋯ During LBNP-induced hypovolemia, there were reciprocal changes in UL&LL bioimpedance. These changes reflected hemodynamic compensatory mechanisms to hypovolemia.
-
J Clin Monit Comput · Apr 2024
Racial effects on masimo pulse oximetry: impact of low perfusion index.
Evaluate the SpO2-SaO2 difference between Black and White volunteer subjects having a low perfusion index (Pi) compared to those having a normal Pi. ⋯ Masimo SET® pulse oximeters with RD SET® sensors are accurate for individuals of both Black and White races when Pi is normal, as well as during conditions when Pi is low. The ARMS for all conditions studied is well within FDA standards. This study was conducted in healthy volunteers during well-controlled laboratory desaturations, and results could vary under certain challenging clinical conditions.
-
J Clin Monit Comput · Apr 2024
Pressure-adjusted venting eliminates start-up delays and compensates for vertical position of syringe infusion pumps used for microinfusion.
Microinfusions are commonly used for the administration of catecholamines, but start-up delays pose a problem for reliable and timely drug delivery. Recent findings show that venting of the syringe infusion pump with draining of fluid to ambient pressure before directing the flow towards the central venous catheter does not counteract start-up delays. With the aim to reduce start-up delays, this study compared fluid delivery during start-up of syringe infusion pumps without venting, with ambient pressure venting, and with central venous pressure (CVP)-adjusted venting. ⋯ At 360 s after start-up 72% to 92% of expected fluid volumes were delivered without venting, 46% to 82% with ambient pressure venting and 96% to 99% with CVP-adjusted venting. CVP-adjusted venting demonstrated consistent results across vertical pump placements (p = 0.485), whereas the other methods had significant variances (p < 0.001 for both). In conclusion, CVP-adjusted venting effectively eliminates imprecise drug delivery and start-up delays when using microinfusions.