Journal of clinical monitoring and computing
-
J Clin Monit Comput · Apr 2023
A machine learning approach to predicting early and late postoperative reintubation.
Accurate estimation of surgical risks is important for informing the process of shared decision making and informed consent. Postoperative reintubation (POR) is a severe complication that is associated with postoperative morbidity. Previous studies have divided POR into early POR (within 72 h of surgery) and late POR (within 30 days of surgery). ⋯ The scoring systems developed from the logistic regression models demonstrated strong performance in terms of both accuracy and discrimination across the different POR outcomes (Average Brier score, 0.172; Average c-statistic, 0.852). These results were only marginally worse than prediction using the full set of risk variables (Average Brier score, 0.145; Average c-statistic, 0.870). While more work needs to be done to identify clinically relevant differences between the early and late POR outcomes, the scoring systems provided here can be used by surgeons and patients to improve the quality of care overall.
-
Recent publications have suggested that pulse oximeters exhibit reduced accuracy in dark-skinned patients during periods of hypoxemia. Masimo SET® (Signal Extraction Technology®) has been designed, calibrated, and validated using nearly equal numbers of dark and light skinned subjects, with the goal of eliminating differences between pulse oximetry saturation (SpO2) and arterial oxygen saturation (SaO2) values due to skin pigmentation. The accuracy concerns reported in dark-skinned patients led us to perform a retrospective analysis of healthy Black and White volunteers. ⋯ Occult hypoxemia was rare and did not occur in Black subjects. Masimo RD SET® can be used with equal assurance in people with dark or light skin. These laboratory results were obtained in well-controlled experimental conditions in healthy volunteers-not reflecting actual clinical conditions/patients.
-
J Clin Monit Comput · Apr 2023
Development and usage of an anesthesia data warehouse: lessons learnt from a 10-year project.
This paper describes the development and implementation of an anesthesia data warehouse in the Lille University Hospital. We share the lessons learned from a ten-year project and provide guidance for the implementation of such a project. Our clinical data warehouse is mainly fed with data collected by the anesthesia information management system and hospital discharge reports. ⋯ We reported the main concerns and barriers during the development of this project and we provided 8 tips to handle them. We have implemented our data warehouse into the OMOP common data model as a complementary downstream data model. The next step of the project will be to disseminate the use of the OMOP data model for anesthesia and critical care, and drive the trend towards federated learning to enhance collaborations and multicenter studies.
-
J Clin Monit Comput · Apr 2023
Association between intraoperative plantar regional oxygen saturation and acute kidney injury after cardiac surgery.
Acute kidney injury (AKI) is one of the most common complications after cardiac surgery, associated with increased mortality and morbidity. Near-infrared spectroscopy (NIRS) continuously measures regional oxygen saturation(rSO2) in real-time. This exploratory retrospective study aimed to investigate the association between intraoperative plantar rSO2 and postoperative AKI in cardiac surgery patients. ⋯ Independent of MAP, intraoperative plantar rSO2 was associated with AKI after cardiac surgery. However, intraoperative cerebral rSO2 was not associated with AKI. Intraoperative plantar rSO2 monitoring may be helpful in preventing AKI.
-
J Clin Monit Comput · Apr 2023
Quantitative regional cerebral blood flow measurement using near-infrared spectroscopy and indocyanine green in patients undergoing superficial temporal to middle cerebral artery bypass for moyamoya disease: a novel method using a frequency filter.
Measuring regional cerebral blood flow (rCBF) after revascularization for moyamoya disease, as a type of ischemic cerebrovascular disease, is crucial. This study aims to validate our novel technology that combines near-infrared spectroscopy (NIRS) with a frequency filter to extract the arterial component. ⋯ Similar trends were observed for rCBF_S (MD, 3.98 ml/min/100 g; 95% CI, 2.30-5.67 ml/min/100 g on the diseased side; MD, 2.77 ml/min/100 g; 95% CI, 1.09-4.45 ml/min/100 g on the non-diseased side). Intraclass correlations 3 (ICC3s) between rCBF_N and rCBF_S were weak on the diseased side (ICC3, 0.25; 95% CI, -0.03-0.5; p = 0.07) and the non-diseased side (ICC3, 0.24; 95% CI, -0.05-0.5; p = 0.08). rCBF measurements based on this novel method were weakly correlated with rCBF measurements with SPECT.