Journal of clinical monitoring and computing
-
J Clin Monit Comput · Oct 2024
Observational StudyCentral venous pressure waveform analysis during sleep/rest: a novel approach to enhance intensive care unit post-extubation monitoring of extubation failure.
This pilot study aimed to investigate the relation between cardio-respiratory parameters derived from Central Venous Pressure (CVP) waveform and Extubation Failure (EF) in mechanically ventilated ICU patients during post-extubation period. This study also proposes a new methodology for analysing these parameters during rest/sleep periods to try to improve the identification of EF. We conducted a prospective observational study, computing CVP-derived parameters including breathing effort, spectral analyses, and entropy in twenty critically ill patients post-extubation. ⋯ We also identified a possible improvement in the differentiation between the two groups of patients when assessed during rest/sleep states. Although with caveats regarding the sample size, the results of this pilot study may suggest that CVP-derived cardio-respiratory parameters are valuable for monitoring respiratory failure during post-extubation, which could aid in managing non-invasive interventions and possibly reduce the incidence of EF. Our findings also indicate the possible importance of considering sleep/rest state when assessing cardio-respiratory parameters, which could enhance respiratory failure detection/monitoring.
-
J Clin Monit Comput · Oct 2024
Predictive value of TCCD and regional cerebral oxygen saturation for detecting early postoperative brain injury.
This study aims to analyze the risk factors for early postoperative brain injury in patients undergoing cardiovascular surgery and explore the predictive value of transcranial color Doppler (TCCD) and regional cerebral oxygen saturation (rSO2) for detecting early postoperative brain injury in cardiovascular surgery patients. ⋯ The decreased rSO2 and cerebral blood flow levels, aorta occlusion time, and history of atrial fibrillation were independent risk factors for early postoperative brain injury. TCCD and rSO2 could effectively monitor brain metabolism and cerebral blood flow and predict early postoperative brain injury.
-
Prediction and avoidance of intraoperative hypotension (IOH) can lead to less postoperative morbidity. Machine learning (ML) is increasingly being applied to predict IOH. We hypothesize that incorporating demographic and physiological features in an ML model will improve the performance of IOH prediction. ⋯ The multivariate model yielded average AUC = 0.97 in the static context of a single prediction made up to 8 min before a possible IOH event, and it outperformed a univariate model based on MAP-only (average AUC = 0.83). The MMV model demonstrated AUC = 0.96, PPV = 0.89, and NPV = 0.98 within the challenging context of a dynamic sliding window across 40 min prior to a possible IOH event. We present a novel ML model to predict IOH with a distinctive "dial" on sensitivity and specificity to predict first IOH episode during liver resection surgeries.
-
J Clin Monit Comput · Sep 2024
ReviewA review of machine learning methods for non-invasive blood pressure estimation.
Blood pressure is a very important clinical measurement, offering valuable insights into the hemodynamic status of patients. Regular monitoring is crucial for early detection, prevention, and treatment of conditions like hypotension and hypertension, both of which increasing morbidity for a wide variety of reasons. ⋯ Non-invasive techniques, in contrast, reduce these risks and can provide intermittent or continuous blood pressure readings. This review explores modern machine learning-based non-invasive methods for blood pressure estimation, discussing their advantages, limitations, and clinical relevance.
-
J Clin Monit Comput · Sep 2024
An accelerometry and gyroscopy-based system for detecting swallowing and coughing events.
Measuring spontaneous swallowing frequencies (SSF), coughing frequencies (CF), and the temporal relationships between swallowing and coughing in patients could provide valuable clinical insights into swallowing function, dysphagia, and the risk of pneumonia development. Medical technology with these capabilities has potential applications in hospital settings. In the management of intensive care unit (ICU) patients, monitoring SSF and CF could contribute to predictive models for successful weaning from ventilatory support, extubation, or tracheal decannulation. ⋯ SSF, CF and the temporal relationship between swallowing and coughing are parameters that could have value as predictive tools for diagnosis and therapeutic guidance. Based on 2 tri-axial accelerometry and gyroscopic sensors, a model was developed with an acceptable sensitivity and precision for the detection of swallowing and coughing movements. Also due to simplicity and robustness of the set-up, the model is promising for further scientific research in a wide range of clinical indications.