Pervasive Sensing and AI in Intelligent ICU
Critical IllnessPain2 moreImportant information related to the visual assessment of patients, such as facial expressions, head and extremity movements, posture, and mobility are captured sporadically by overburdened nurses, or are not captured at all. Consequently, these important visual cues, although associated with critical indices such as physical functioning, pain, delirious state, and impending clinical deterioration, often cannot be incorporated into clinical status. The overall objectives of this project are to sense, quantify, and communicate patients' clinical conditions in an autonomous and precise manner, and develop a pervasive intelligent sensing system that combines deep learning algorithms with continuous data from inertial, color, and depth image sensors for autonomous visual assessment of critically ill patients. The central hypothesis is that deep learning models will be superior to existing acuity clinical scores by predicting acuity in a dynamic, precise, and interpretable manner, using autonomous assessment of pain, emotional distress, and physical function, together with clinical and physiologic data.
Machine Learning Ventilator Decision System VS. Standard Controlled Ventilation
Mechanical VentilationCritically Ill PatientsVentilator-induced lung injury is associated with increased morbidity and mortality. Despite intense efforts in basic and clinical research, an individualized ventilation strategy for critically ill patients remains a major challenge. However, an individualized mechanical ventilation approach remains a challenging task: A multitude of factors, e.g., lab values, vitals, comorbidities, disease progression, and other clinical data must be taken into consideration when choosing a patient's specific optimal ventilation regime. The aim of this work was to evaluate the machine learning ventilator decision system, which is able to suggest a dynamically optimized mechanical ventilation regime for critically-ill patients. Compare with standard controlled ventilation, to test whether the clinical application of the machine learning ventilator decision system reduces mechanical ventilation time and mortality.
Albumin To Enhance Recovery After Acute Kidney Injury
Acute Kidney InjuryRenal Replacement Therapy2 moreStudy objectives: To determine whether, in critically ill patients with Acute Kidney Injury requiring renal replacement therapy (AKI-RRT), randomization to receive intravenous hyperoncotic albumin 20-25% (100 mL X two doses) compared to control/placebo normal saline boluses (100 mL X two doses) given during RRT sessions, leads to: An increase in organ support-free days (primary outcome) at 28 days following initiation of RRT; and An increase in RRT-free days (principal secondary outcome) at 28 days following initiation of RRT.
Blender Biomarkers: A BLENDER Sub-study to Evaluate the Effect of Oxygen Dose on Oxidative Stress...
Cardiac FailureCritical IllnessTo compare the impact of liberal vs conservative oxygen doses on markers of oxidative stress in patients enrolled in the BLENDER trial.
Preventing Cardiovascular Collapse With Vasopressors During Tracheal Intubation
Critical IllnessRespiratory FailureTracheal intubation (TI) is associated with a high risk of adverse events in critically ill patients and peri-intubation hemodynamic collapse is the most commonly observed. The primary aim of the PREVENTION trial is to compare the effect of the pre-emptive use of noradrenaline versus no peri-intubation use of noradrenaline on incidence of cardiovascular collapse following TI in adult critically ill patients. Patients with absolute indication or contraindication to vasopressor support will be excluded from this trial. Patients will be randomized 1:1 to a continuous infusion of noradrenaline started before induction titrated according to baseline mean arterial pressure. The primary outcome will be the incidence of cardiovascular collapse. Secondary outcomes will include lowest systolic blood pressure and cardiac arrest within 30 minutes from intubation.
Neurocognitive Outcomes for ICU Patients With Acute Kidney Injury
DeliriumAcute Kidney Injury4 moreIntroduction. Initiation of acute kidney replacement therapy (KRT) is common in critically ill adults admitted to the intensive care unit (ICU), and is associated with increased morbidity and mortality. KRT has been linked to poor neurocognitive outcomes, leading to a reduced quality of life, as well as increased utilization of healthcare resources. Adults initiated on dialysis in the ICU may be particularly at risk of neurocognitive impairment, as survivors of critical illness are already predisposed to developing cerebrovascular disease and cognitive dysfunction over the long-term relative to healthy controls. Regional cerebral oxygen saturation (rSO2) may provide a critical early marker of long-term neurocognitive impairment in patients in this population. The INCOGNITO-AKI study aims to understand cerebral oxygenation in patients undergoing KRT, either continuous or intermittent, in the ICU. These findings will be correlated with long-term cognitive and functional outcomes, as well as structural brain pathology. Methods and analysis. 108 patients scheduled to undergo treatment for acute kidney injury with KRT in the Kingston Health Sciences Centre ICU will be recruited into this prospective observational study. Enrolled patients will be assessed with intradialytic cerebral oximetry using near infrared spectroscopy (NIRS). Delirium will be assessed daily with the Confusion Assessment Method-Intensive Care Unit (CAM-ICU) and delirium severity quantified as cumulative CAM-ICU-7 scores. Neurocognitive impairment will be assessed at 3- and 12-months after hospital discharge using the Kinarm and Repeatable Battery for the Assessment of Neuropsychological Status (RBANS). Structural brain pathology on MRI will also be measured at the same timepoints. Driving safety, adverse events, and medication adherence will be assessed at 12-months to evaluate the impact of neurocognitive impairment on functional outcomes. Ethics and dissemination. This study has been approved by the Queen's University Health Sciences and Affiliated Teaching Hospitals Research Ethics Board (Approval number: DMED-2424-20). Results will be presented at critical care scientific conferences and a lay summary will be provided to patients and families in their preferred format.
The EXCEL Registry of Patients Requiring ECMO
Critically IllAcute Respiratory Failure2 moreECMO is associated with significant costs, risks and requires specialist training and expertise. EXCEL is a novel, high-quality, detailed prospective registry of patients requiring ECMO in Australia and New Zealand. The registry provides information on patient selection, complications, costs and patient reported outcome measures. EXCEL uses the Theoretical Domains Framework to identify evidence-practice gaps and explore barriers and enablers to tailor implementation of evidence
Body Impedance Analysis to Detect ICUAW
Critical IllnessThe aim of the study is to detect a value of muscle and organ mass measured by body impedance analysis and its correlation with the Medical Research Council (MRC) score. An MRC score ≤ 48 is defined as a diagnosis of ICU acquired weakness. The correlation of the values detected by BIA and their transfer to an MRC Score ≤ 48 will be investigated. The knowledge gained will be used for early detection of ICUAW in order to reduce the consequences of the same.
The Effectiveness of Urine mtDNA and Beta 2-MG to Predict Acute Kidney Injury for Critically Ill...
Surgery-ComplicationsAcute Kidney Injury1 more1. Research background Research hypothesis The development of acute kidney injury (AKI) can be predicted using urine mitochondrial deoxyribonucleic acid (UmtDNA), serum and urine beta-2 microglobulin (β2-MG) in critically ill surgical patients Basis of research hypothesis i. Correlation between mitochondria and renal function (Results of previous studies) Mitochondria are involved in development and recovery of diabetic nephropathy. UmtDNA can be used as early marker to detect the development of AKI ※ Mitochondria As an organelle located within the cell, it is an organ that produces energy through adenosine triphosphate (ATP) through cellular oxidative phosphorylation. The kidney has the second most mitochondria after the heart. II. Correlation between elevation of β2-MG and renal function Circulating β2-MG infiltrates the glomerulus and is reabsorbed and metabolized in the proximal tubule of the kidney. Therefore, it increases in the blood due to a decrease in metabolism when renal function is abnormal. ※ Beta 2-microglobulin As the light chain of the class I major histocompatibility antigen, it is a protein distributed in nucleated cells (especially lymphocytes and monocytes) in the body. III. Mechanism of acute kidney injury in critically ill surgical patients Blood flow to the kidneys is reduced due to decreased cardiac output, vasoconstriction due to systemic inflammatory response, hemodynamic changes, and decreased body fluid. This leads to renal tubular injury along with ischemic reperfusion injury. Renal tubular injury increases the permeability of the transition pore that connects the outer and inner mitochondrial membranes, resulting in mitochondrial structural damage and oxidative injury. It causes a decrease of ATP in kidney cells and induces apoptosis of kidney cells. Urine mtDNA, a product of this kidney injury, could be used as a biomarker to predict impairment of renal function in critically ill surgical patients. Serum β2-MG maybe increase due to a decrease of metabolism of β2-MG in AKI.
Exploring Pulse OXimeter Accuracy Across SKin Tones
Critical IllnessHypoxemiaThis study within a trial (SWAT) will be a sub-study of the UK-ROX trial (ISRCTN13384956), which is currently running in intensive care units across the UK. UK-ROX is large-scale randomised controlled trial evaluating conservative oxygen therapy (a target SpO2 of 88-92%) versus usual oxygen therapy in mechanically ventilated adult patients admitted to ICUs in the UK. The purpose of this observational sub-study is to compare pulse oximeter-derived peripheral oxygen saturation (SpO2) values to co-oximeter-derived arterial oxygen saturation (SaO2) measurements from arterial blood gas (ABG) samples, for a range of fingertip pulse oximeters in an ethnically diverse group of adult patients admitted to UK intensive care units (ICUs). Approximately 900 patients will be recruited over 12 month period from 24 sites to provide an anticipated 10,800 paired SpO2 and SaO2 measurements. Patient skin tone will be objectively measured using a handheld spectrophotometer. Data from the sub-study will be used to determine the accuracy of the tested pulse oximeters across a range of skin tones and arterial oxygenation levels.