Agreement and Reliability Analysis of Machine Learning Scaling and Wireless Monitoring in the Assessment of Acute Proximal Weakness by Experts and Non-Experts: A Feasibility Study

Assessing the symptoms of proximal weakness caused by neurological deficits requires the knowledge and experience of neurologists. Recent advances in machine learning and the Internet of Things have resulted in the development of automated systems that emulate physicians’ assessments. The application of those systems requires not only accuracy in the classification but also reliability regardless of users’ proficiency in the real environment for the clinical point-of-care and the personalized health management. This study provides an agreement and reliability analysis of using a machine learning-based scaling of Medical Research Council (MRC) proximal scores to evaluate proximal weakness by experts and non-experts. The system trains an ensemble learning model using the signals from sensors attached to the limbs of patients in a neurological intensive care unit. For the agreement analysis, we investigated the percent agreement of MRC proximal scores and Bland-Altman plots of kinematic features between the expert- and non-expert scaling. We also analyzed the intra-class correlation coefficients (ICCs) of kinematic features and Krippendorff’s alpha of the observers’ scaling for the reliability analysis. The mean percent agreement between the expert- and the non-expert scaling was 0.542 for manual scaling and 0.708 for autonomous scaling. The ICCs of kinematic features measured using sensors ranged from 0.742 to 0.850, whereas the Krippendorff’s alpha of manual scaling for the three observers was 0.275. The autonomous assessment system can be utilized by the caregivers, paramedics, or other observers during an emergency to evaluate acute stroke patients.

The First 24 h Hemodynamic Management in NICU after Revascularization Surgery in Moyamoya Disease

Objective. To evaluate whether hemodynamic factors are risk factors for prognosis in moyamoya disease (MMD). Materials and Methods. The retrospective study reviewed a single-center MMD cohort in Huashan Hospital from August 2017 to January 2020. Stroke events in 30 days and follow-up modified Rankin Scale (mRS) grade were recorded. Systematic assessments with perioperative mean arterial pressure (MAP), red blood cell (RBC) parameters, and fluid management were also conducted. Logistic regressions were applied to evaluate the predictors of worse outcomes. Data was analyzed using SPSS 24.0. Results. Admission to neurological intensive care unit (NICU) totalled about 347 after revascularization surgery. The result showed that the higher the postoperative MAP level (favorable group 95.7 ± 11.4 mmHg vs. unfavorable group 103.6 ± 10.4 mmHg, p < 0.001 ) and the greater the MAP variability (favorable group 0.26 ± 13.2 vs. unfavorable group 7.2 ± 13.5 , p = 0.006 ) were, the higher the patient’s follow-up mRS grade was. What is more, a higher early postoperative Hb level also seemed to predict a worse long-term clinical outcome (favorable group 116.9 ± 17.1 g/L vs. unfavorable group 123.7 ± 13.0 g/L, p = 0.03 ), but the difference disappeared after adjusting sex and age. Logistic regression analyses showed that a higher level of postoperative MAP ( β = 0.024 , 95% CI (0.004, 0.044), and p = 0.02 ) within the first 24 h in NICU might be the short-term risk factor. For long-term outcome, a higher level ( β = 1.058 , 95% CI (1.022, 1.096), and p = 0.001 ) and a greater variability ( β = 30.982 , 95% CI (2.112, 454.414), and p = 0.01 ) of postoperative MAP might be the negative predictors of mRS grade. Conclusions. The early postoperative hemodynamic management might be extremely critical for patients with MMD. Both high postoperative MAP levels and large MAP variability might affect the prognosis. What is more, we also found that a higher postoperative Hb level might be related with a worse outcome.

Glycemic Control in Neurological Intensive Care Unit Patients

Critically ill patients often develop hyperglycemia because of the metabolic response to trauma and stress. In response to any form of damage to the organism, it reacts by increasing its own glucose production which subsequently causes hyperglycemia. This adaptive reaction of the organism is directed to aid in the rapid restoration after the damage. Therefore, glucose is an indispensable substrate in the critically ill which aids the reparation process. Severe and persistent hyperglycemia is associated with unfavorable outcomes and is considered to be an independent predictor of in-hospital mortality. The discussion remains on whether hyperglycemia is just a marker of increased stress which makes it a surrogate indicator of disease severity or if it is the reason for the unfavorable outcome. A few years ago, several published articles suggested that a tight glycemic control within the normal range improves treatment outcome. Over time, researchers have changed their point of view and currently there is a discussion on this matter in the scientific literatures. At the same time, the question of what glycemic level should be maintained for patients in the Neurological Intensive Care Unit is a matter of discussion. In this review, the authors analyzed the latest guidelines on treatment of critical patients with neurosurgical and neurological pathologies, specifically the glycemic control in this category of patients.

Nurses: The Missing Link in Continuous Electroencephalogram Monitoring?

The last decade has been marked by the advent of continuous EEG (cEEG) monitoring, which is now recommended as the standard of care in numerous medical conditions seen in the neurological intensive care unit (ICU).1, 2 In clinical practice, its main indications are seizure detection, treatment monitoring, and prognostication in various conditions such as seizures/status epilepticus, ischemic stroke, subarachnoid hemorrhage, intracerebral hemorrhage, traumatic brain injury, brain tumor, encephalitis/sepsis-associated encephalopathy, extracorporeal membrane oxygenation, targeted temperature management, and cardiac arrest.2, 3

Standardized Endoscopic Swallowing Evaluation for Tracheostomy Decannulation in Critically Ill Neurologic Patients – a prospective evaluation

Background Removal of a tracheostomy tube in critically ill neurologic patients is a critical issue during intensive care treatment, particularly due to severe dysphagia and insufficient airway protection. The “Standardized Endoscopic Evaluation for Tracheostomy Decannulation in Critically Ill Neurologic Patients” (SESETD) is an objective measure of readiness for decannulation. This protocol includes the stepwise evaluation of secretion management, spontaneous swallowing, and laryngeal sensitivity during fiberoptic endoscopic evaluation of swallowing (FEES). Here, we first evaluated safety and secondly effectiveness of the protocol and sought to identify predictors of decannulation success and decannulation failure. Methods A prospective observational study was conducted in the neurological intensive care unit at Münster University Hospital, Germany between January 2013 and December 2017. Three hundred and seventy-seven tracheostomized patients with an acute neurologic disease completely weaned from mechanical ventilation were included, all of whom were examined by FEES within 72 h from end of mechanical ventilation. Using regression analysis, predictors of successful decannulation, as well as decannulation failure were investigated. Results Two hundred and twenty-seven patients (60.2%) could be decannulated during their stay according to the protocol, 59 of whom within 24 h from the initial FEES after completed weaning. 3.5% of patients had to be recannulated due to severe dysphagia or related complications. Prolonged mechanical ventilation showed to be a significant predictor of decannulation failure. Lower age was identified to be a significant predictor of early decannulation after end of weaning. Transforming the binary SESETD into a 4-point scale helped predicting decannulation success in patients not immediately ready for decannulation after the end of respiratory weaning (optimal cutoff ≥1; sensitivity: 64%, specifity: 66%). Conclusions The SESETD showed to be a safe and efficient tool to evaluate readiness for decannulation in our patient collective of critically ill neurologic patients.