AI Article Synopsis
- Passive leg raising (PLR) is a conventional method to assess fluid responsiveness in critically ill patients, but its use is often limited due to patient mobilization challenges.
- A study of 100 critically ill patients utilized transthoracic echocardiography (TTE) measurements and machine learning techniques to predict fluid responsiveness based on cardiac function changes.
- The results showed that machine learning models, particularly partial least-squares regression (PLS), were highly effective in predicting fluid responsiveness, offering comparable performance to PLR assessments.
Article Abstract
Background: Passive leg raising (PLR) predicts fluid responsiveness in critical illness, although restrictions in mobilising patients often preclude this haemodynamic challenge being used. We investigated whether machine learning applied on transthoracic echocardiography (TTE) data might be used as a tool for predicting fluid responsiveness in critically ill patients.
Methods: We studied, 100 critically ill patients (mean age: 62 yr [standard deviation: 14]) with severe sepsis or septic shock prospectively over 24 months. Transthoracic echocardiography measurements were performed at baseline, after PLR, and before and after a standardised fluid challenge in learning and test populations (n=50 patients each). A 15% increase in stroke volume defined fluid responsiveness. The machine learning methods used were classification and regression tree (CART), partial least-squares regression (PLS), neural network (NNET), and linear discriminant analysis (LDA). Each method was applied offline to determine whether fluid responsiveness may be predicted from left and right cardiac ventricular physiological changes detected by cardiac ultrasound. Predictive values for fluid responsiveness were compared by receiver operating characteristics (area under the curve [AUC]; mean [95% confidence intervals]).
Results: In the learning sample, the AUC values were PLR 0.76 (0.62-0.89), CART 0.83 (0.73-0.94), PLS 0.97 (0.93-1), NNET 0.93 (0.85-1), and LDA 0.90 (0.81-0.98). In the test sample, the AUC values were PLR 0.77 (0.64-0.91), CART 0.68 (0.54-0.81), PLS 0.83 (0.71-0.96), NNET 0.83 (0.71-0.94), and LDA 0.85 (0.74-0.96) respectively. The PLS model identified inferior vena cava collapsibility, velocity-time integral, S-wave, E/Ea ratio, and E-wave as key echocardiographic parameters.
Conclusions: Machine learning generated several models for predicting fluid responsiveness that were comparable with the haemodynamic response to PLR.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.bja.2020.11.039 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A Droplet Microfluidic Sensor for Point-of-Care Measurement of Plasma/Serum Total Free Thiol Concentrations.
Anal Chem
January 2025
Mechanical Engineering, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton SO17 1BJ, U.K.
Total free thiols are an important marker of the whole-body redox state, which has been shown to be associated with clinical outcome in health and disease. Recent investigations have suggested that increased insight may be gained by monitoring alterations of redox state in response to exercise and hypoxia and to monitor redox trajectories in disease settings. However, conducting such studies is challenging due to the requirement for repeated venous blood sampling and intensive lab work.
View Article and Find Full Text PDFLinking higher amyloid beta 1-38 (Aβ(1-38)) levels to reduced Alzheimer's disease progression risk.
Alzheimers Dement
January 2025
Department of Psychiatry and Neuroscience, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany.
Introduction: The beneficial effects of amyloid beta 1-38, or Aβ(1-38), on Alzheimer's disease (AD) progression in humans in vivo remain controversial. We investigated AD patients' cerebrospinal fluid (CSF) Aβ(1-38) and AD progression.
Methods: Cognitive function and diagnostic change were assessed annually for 3 years in 177 Aβ-positive participants with subjective cognitive decline (SCD), mild cognitive impairment (MCI), and dementia from the German Center for Neurodegenerative Diseases (DZNE) longitudinal cognitive impairment and dementia study (DELCODE) cohort using the Mini-Mental State Examination (MMSE), Preclinical Alzheimer's Cognitive Composite (PACC), Clinical Dementia Rating (CDR), and National Institute of Neurological and Communicative Disorders and Stroke-Alzheimer's Disease and Related Disorders Association (NINCDS-ADRDA) criteria.
Unusual cholesterol crystal formation in a rare clinical case report of splenic echinococcal cyst in a patient from Sardinia, Italy.
Front Parasitol
January 2025
World Organisation for Animal Health (WOAH) and National Reference Laboratory for Echinococcosis, Istituto Zooprofilattico della Sardegna, Sassari, Italy.
Cystic echinococcosis (CE) is a zoonotic disease caused by sensu lato, the metacestode of a tapeworm parasite of high medical importance. Infection of the parasite leads to the development of echinococcal cysts, and the spleen is a rarely infected organ. A 46-year-old woman who was born and who resides in Sardinia, Italy, was referred to the Echinococcosis outpatient clinic at the University Hospital of Sassari (Sardinia, Italy) for a pain in the left flank.
View Article and Find Full Text PDFCerebrospinal fluid (CSF) dynamics, driven by sensory stimulation-induced neuronal activity, is crucial for maintaining homeostasis and clearing metabolic waste. However, it remains unclear whether such CSF flow is impaired in age-related neurodegenerative diseases of the visual system. This study addresses this gap by examining CSF flow during visual stimulation in glaucoma patients and healthy older adults using functional magnetic resonance imaging.
View Article and Find Full Text PDFDevelopment of a Prandtl-Ishlinskii hysteresis model for a large capacity magnetorheological fluid damper.
J Vib Control
January 2025
Department of Mechanical, Industrial and Aerospace Engineering, Concordia University, Montreal, QC, Canada.
Magnetorheological (MR) fluid (MRF) dampers, serving as fail-safe semi-active devices, exhibit nonlinear hysteresis characteristics, emphasizing the necessity for accurate modeling to formulate effective control strategies in smart systems. This paper introduces a novel stop operator-based Prandtl-Ishlinskii (PI) model, featuring a reduced parameter set (seven), designed to estimate the nonlinear hysteresis properties of a large-scale bypass MRF damper with variable stiffness capabilities under varying applied current. With only seven parameters, the model realizes current, displacement, and rate dependencies.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!