Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Multi-scale multi-object semi-supervised consistency learning for ultrasound image segmentation.
Neural Netw
December 2024
Department of Mechanical Engineering, National University of Singapore, 9 Engineering Drive 1, Singapore 117575, Singapore. Electronic address:
Manual annotation of ultrasound images relies on expert knowledge and requires significant time and financial resources. Semi-supervised learning (SSL) exploits large amounts of unlabeled data to improve model performance under limited labeled data. However, it faces two challenges: fusion of contextual information at multiple scales and bias of spatial information between multiple objects.
View Article and Find Full Text PDFComparison between AI and human expert performance in acute pain assessment in sheep.
Sci Rep
January 2025
Department of Information Systems, University of Haifa, Haifa, Israel.
This study explores the question whether Artificial Intelligence (AI) can outperform human experts in animal pain recognition using sheep as a case study. It uses a dataset of N = 48 sheep undergoing surgery with video recordings taken before (no pain) and after (pain) surgery. Four veterinary experts used two types of pain scoring scales: the sheep facial expression scale (SFPES) and the Unesp-Botucatu composite behavioral scale (USAPS), which is the 'golden standard' in sheep pain assessment.
View Article and Find Full Text PDF"We are doing it together, don't worry" - A qualitative study on the implementation of electronic medical records in German hospitals.
Z Evid Fortbild Qual Gesundhwes
January 2025
Institute of Medical Sociology, Health Services Research, and Rehabilitation Science, Faculty of Human Sciences & Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.
Background: The ongoing implementation of electronic medical records (EMRs) in German hospitals is currently slow. Implementation science widely acknowledges the barriers and facilitators to implementation. Thus, specific preconditions are necessary to address the former and to support an effective EMR implementation.
View Article and Find Full Text PDFpyAKI-An open source solution to automated acute kidney injury classification.
PLoS One
January 2025
Department of Anaesthesiology, Intensive Care and Pain Medicine, University Hospital Müunster, Müunster, Germany.
Article Synopsis
- Acute kidney injury (AKI) affects a significant number of critically ill patients, with the lack of standardized tools for implementing KDIGO criteria creating challenges for researchers.
- The pyAKI pipeline was developed to address these issues, using the MIMIC-IV database to establish a standardized model for consistent AKI diagnosis.
- Validation tests showed that pyAKI performs better than human annotations, achieving perfect accuracy and offering a valuable resource for clinicians and data scientists in AKI research.
Introduction: Out-of-hospital cardiac arrest (OHCA) is a critical condition associated with high mortality rates and neurological impairment among survivors. In comatose OHCA patients who achieve return of spontaneous circulation, early risk stratification is important to inform treatment pathways and potentially improve outcomes. A range of prognostic tools have been developed to predict survival and neurological recovery.
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!