AI Article Synopsis
- This study looks at how well a special type of computer learning can predict if critically ill patients on ventilators can breathe on their own again.
- The researchers used a large database of patient information and found that a multitask learning system worked better when it focused on certain tasks together.
- Overall, the study showed that using this special learning method helped make better predictions and the researchers also looked at mistakes made by the model to improve it.
Article Abstract
Objective: Weaning is an essential issue in critical care. This study explores the efficacy of multitask learning models in predicting successful weaning in critically ill ventilated patients using the Medical Information Mart for Intensive Care (MIMIC) IV database.
Methods: We employed a multitask learning framework with a shared bottom network to facilitate common knowledge extraction across all tasks. We used the Shapley additive explanations (SHAP) plot and partial dependence plot (PDP) for model explainability. Furthermore, we conducted an error analysis to assess the strength and limitation of the model. Area under receiver operating characteristic curve (AUROC), calibration plot and decision curve analysis were used to determine the performance of the model.
Results: A total of 7758 critically ill patients were included in the analyses, and 78.5% of them were successfully weaned. Multitask learning combined with spontaneous breath trial achieved a higher performance to predict successful weaning compared with multitask learning combined with shock and mortality (area under receiver operating characteristic curve, AUROC, 0.820 ± 0.002 vs 0.817 ± 0.001, < 0.001). We assessed the performance of the model using calibration and decision curve analyses and further interpreted the model through SHAP and PDP plots. The error analysis identified a relatively high error rate among those with low disease severities, including low mean airway pressure and high enteral feeding.
Conclusion: We demonstrated that multitask machine learning increased predictive accuracy for successful weaning through combining tasks with a high inter-task relationship. The model explainability and error analysis should enhance trust in the model.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11459496 | PMC |
| http://dx.doi.org/10.1177/20552076241289732 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Unified Knowledge-Guided Molecular Graph Encoder with multimodal fusion and multi-task learning.
Neural Netw
December 2024
School of Computer Science, Wuhan University, Luojiashan Road, Wuchang District., Wuhan, 430072, Hubei Province, China; Hubei Key Laboratory of Digital Finance Innovation, Hubei University of Economics, No. 8, Yangqiaohu Avenue, Zanglong Island Development Zone, Jiangxia District, Wuhan, 2007, Hubei Province, China. Electronic address:
The remarkable success of Graph Neural Networks underscores their formidable capacity to assimilate multimodal inputs, markedly enhancing performance across a broad spectrum of domains. In the context of molecular modeling, considerable efforts have been made to enrich molecular representations by integrating data from diverse aspects. Nevertheless, current methodologies frequently compartmentalize geometric and semantic components, resulting in a fragmented approach that impairs the holistic integration of molecular attributes.
View Article and Find Full Text PDFA novel generative multi-task representation learning approach for predicting postoperative complications in cardiac surgery patients.
J Am Med Inform Assoc
December 2024
AI for Health Institute, Washington University in St Louis, St Louis, MO 63130, United States.
Objective: Early detection of surgical complications allows for timely therapy and proactive risk mitigation. Machine learning (ML) can be leveraged to identify and predict patient risks for postoperative complications. We developed and validated the effectiveness of predicting postoperative complications using a novel surgical Variational Autoencoder (surgVAE) that uncovers intrinsic patterns via cross-task and cross-cohort presentation learning.
View Article and Find Full Text PDF[A comparative assessment of neurochemical and neurophysiological parameters of cardiac surgery patients who underwent different versions of multitasking cognitive training].
Zh Nevrol Psikhiatr Im S S Korsakova
December 2024
Research Institute for Complex Issues of Cardiovascular Diseases, Kemerovo, Russia.
Objective: To compare biomarkers of neurovascular unit (NVU) - S100β, NSE, BDNF and indicators of the brain electrical activity in patients who underwent coronary artery bypass grafting (CABG) depending on the use of different versions of multi-tasking cognitive training (CT).
Material And Methods: The study included 89 people, of whom 47 completed the CTI (postural and three cognitive tasks (counting backwards, verbal fluency and the open-ended task «Unusual use of an ordinary object») and 42 patients, who underwent CTII (visuomotor reaction and the same cognitive tasks) in the early postoperative CABG period. The patients of both groups underwent complex testing of psychomotor, executive functions, attention, short-term memory and EEG study in the perioperative period of CABG.
Approaching coupled-cluster accuracy for molecular electronic structures with multi-task learning.
Nat Comput Sci
December 2024
Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA.
Machine learning plays an important role in quantum chemistry, providing fast-to-evaluate predictive models for various properties of molecules; however, most existing machine learning models for molecular electronic properties use density functional theory (DFT) databases as ground truth in training, and their prediction accuracy cannot surpass that of DFT. In this work we developed a unified machine learning method for electronic structures of organic molecules using the gold-standard CCSD(T) calculations as training data. Tested on hydrocarbon molecules, our model outperforms DFT with several widely used hybrid and double-hybrid functionals in terms of both computational cost and prediction accuracy of various quantum chemical properties.
View Article and Find Full Text PDFLearning everyday multitasking activities-An online survey about people's experiences and opinions.
PLoS One
December 2024
Department of Life Sciences, Centre for Clinical and Cognitive Neuroscience, Brunel University London, Kingston Lane, Uxbridge, Middlesex, United Kingdom.
Multitasking (MT)-performing more than one task at a time-has become ubiquitous in everyday life. Understanding of how MT is learned could enable optimizing learning regimes for tasks and occupations that necessitate frequent MT. Previous research has distinguished between MT learning regimes in which all tasks are learned in parallel, single-task (ST) learning regimes in which all tasks are learned individually, and mixed learning regimes (Mix) in which MT and ST regimes are mixed.
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!