A multi-task Gaussian process self-attention neural network for real-time prediction of the need for mechanical ventilators in COVID-19 patients

Zhang, Kai; Karanth, Siddharth; Patel, Bela; Murphy, Robert P.; Jiang, Xiaoqian

doi:10.1016/j.jbi.2022.104079

Cited by 18 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In tackling these complexities, GPs have shown to be exceptionally valuable for healthcare data analysis. GPs and their variants offer distinctive advantages in this domain, excelling in tasks like missing data imputation (Imani et al, 2019), predictive modeling (Colopy et al, 2016), multi-task learning (Dürichen et al, 2014), and early warning detection (Zhang et al, 2022). In Rinta-Koski et al (2018), a standard GP was employed to predict in-hospital mortality among premature infants.…”

Section: Healthcare and Biomedical Data Analysismentioning

confidence: 99%

A survey on Bayesian nonparametric learning for time series analysis

Vélez-Cruz

2024

Front. Signal Process.

View full text Add to dashboard Cite

Time series analysis aims to understand underlying patterns and relationships in data to inform decision-making. As time series data are becoming more widely available across a variety of academic disciplines, time series analysis has become a rapidly growing field. In particular, Bayesian nonparametric (BNP) methods are gaining traction for their power and flexibility in modeling, predicting, and extracting meaningful information from time series data. The utility of BNP methods lies in their ability to encode prior information and represent complex patterns in the data without imposing strong assumptions about the underlying distribution or functional form. BNP methods for time series analysis can be applied to a breadth of problems, including anomaly detection, noise density estimation, and time series clustering. This work presents a comprehensive survey of the existing literature on BNP methods for time series analysis. Various temporal BNP models are discussed along with notable applications and possible approaches for inference. This work also highlights current research trends in the field and potential avenues for further development and exploration.

show abstract

Section: Healthcare and Biomedical Data Analysismentioning

confidence: 99%

A survey on Bayesian nonparametric learning for time series analysis

Vélez-Cruz

2024

Front. Signal Process.

View full text Add to dashboard Cite

show abstract

“…The results of this study are promising, as machine learning techniques can provide high accuracy in blood pressure estimation. Moreover, Zhang et al conducted research demonstrating the efficacy of neural network-based machine-learning models in identifying patient-ventilator asynchrony during mechanical breathing [ 8 ]. The suggested neural network model has improved in terms of resilience and consistency.…”

Section: Introductionmentioning

confidence: 99%

Machine learning algorithm for ventilator mode selection, pressure and volume control

T.,

G.,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Mechanical ventilation techniques are vital for preserving individuals with a serious condition lives in the prolonged hospitalization unit. Nevertheless, an imbalance amid the hospitalized people demands and the respiratory structure could cause to inconsistencies in the patient’s inhalation. To tackle this problem, this study presents an Iterative Learning PID Controller (ILC-PID), a unique current cycle feedback type controller that helps in gaining the correct pressure and volume. The paper also offers a clear and complete examination of the primarily efficient neural approach for generating optimal inhalation strategies. Moreover, machine learning-based classifiers are used to evaluate the precision and performance of the ILC-PID controller. These classifiers able to forecast and choose the perfect type for various inhalation modes, eliminating the likelihood that patients will require mechanical ventilation. In pressure control, the suggested accurate neural categorization exhibited an average accuracy rate of 88.2% in continuous positive airway pressure (CPAP) mode and 91.7% in proportional assist ventilation (PAV) mode while comparing with the other classifiers like ensemble classifier has reduced accuracy rate of 69.5% in CPAP mode and also 71.7% in PAV mode. An average accuracy of 78.9% rate in other classifiers compared to neutral network in CPAP. The neural model had an typical range of 81.6% in CPAP mode and 84.59% in PAV mode for 20 cm H2O of volume created by the neural network classifier in the volume investigation. Compared to the other classifiers, an average of 72.17% was in CPAP mode, and 77.83% was in PAV mode in volume control. Different approaches, such as decision trees, optimizable Bayes trees, naive Bayes trees, nearest neighbour trees, and an ensemble of trees, were also evaluated regarding the accuracy by confusion matrix concept, training duration, specificity, sensitivity, and F1 score.

show abstract

“…Furhter models proposed end-to-end solutions allowing for integrated and robust real-time predictions over time optimizing the risk prediction. 25,26 In this study, we created ANN based rapid CT assessment tool trained to map and label the type, localization and volume of the lung tissue involvement among patients with COVID-19 as a part of the rapid assistance for the visualization of the type and extent of the inflammatory changes. Subsequently, we have used the data from this tool to model the in-hospital mortality and mechanical ventilation risk using large scale (>4000 cases) clinical data set.…”

Section: Introductionmentioning

confidence: 99%

“…The algorithm was trained with the inclusion of laboratory information and a gradient‐boosting algorithm to make final predictions. Furhter models proposed end‐to‐end solutions allowing for integrated and robust real‐time predictions over time optimizing the risk prediction 25,26 …”

Section: Introductionmentioning

confidence: 99%

Artificial neural network based prediction of the lung tissue involvement as an independent in‐hospital mortality and mechanical ventilation risk factor in COVID‐19

Parczewski,

Kufel,

Aksak‐Wąs

et al. 2023

Journal of Medical Virology

View full text Add to dashboard Cite

Introduction: During COVID-19 pandemic, artificial neural network (ANN) systems have been providing aid for clinical decisions. However, to achieve optimal results, these models should link multiple clinical data points to simple models. This study aimed to model the in-hospital mortality and mechanical ventilation risk using a two step approach combining clinical variables and ANN-analyzed lung inflammation data.Methods: A data set of 4317 COVID-19 hospitalized patients, including 266 patients requiring mechanical ventilation, was analyzed. Demographic and clinical data (including the length of hospital stay and mortality) and chest computed tomography (CT) data were collected. Lung involvement was analyzed using a trained ANN.The combined data were then analyzed using unadjusted and multivariate Cox proportional hazards models.Results: Overall in-hospital mortality associated with ANN-assigned percentage of the lung involvement (hazard ratio [HR]: 5.72, 95% confidence interval [CI]: 4.4-7.43, p < 0.001 for the patients with >50% of lung tissue affected by COVID-19 pneumonia), age category (HR: 5.34, 95% CI: 3.32-8.59 for cases >80 years,

show abstract

A multi-task Gaussian process self-attention neural network for real-time prediction of the need for mechanical ventilators in COVID-19 patients

Cited by 18 publications

References 28 publications

A survey on Bayesian nonparametric learning for time series analysis

A survey on Bayesian nonparametric learning for time series analysis

Machine learning algorithm for ventilator mode selection, pressure and volume control

Artificial neural network based prediction of the lung tissue involvement as an independent in‐hospital mortality and mechanical ventilation risk factor in COVID‐19

Contact Info

Product

Resources

About