Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction

Jun, Eunji; Mulyadi, Ahmad Wisnu; Choi, Jaehun; Suk, Heung-Il

doi:10.1109/tnnls.2020.3016670

Cited by 12 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In RNN-based studies, our model achieved on par performance compared to other mortality prediction studies by Harutyunyan et al [ 22 ] (0.87 vs. 0.87) and Jun et al [ 21 ] (0.87 vs. 0.87). Harutyunyan et al [ 22 ] used a multi-task LSTM to predict multiple clinical events, including mortality, with 17 clinical variables.…”

Section: Discussionmentioning

confidence: 61%

“…Harutyunyan et al [ 22 ] used a multi-task LSTM to predict multiple clinical events, including mortality, with 17 clinical variables. Jun et al [ 21 ] used a variational RNN with 99 clinical variables. All of the aforementioned studies were conducted using the MIMIC-III database.…”

Section: Discussionmentioning

confidence: 99%

“…Their model takes hourly measurements over a 48-h period and achieved an AUC of 0.76. Jun et al [ 21 ] proposed a bidirectional GRU model for mortality prediction that takes bi-hourly measurements of 99 clinical variables over a 48-h period. Their model achieved an AUC of 0.87.…”

Section: Related Workmentioning

confidence: 99%

“…Previous studies have used descriptive statistics on clinical observations and tree-based algorithms for mortality prediction [ 14 , 15 , 16 ]. Several studies employed time-series techniques to process real-valued clinical observations for mortality prediction [ 17 , 18 , 19 , 20 , 21 ]. Some studies have developed algorithms that can predict multiple important clinical events [ 22 , 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Feature Explanations in Recurrent Neural Networks for Predicting Risk of Mortality in Intensive Care Patients

Pattalung

Ingviya

Chaichulee

2021

JPM

View full text Add to dashboard Cite

Critical care staff are presented with a large amount of data, which made it difficult to systematically evaluate. Early detection of patients whose condition is deteriorating could reduce mortality, improve treatment outcomes, and allow a better use of healthcare resources. In this study, we propose a data-driven framework for predicting the risk of mortality that combines high-accuracy recurrent neural networks with interpretable explanations. Our model processes time-series of vital signs and laboratory observations to predict the probability of a patient’s mortality in the intensive care unit (ICU). We investigated our approach on three public critical care databases: Multiparameter Intelligent Monitoring in Intensive Care III (MIMIC-III), MIMIC-IV, and eICU. Our models achieved an area under the receiver operating characteristic curve (AUC) of 0.87–0.91. Our approach was not only able to provide the predicted mortality risk but also to recognize and explain the historical contributions of the associated factors to the prediction. The explanations provided by our model were consistent with the literature. Patients may benefit from early intervention if their clinical observations in the ICU are continuously monitored in real time.

show abstract

Section: Discussionmentioning

confidence: 61%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Feature Explanations in Recurrent Neural Networks for Predicting Risk of Mortality in Intensive Care Patients

Pattalung

Ingviya

Chaichulee

2021

JPM

View full text Add to dashboard Cite

show abstract

“…This can occur because machine learning (ML) models are often trained on data from health care organizations that are already riddled with inequity, potentially creating bias in the data and the resulting recommendations. For example, ML algorithms that are designed to predict hospital mortality may be biased by the data used to train them [11][12][13][14][15][16]. In particular, these algorithms are often trained on data from electronic health records (EHRs).…”

Section: Ai Is a Double-edged Sword For Health Disparities And Inequi...mentioning

confidence: 99%

Human-Centered Design to Address Biases in Artificial Intelligence

Chen¹,

Clayton²,

Novak³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

The potential of artificial intelligence (AI) to reduce health care disparities and inequities is recognized, but it can also exacerbate these issues if not implemented in an equitable manner. This perspective identifies potential biases in each stage of the AI life cycle, including data collection, annotation, machine learning model development, evaluation, deployment, operationalization, monitoring, and feedback integration. To mitigate these biases, we suggest involving a diverse group of stakeholders, using human-centered AI principles. Human-centered AI can help ensure that AI systems are designed and used in a way that benefits patients and society, which can reduce health disparities and inequities. By recognizing and addressing biases at each stage of the AI life cycle, AI can achieve its potential in health care.

show abstract

DP-MHAN: A Disease Prediction Method Based on Metapath Aggregated Heterogeneous Graph Attention Networks

Cui

2023

Database Systems for Advanced Applications

View full text Add to dashboard Cite

Uncertainty-Gated Stochastic Sequential Model for EHR Mortality Prediction

Cited by 12 publications

References 20 publications

Feature Explanations in Recurrent Neural Networks for Predicting Risk of Mortality in Intensive Care Patients

Feature Explanations in Recurrent Neural Networks for Predicting Risk of Mortality in Intensive Care Patients

Human-Centered Design to Address Biases in Artificial Intelligence

DP-MHAN: A Disease Prediction Method Based on Metapath Aggregated Heterogeneous Graph Attention Networks

Contact Info

Product

Resources

About