Research Topic

The Use of Convolutional Neural Networks in the Death Risk Prediction in Intensive Care Units

About this Research Topic

With the development of science and technology towards more intelligent solutions in the field of medicine, the intensive care unit (ICU) has become a research hotspot in the healthcare domain. The main reason is that ICU patients are critically ill. Therefore, the prediction of patients' death risk plays an important role in patients' cure rate. At present, logistic regression models are mainly used to predict the death in ICU in China and foreign countries. However, the indexes of ICU patients are irregular and non-linear, which leads to different degrees of error in the analysis results of logistic regression models.

With the rapid development of the new generation of artificial intelligence and big data technologies, the relevant medical information of ICU patients is usually dynamically stored in the patient personal database system of the hospital department. Moreover, deep learning technologies have gone beyond traditional machine learning methods. In the context of deep learning technologies, convolutional neural networks is a classical supervised feedforward neural network which is composed of a convolutional layer, pooling layer, and full connected layer. Some researchers have applied convolutional neural networks as an efficient deep learning technology in the field of medicine and bioinformatics.

Convolutional neural networks are used to build models. The accuracy, sensitivity, specificity, Youden index, and recall ratio are compared with that of the traditional SAPS-II model. The performance of a convolutional neural network model is better than a SAPS-II model and has obvious advantages. Therefore, the combination of a convolutional neural network under deep learning and ICU death risk prediction to build a new intelligent death risk prediction model has become one of the key problems to be solved in the medical field.

In view of the value of convolutional neural networks under deep learning in the medical field, especially in ICU, as well as the arrival of a new generation of Internet and artificial intelligence technology, medical big data is increasingly recognized by medical researchers. Based on this, a convolutional neural network is applied to the death prediction of ICU patients, which is of great significance to improve the cure rate of critically ill patients and reduce the workload of medical staff. Therefore, this Research Topic aims to share the application value of convolutional neural networks in ICUs. Topics include but are not limited to:
- Disease diagnosis in ICU based on artificial intelligence technology;
- Application of deep learning technology in disease control of ICU;
- Prediction of disease conditions in ICU based on artificial neural networks;
- Severe disease death prediction based on convolutional neural networks;
- Respiratory failure monitoring in ICU based on deep belief networks;
- Application of artificial intelligence technology in the diagnosis of severe acute kidney injury;
- Condition control of patients with severe cardiac insufficiency based on artificial neural network models;
- The value of bottom-top unsupervised learning in the diagnosis of severe diseases;
- Application of top-bottom supervised learning in ICU disease control;
- Severe disease diagnosis technology based on artificial intelligence and artificial neural network.


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

With the development of science and technology towards more intelligent solutions in the field of medicine, the intensive care unit (ICU) has become a research hotspot in the healthcare domain. The main reason is that ICU patients are critically ill. Therefore, the prediction of patients' death risk plays an important role in patients' cure rate. At present, logistic regression models are mainly used to predict the death in ICU in China and foreign countries. However, the indexes of ICU patients are irregular and non-linear, which leads to different degrees of error in the analysis results of logistic regression models.

With the rapid development of the new generation of artificial intelligence and big data technologies, the relevant medical information of ICU patients is usually dynamically stored in the patient personal database system of the hospital department. Moreover, deep learning technologies have gone beyond traditional machine learning methods. In the context of deep learning technologies, convolutional neural networks is a classical supervised feedforward neural network which is composed of a convolutional layer, pooling layer, and full connected layer. Some researchers have applied convolutional neural networks as an efficient deep learning technology in the field of medicine and bioinformatics.

Convolutional neural networks are used to build models. The accuracy, sensitivity, specificity, Youden index, and recall ratio are compared with that of the traditional SAPS-II model. The performance of a convolutional neural network model is better than a SAPS-II model and has obvious advantages. Therefore, the combination of a convolutional neural network under deep learning and ICU death risk prediction to build a new intelligent death risk prediction model has become one of the key problems to be solved in the medical field.

In view of the value of convolutional neural networks under deep learning in the medical field, especially in ICU, as well as the arrival of a new generation of Internet and artificial intelligence technology, medical big data is increasingly recognized by medical researchers. Based on this, a convolutional neural network is applied to the death prediction of ICU patients, which is of great significance to improve the cure rate of critically ill patients and reduce the workload of medical staff. Therefore, this Research Topic aims to share the application value of convolutional neural networks in ICUs. Topics include but are not limited to:
- Disease diagnosis in ICU based on artificial intelligence technology;
- Application of deep learning technology in disease control of ICU;
- Prediction of disease conditions in ICU based on artificial neural networks;
- Severe disease death prediction based on convolutional neural networks;
- Respiratory failure monitoring in ICU based on deep belief networks;
- Application of artificial intelligence technology in the diagnosis of severe acute kidney injury;
- Condition control of patients with severe cardiac insufficiency based on artificial neural network models;
- The value of bottom-top unsupervised learning in the diagnosis of severe diseases;
- Application of top-bottom supervised learning in ICU disease control;
- Severe disease diagnosis technology based on artificial intelligence and artificial neural network.


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Topic Editors

Loading..

Submission Deadlines

31 May 2021 Abstract
31 August 2021 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..

Topic Editors

Loading..

Submission Deadlines

31 May 2021 Abstract
31 August 2021 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..
Loading..

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..