scholarly journals DEVELOPMENT OF REAL‐TIME PREDICTION MODEL FOR PNEUMONIA BASED ON CLINICAL AND ENVIRONMENTAL DATA USING DEEP LEARNING

Respirology ◽  
2019 ◽  
Vol 24 (S2) ◽  
pp. 134-134
Keyword(s):  
Deep Learning ◽  
Prediction Model ◽  
Real Time ◽  
Environmental Data ◽  
Time Prediction

scholarly journals Development of a Real-Time Risk Prediction Model for In-Hospital Cardiac Arrest in Critically Ill Patients Using Deep Learning: Retrospective Study (Preprint)

2019 ◽  
Author(s):  
Junetae Kim ◽  
Yu Rang Park ◽  
Jeong Hoon Lee ◽  
Jae-Ho Lee ◽  
Young-Hak Kim ◽  
...  
Keyword(s):  
Cardiac Arrest ◽  
Intensive Care ◽  
Deep Learning ◽  
Retrospective Study ◽  
Prediction Model ◽  
Real Time ◽  
Risk Prediction ◽  
Time Dependent ◽  
Time Prediction ◽  
Deep Learning Model

BACKGROUND Cardiac arrest is the most serious death-related event in intensive care units (ICUs), but it is not easily predicted because of the complex and time-dependent data characteristics of intensive care patients. Given the complexity and time dependence of ICU data, deep learning–based methods are expected to provide a good foundation for developing risk prediction models based on large clinical records. OBJECTIVE This study aimed to implement a deep learning model that estimates the distribution of cardiac arrest risk probability over time based on clinical data and assesses its potential. METHODS A retrospective study of 759 ICU patients was conducted between January 2013 and July 2015. A character-level gated recurrent unit with a Weibull distribution algorithm was used to develop a real-time prediction model. Fivefold cross-validation testing (training set: 80% and validation set: 20%) determined the consistency of model accuracy. The time-dependent area under the curve (TAUC) was analyzed based on the aggregation of 5 validation sets. RESULTS The TAUCs of the implemented model were 0.963, 0.942, 0.917, 0.875, 0.850, 0.842, and 0.761 before cardiac arrest at 1, 8, 16, 24, 32, 40, and 48 hours, respectively. The sensitivity was between 0.846 and 0.909, and specificity was between 0.923 and 0.946. The distribution of risk between the cardiac arrest group and the non–cardiac arrest group was generally different, and the difference rapidly increased as the time left until cardiac arrest reduced. CONCLUSIONS A deep learning model for forecasting cardiac arrest was implemented and tested by considering the cumulative and fluctuating effects of time-dependent clinical data gathered from a large medical center. This real-time prediction model is expected to improve patient’s care by allowing early intervention in patients at high risk of unexpected cardiac arrests.

scholarly journals Development of a Real-Time Risk Prediction Model for In-Hospital Cardiac Arrest in Critically Ill Patients Using Deep Learning: Retrospective Study

10.2196/16349 ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. e16349 ◽  
Author(s):  
Junetae Kim ◽  
Yu Rang Park ◽  
Jeong Hoon Lee ◽  
Jae-Ho Lee ◽  
Young-Hak Kim ◽  
...  
Keyword(s):  
Cardiac Arrest ◽  
Intensive Care ◽  
Deep Learning ◽  
Retrospective Study ◽  
Prediction Model ◽  
Real Time ◽  
Risk Prediction ◽  
Time Dependent ◽  
Time Prediction ◽  
Deep Learning Model

Background Cardiac arrest is the most serious death-related event in intensive care units (ICUs), but it is not easily predicted because of the complex and time-dependent data characteristics of intensive care patients. Given the complexity and time dependence of ICU data, deep learning–based methods are expected to provide a good foundation for developing risk prediction models based on large clinical records. Objective This study aimed to implement a deep learning model that estimates the distribution of cardiac arrest risk probability over time based on clinical data and assesses its potential. Methods A retrospective study of 759 ICU patients was conducted between January 2013 and July 2015. A character-level gated recurrent unit with a Weibull distribution algorithm was used to develop a real-time prediction model. Fivefold cross-validation testing (training set: 80% and validation set: 20%) determined the consistency of model accuracy. The time-dependent area under the curve (TAUC) was analyzed based on the aggregation of 5 validation sets. Results The TAUCs of the implemented model were 0.963, 0.942, 0.917, 0.875, 0.850, 0.842, and 0.761 before cardiac arrest at 1, 8, 16, 24, 32, 40, and 48 hours, respectively. The sensitivity was between 0.846 and 0.909, and specificity was between 0.923 and 0.946. The distribution of risk between the cardiac arrest group and the non–cardiac arrest group was generally different, and the difference rapidly increased as the time left until cardiac arrest reduced. Conclusions A deep learning model for forecasting cardiac arrest was implemented and tested by considering the cumulative and fluctuating effects of time-dependent clinical data gathered from a large medical center. This real-time prediction model is expected to improve patient’s care by allowing early intervention in patients at high risk of unexpected cardiac arrests.

The Error Correction Model on Kalman Filter

2014 ◽  
Vol 644-650 ◽  
pp. 3968-3971
Author(s):  
Ya Qiu Hao
Keyword(s):  
Prediction Model ◽  
Real Time ◽  
Arrival Time ◽  
Running Speed ◽  
Correction Model ◽  
The Real ◽  
Time Prediction ◽  
Speed Prediction ◽  
Arrival Time Prediction ◽  
Bus Arrival Time Prediction

In this paper, authors extracted the data from the GPS equipment on the bus and established the real-time bus arrival time prediction model and bus running speed prediction model based on Kalman filtering technique. Analyse the error and build the error correction model. Firstly the bus running speed was predicted in the next section with the bus running speed prediction model, and then the bus arrival time was predicted with the real-time bus arrival time prediction model. Applying the newest information of bus running speed and bus arrival time, we were able to predict the real-time bus arrival time dynamically. The bus running speed prediction model and the real-time bus arrival time prediction model were assessed with the data of transit route NO.300 in Beijing. Lastly we assessed the real-time bus arrival time with the error between bus arrival time and real-time bus arrival time so that the prediction error was improved to 10 seconds which has higher prediction accuracy.

scholarly journals Deep Learning Software Defect Prediction Methods for Cloud Environments Research

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Wenjian Liu ◽  
Baoping Wang ◽  
Wennan Wang
Keyword(s):  
Deep Learning ◽  
Prediction Model ◽  
Real Time ◽  
Defect Prediction ◽  
Prediction Methods ◽  
Learning Approach ◽  
Software Defect Prediction ◽  
Imbalance Problem ◽  
Software Defect ◽  
Ladder Network

This paper provides an in-depth study and analysis of software defect prediction methods in a cloud environment and uses a deep learning approach to justify software prediction. A cost penalty term is added to the supervised part of the deep ladder network; that is, the misclassification cost of different classes is added to the model. A cost-sensitive deep ladder network-based software defect prediction model is proposed, which effectively mitigates the negative impact of the class imbalance problem on defect prediction. To address the problem of lack or insufficiency of historical data from the same project, a flow learning-based geodesic cross-project software defect prediction method is proposed. Drawing on data information from other projects, a migration learning approach was used to embed the source and target datasets into a Gaussian manifold. The kernel encapsulates the incremental changes between the differences and commonalities between the two domains. To this point, the subspace is the space of two distributional approximations formed by the source and target data transformations, with traditional in-project software defect classifiers used to predict labels. It is found that real-time defect prediction is more practical because it has a smaller amount of code to review; only individual changes need to be reviewed rather than entire files or packages while making it easier for developers to assign fixes to defects. More importantly, this paper combines deep belief network techniques with real-time defect prediction at a fine-grained level and TCA techniques to deal with data imbalance and proposes an improved deep belief network approach for real-time defect prediction, while trying to change the machine learning classifier underlying DBN for different experimental studies, and the results not only validate the effectiveness of using TCA techniques to solve the data imbalance problem but also show that the defect prediction model learned by the improved method in this paper has better prediction performance.

A Simulated Prospective Evaluation of a Deep Learning Model for Real-Time Prediction of Clinical Deterioration Among Ward Patients

2021 ◽  
Vol Publish Ahead of Print ◽  
Author(s):  
Parth K. Shah ◽  
Jennifer C. Ginestra ◽  
Lyle H. Ungar ◽  
Paul Junker ◽  
Jeff I. Rohrbach ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Learning Model ◽  
Clinical Deterioration ◽  
Prospective Evaluation ◽  
Time Prediction ◽  
Deep Learning Model

Real-time Prediction Model for Satellite Telemetry Parameter Based on PSRT-RVM

2021 ◽  
Author(s):  
Jiahui He ◽  
Zhijun Cheng ◽  
Hongbin Liu ◽  
Bowen Li ◽  
Bo Guo
Keyword(s):  
Prediction Model ◽  
Real Time ◽  
Satellite Telemetry ◽  
Time Prediction
Sign in / Sign up

Export Citation Format

Share Document