Early Warning and Prediction of Heart Failure by Ensemble Deep Learning and Trend Similarity Measure based on Real Healthcare Data (Preprint)

2021 ◽  
Author(s):  
Chunjie Zhou ◽  
Aihua Hou ◽  
Ali Li ◽  
Zhenxing Zhang ◽  
Pengfei Dai ◽  
...  
Keyword(s):  
Risk Factors ◽  
Heart Failure ◽  
Deep Learning ◽  
Similarity Measure ◽  
Early Warning ◽  
Heart Diseases ◽  
Prediction Method ◽  
Physiological Data ◽  
Slow Disease Progression ◽  
Deep Learning Model

BACKGROUND In recent years, heart diseases cause more than 18 million deaths every year. Heart failure (HF) prediction is essential to slow disease progression by changing lifestyle and pharmacologic interventions before heart diseases occur. Various researches have been proposed recently to predict heart failure. However, these methods did not combine different data sources with high-dimensional for heart failure prediction. In addition, the existing methods failed to consider the coexisting risk factors for heart failure and the complex relationships among them. OBJECTIVE Our goal is to make early warning and prediction of heart failure, which can offer the opportunity to test and ultimately develop effective lifestyle and pharmacologic interventions. In this paper, both electronic medical records and physiological data are considered, so as to provide enough source information to identify valuable risk factors of heart failure and make HF prediction. METHODS In this paper, an early warning and prediction method for heart failure is proposed using deep learning and trend similarity measure approaches. First, we present the data fusion and feature extraction method to merge different sources of data and get several important risk factors, which contain relevant and valuable information for HF. Second, an ensemble deep learning model for HF prediction is proposed based on gradient algorithms and back propagation techniques. In addition, we present an anomaly detection method to eliminate abnormal data caused by mood changes or environmental factors. Finally, evaluated by the Haar wavelet decomposition strategy, a data sequence trend similarity measure method is proposed aiming at prediction and early warning of heart failure in massive medical data. RESULTS The proposed method is evaluated based on our real research project HeartCarer, which includes risk factor information and physiological data. We combine these datasets from 2015 to 2020 to make a better performance evaluation for the proposed deep learning model and similarity measure method. The combined dataset totally involves 2,976 HF patients, 18,203 family members closely related to patients, and 295,801 healthy people. By comparing with other state-of-the-art methods and our prior work in [2] (90%), the proposed method can obtain a higher accuracy of 98.5% in heart disease prediction. CONCLUSIONS Heart failure (HF) prediction is essential to slow disease progression by changing lifestyle and pharmacologic interventions before heart diseases occur. An early warning and prediction method for heart failure is proposed using deep learning and trend similarity measure approaches in this paper. The proposed method is evaluated based on our real research project HeartCarer and obtain a high accuracy in heart disease prediction.

BEHRT-HF: an interpretable transformer-based, deep learning model for prediction of incident heart failure

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Rao ◽  
Y Li ◽  
R Ramakrishnan ◽  
A Hassaine ◽  
D Canoy ◽  
...  
Keyword(s):  
Heart Failure ◽  
Deep Learning ◽  
State Of The Art ◽  
Failure Prediction ◽  
Predictive Performance ◽  
Learning Model ◽  
Learning Framework ◽  
Incident Heart Failure ◽  
Ablation Study ◽  
Deep Learning Model

Abstract Background/Introduction Predicting incident heart failure has been challenging. Deep learning models when applied to rich electronic health records (EHR) offer some theoretical advantages. However, empirical evidence for their superior performance is limited and they remain commonly uninterpretable, hampering their wider use in medical practice. Purpose We developed a deep learning framework for more accurate and yet interpretable prediction of incident heart failure. Methods We used longitudinally linked EHR from practices across England, involving 100,071 patients, 13% of whom had been diagnosed with incident heart failure during follow-up. We investigated the predictive performance of a novel transformer deep learning model, “Transformer for Heart Failure” (BEHRT-HF), and validated it using both an external held-out dataset and an internal five-fold cross-validation mechanism using area under receiver operating characteristic (AUROC) and area under the precision recall curve (AUPRC). Predictor groups included all outpatient and inpatient diagnoses within their temporal context, medications, age, and calendar year for each encounter. By treating diagnoses as anchors, we alternatively removed different modalities (ablation study) to understand the importance of individual modalities to the performance of incident heart failure prediction. Using perturbation-based techniques, we investigated the importance of associations between selected predictors and heart failure to improve model interpretability. Results BEHRT-HF achieved high accuracy with AUROC 0.932 and AUPRC 0.695 for external validation, and AUROC 0.933 (95% CI: 0.928, 0.938) and AUPRC 0.700 (95% CI: 0.682, 0.718) for internal validation. Compared to the state-of-the-art recurrent deep learning model, RETAIN-EX, BEHRT-HF outperformed it by 0.079 and 0.030 in terms of AUPRC and AUROC. Ablation study showed that medications were strong predictors, and calendar year was more important than age. Utilising perturbation, we identified and ranked the intensity of associations between diagnoses and heart failure. For instance, the method showed that established risk factors including myocardial infarction, atrial fibrillation and flutter, and hypertension all strongly associated with the heart failure prediction. Additionally, when population was stratified into different age groups, incident occurrence of a given disease had generally a higher contribution to heart failure prediction in younger ages than when diagnosed later in life. Conclusions Our state-of-the-art deep learning framework outperforms the predictive performance of existing models whilst enabling a data-driven way of exploring the relative contribution of a range of risk factors in the context of other temporal information. Funding Acknowledgement Type of funding source: Private grant(s) and/or Sponsorship. Main funding source(s): National Institute for Health Research, Oxford Martin School, Oxford Biomedical Research Centre

Insights into deep learning for earthquake magnitude and location estimation

2021 ◽  
Author(s):  
Jannes Münchmeyer ◽  
Dino Bindi ◽  
Ulf Leser ◽  
Frederik Tilmann
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Early Warning ◽  
Source Parameters ◽  
Spectral Composition ◽  
Learning Model ◽  
Location Estimation ◽  
Training Set ◽  
Earthquake Source Parameters ◽  
Deep Learning Model

<p><span>The estimation of earthquake source parameters, in particular magnitude and location, in real time is one of the key tasks for earthquake early warning and rapid response. In recent years, several publications introduced deep learning approaches for these fast assessment tasks. Deep learning is well suited for these tasks, as it can work directly on waveforms and </span><span>can</span><span> learn features and their relation from data.</span></p><p><span>A drawback of deep learning models is their lack of interpretability, i.e., it is usually unknown what reasoning the network uses. Due to this issue, it is also hard to estimate how the model will handle new data whose properties differ in some aspects from the training set, for example earthquakes in previously seismically quite regions. The discussions of previous studies usually focused on the average performance of models and did not consider this point in any detail.</span></p><p><span>Here we analyze a deep learning model for real time magnitude and location estimation through targeted experiments and a qualitative error analysis. We conduct our analysis on three large scale regional data sets from regions with diverse seismotectonic settings and network properties: Italy and Japan with dense networks </span><span>(station spacing down to 10 km)</span><span> of strong motion sensors, and North Chile with a sparser network </span><span>(station spacing around 40 km) </span><span>of broadband stations. </span></p><p><span>We obtained several key insights. First, the deep learning model does not seem to follow the classical approaches for magnitude and location estimation. For magnitude, one would classically expect the model to estimate attenuation, but the network rather seems to focus its attention on the spectral composition of the waveforms. For location, one would expect a triangulation approach, but our experiments instead show indications of a fingerprinting approach. </span>Second, we can pinpoint the effect of training data size on model performance. For example, a four times larger training set reduces average errors for both magnitude and location prediction by more than half, and reduces the required time for real time assessment by a factor of four. <span>Third, the model fails for events with few similar training examples. For magnitude, this means that the largest event</span><span>s</span><span> are systematically underestimated. For location, events in regions with few events in the training set tend to get mislocated to regions with more training events. </span><span>These characteristics can have severe consequences in downstream tasks like early warning and need to be taken into account for future model development and evaluation.</span></p>

scholarly journals Public Opinion Early Warning Agent Model: A Deep Learning Cascade Virality Prediction Model Based on Multi-Feature Fusion

2021 ◽  
Vol 15 ◽  
Author(s):  
Liqun Gao ◽  
Yujia Liu ◽  
Hongwu Zhuang ◽  
Haiyang Wang ◽  
Bin Zhou ◽  
...  
Keyword(s):  
Deep Learning ◽  
Public Opinion ◽  
Prediction Model ◽  
Network Structure ◽  
Early Warning ◽  
Feature Fusion ◽  
Learning Model ◽  
Feature Model ◽  
Underlying Network ◽  
Deep Learning Model

With the rapid popularity of agent technology, a public opinion early warning agent has attracted wide attention. Furthermore, a deep learning model can make the agent more automatic and efficient. Therefore, for the agency of a public opinion early warning task, the deep learning model is very suitable for completing tasks such as popularity prediction or emergency outbreak. In this context, improving the ability to automatically analyze and predict the virality of information cascades is one of the tasks that deep learning model approaches address. However, most of the existing studies sought to address this task by analyzing cascade underlying network structure. Recent studies proposed cascade virality prediction for agnostic-networks (without network structure), but did not consider the fusion of more effective features. In this paper, we propose an innovative cascade virus prediction model named CasWarn. It can be quickly deployed in intelligent agents to effectively predict the virality of public opinion information for different industries. Inspired by the agnostic-network model, this model extracts the key features (independent of the underlying network structure) of an information cascade, including dissemination scale, emotional polarity ratio, and semantic evolution. We use two improved neural network frameworks to embed these features, and then apply the classification task to predict the cascade virality. We conduct comprehensive experiments on two large social network datasets. Furthermore, the experimental results prove that CasWarn can make timely and effective cascade virality predictions and verify that each feature model of CasWarn is beneficial to improve performance.

scholarly journals Prediction and variation of the auroral oval boundary based on a deep learning model and space physical parameters

2020 ◽  
Vol 27 (1) ◽  
pp. 11-22
Author(s):  
Yiyuan Han ◽  
Bing Han ◽  
Zejun Hu ◽  
Xinbo Gao ◽  
Lixia Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prediction Method ◽  
Auroral Oval ◽  
Physical Parameters ◽  
Statistical Experiments ◽  
Proposed Model ◽  
Solar Wind Parameters ◽  
The Relationship ◽  
Deep Learning Model ◽  
Polar Satellite

Abstract. The auroral oval boundary represents an important physical process with implications for the ionosphere and magnetosphere. An automatic auroral oval boundary prediction method based on deep learning in this paper is applied to study the variation of the auroral oval boundary associated with different space physical parameters. We construct an auroral oval boundary dataset to train our proposed model, which consists of 184 416 auroral oval boundary points extracted from 3842 images captured by the Ultraviolet Imager (UVI) of the Polar satellite and its corresponding 18 space physical parameters selected from the OMNI dataset from December 1996 to March 1997. Furthermore, several statistical experiments and correlation analysis experiments are performed based on our dataset to explore the relationship between space physical parameters and the location of the auroral oval boundary. The experiment results show that the prediction model based on the deep learning method can estimate the auroral oval boundary efficiently, and different space physical parameters have different effects on the auroral oval boundary, especially the interplanetary magnetic field (IMF), geomagnetic indexes, and solar wind parameters.

Abstract 13948: Deep Learning Identification of Brain Structural Atrophy Associated With Heart Failure With Preserved Ejection Fraction Among Patients With Preexisting Dementia Using Clinical Imaging

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Camilo Bermudez Noguera ◽  
Cailey I Kerley ◽  
Karthik Ramadass ◽  
Eric H Farber-Eger ◽  
Ya-Chen Lin ◽  
...  
Keyword(s):  
Risk Factors ◽  
Heart Failure ◽  
Cardiovascular Disease ◽  
Deep Learning ◽  
Ejection Fraction ◽  
Medical Center ◽  
Brain Regions ◽  
Brain Morphology ◽  
Angular Gyrus ◽  
Preserved Ejection Fraction

Background: Heart failure with preserved ejection fraction (HFpEF) and dementia share several cardiovascular risk factors and have been independently associated with brain atrophy. However, it is unclear how HFpEF affects brain morphology in patients with preexisting dementia. Advances in bioinformatics data extraction pipelines, quantitative neuroimaging, and deep learning, have made possible the analysis of the effects of cardiovascular disease on clinical neuroimaging in large datasets. Hypothesis: We hypothesized that HFpEF in the setting of dementia would be associated with distinct brain morphology imaging changes compared to dementia in the absence of HFpEF. Methods: We used the bioinformatics tools at Vanderbilt University Medical Center to extract and analyze deidentified clinical neuroimaging from patients with a diagnosis of dementia with and without coexisting HFpEF from the electronic health record. We identified a total of 30 patients with HFpEF and dementia who had high-resolution, clinical neuroimaging as well as 301 age- and sex-matched controls. We used an automated pipeline to segment the brain into 132 distinct brain regions and estimate their volume to find structural differences associated with HFpEF. Results: We found six regions with significant atrophy associated with HFpEF: accumbens area, amygdala, posterior insula, anterior orbital gyrus, angular gyrus, and cerebellar white matter. There were no regions with atrophy inversely associated with HFpEF (Figure 1). Conclusions: Here, we show that patients with HFpEF have a distinct neuroimaging signature on patients with preexisting dementia. A possible mechanism of injury for this region and the subsequent atrophy has been linked to high aortic stiffening secondary to chronic cardiovascular disease and its risk factors, resulting in end-organ damage due to barotrauma and shear forces.

scholarly journals Dynamic Pollution Emission Prediction Method of a Combined Heat and Power System Based on the Hybrid CNN-LSTM Model and Attention Mechanism

2021 ◽  
Author(s):  
Anping Wan ◽  
Jie Yang ◽  
Ting Chen ◽  
Yang Jinxing ◽  
Ke Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Power System ◽  
Prediction Method ◽  
Learning Model ◽  
Combined Heat And Power ◽  
Attention Mechanism ◽  
Feature Engineering ◽  
Pollution Emission ◽  
Highly Nonlinear ◽  
Deep Learning Model

Abstract The prediction of pollution emission from a combined heat and power (CHP) system is very important for the production regulation and emergency response of a power system. The composition and structure of the CHP equipment are complex, and the production process is cumbersome. The fuel chemical reaction of the pulverized coal in the boiler represents a highly nonlinear and strongly interrelated process that is strongly affected by external environmental factors, which causes a certain level of volatility and uncertainty. In this study, a pollution emission prediction method of CHP systems based on feature engineering and a hybrid deep learning model is proposed. Feature engineering performs multi-step preprocessing on the original data, refines the correlation factors, and removes redundant variables. The hybrid deep learning model has a multi-variable input and is established by combining the convolutional neural network-long short-term memory network with the attention mechanism. The case study is conducted on the collected actual dataset. The influence of the prediction target periodicity on the prediction results is analyzed seasonally to verify the effectiveness of the hybrid model. The results show that the root mean square error of the proposed method is less than one, and the error is reduced compared to the other basic methods, which proves the superiority of the proposed pollution emission prediction method over the existing methods.

scholarly journals Prediction and variation of auroral oval boundary based on deep learning model and space physical parameters

2019 ◽  
Author(s):  
Yiyuan Han ◽  
Bing Han ◽  
Zejun Hu ◽  
Xinbo Gao ◽  
Lixia Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prediction Method ◽  
Auroral Oval ◽  
Physical Parameters ◽  
Statistical Experiments ◽  
Proposed Model ◽  
Analysis Experiment ◽  
Solar Wind Parameters ◽  
The Relationship ◽  
Deep Learning Model

Abstract. The auroral oval boundary represents important physical process with implications for the ionosphere and magnetosphere. An automatic auroral oval boundary prediction method based on deep learning in this paper are applied to study the variation of auroral oval boundary, associated with different space physical parameters. We construct an auroral oval boundary dataset to train our proposed model, which consists of 184416 auroral oval boundary points extracted from 3842 UVI images captured by Ultraviolet Imager of the Polar satellite and its corresponding 18 space physical parameters selected from OMNI dataset during December 1996 to March 1997. Furthermore, several statistical experiments and correlation analysis experiment are performed based on our dataset to explore the relationship between space physical parameters and the location of auroral oval boundary. The experiment results show that the prediction model based on deep learning method could estimate auroral oval boundary efficiently, and different space physical parameters have different effects on auroral oval boundary, especially interplanetary magnetic field (IMF), geomagnetic indexes and solar wind parameters.

Sign in / Sign up

Export Citation Format

Share Document