Abstract P405: A Time-Series Forecast Model to Assess Vital Sign Waveform Variability Prior to Vasospasm

Stroke ◽  
2021 ◽  
Vol 52 (Suppl_1) ◽  
Author(s):  
Farhan Chaudhry ◽  
Ghada Mohamed ◽  
Hassan O Aboul Nour ◽  
Kipp W Johnson ◽  
Rachel J Hunt ◽  
...  
Keyword(s):  
Time Series ◽  
Vital Sign ◽  
Aneurysmal Subarachnoid Hemorrhage ◽  
Arima Model ◽  
Forecast Model ◽  
Arterial Line ◽  
Waveform Data ◽  
Time Series Forecast ◽  
Symptomatic Vasospasm ◽  
Arterial Blood

Introduction: Symptomatic vasospasm (SV) is a complication of aneurysmal subarachnoid hemorrhage (aSAH) and can lead to cerebral infarction. Changes in vital trends, such as heart rate (HR) and mean arterial blood pressure (MAP), have been associated with SV in aSAH. Real-time assessment of instantaneous vital sign waveform data could improve detection of vital sign variability associated with vasospasm. However, no model using instantaneous waveform data exists to predict SV. We hypothesize that autoregressive integrated moving average (ARIMA) analysis, a time-series forecast model, is a useful approach to assess the variability of vital sign waveforms associated with SV. Methods: In this small case-control study, vital signs of patients admitted to the neuroICU with aSAH were obtained using a software-based analytics platform, Sickbay. HR and MAP from 15 aSAH patients were continuously obtained from ECG and arterial line waveforms. Ten patients developed neurologic deficits attributed to angiographically-confirmed SV (Det). Five controls (Con) without SV were matched based on age. 3 Det and 3 Con were randomly selected for further analysis. For Det, waveforms were analyzed at 5-second intervals for 48 hours prior to clinical deterioration. For Con, waveforms were analyzed at a random 48-hour interval. Results: Visually, MAP and not HR was more variable in Det than in Con patients (Figure). The ARIMA model plotted the forecasted-fit for each delta-variable waveform. The MAP confidence interval margins were significantly larger for Det patients compared to the Con patient. This trend was consistent across all other patients. Conclusion: ARIMA is a useful tool to assess HR and MAP waveform variations prior to SV in aSAH. Larger studies are required to solidify this concept and further explore the combination of data analytics platform and ARIMA to predict neurological deterioration in SV.

scholarly journals Research on GDP Forecast Analysis Combining BP Neural Network and ARIMA Model

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shaobo Lu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Prediction Model ◽  
Error Correction ◽  
Relative Error ◽  
Bp Neural Network ◽  
Arima Model ◽  
Forecast Model ◽  
Price Prediction ◽  
The Neural Network

Based on the BP neural network and the ARIMA model, this paper predicts the nonlinear residual of GDP and adds the predicted values of the two models to obtain the final predicted value of the model. First, the focus is on the ARMA model in the univariate time series. However, in real life, forecasts are often affected by many factors, so the following introduces the ARIMAX model in the multivariate time series. In the prediction process, the network structure and various parameters of the neural network are not given in a systematic way, so the operation of the neural network is affected by many factors. Each forecasting method has its scope of application and also has its own weaknesses caused by the characteristics of its own model. Secondly, this paper proposes an effective combination method according to the GDP characteristics and builds an improved algorithm BP neural network price prediction model, the research on the combination of GDP prediction model is currently mostly focused on the weighted form, and this article proposes another combination, namely, error correction. According to the price characteristics, we determine the appropriate number of hidden layer nodes and build a BP neural network price prediction model based on the improved algorithm. Validation of examples shows that the error-corrected GDP forecast model is also better than the weighted GDP forecast model, which shows that error correction is also a better combination of forecasting methods. The forecast results of BP neural network have lower errors and monthly prices. The relative error of prediction is about 2.5%. Through comparison with the prediction results of the ARIMA model, in the daily price prediction, the relative error of the BP neural network prediction is 1.5%, which is lower than the relative error of the ARIMA model of 2%.

scholarly journals Forecasting leading industry stock prices based on a hybrid time-series forecast model

PLoS ONE ◽  
2018 ◽  
Vol 13 (12) ◽  
pp. e0209922 ◽  
Author(s):  
Ming-Chi Tsai ◽  
Ching-Hsue Cheng ◽  
Meei-Ing Tsai ◽  
Huei-Yuan Shiu
Keyword(s):  
Time Series ◽  
Stock Prices ◽  
Forecast Model ◽  
Time Series Forecast ◽  
Leading Industry

The Implication of Taiwan's Ore Tramp Carrier Cargo on the Blast Furnace Plant

2013 ◽  
Vol 694-697 ◽  
pp. 3488-3491 ◽  
Author(s):  
Ming Tao Chou ◽  
Chien Chang Chou
Keyword(s):  
Time Series ◽  
Blast Furnace ◽  
Forecast Error ◽  
Forecast Model ◽  
Time Series Model ◽  
Fuzzy Time Series ◽  
Time Series Forecast ◽  
The Relationship ◽  
Furnace Plant ◽  
Blast Furnace Plant

The article used a fuzzy time series model to analyze the relationship between the Taiwans ore tramp carrier cargo and the blast furnace plant in Taiwan. Finally, the proposed fuzzy time series model is applied to an empirical study in Taiwan. The results show that the proposed fuzzy time series forecast model produces a lower forecast error. That indicates it is an appropriate forecast tool.

Study on Grey Forecast Method of Chaotic Time Series

2010 ◽  
Vol 108-111 ◽  
pp. 1239-1243
Author(s):  
Rui Hua Lv ◽  
Yuan Yuan Wang
Keyword(s):  
Time Series ◽  
Forecast Model ◽  
Chaotic Time Series ◽  
Forecast Method ◽  
Time Series Forecast ◽  
Set Up ◽  
Forecast Problem

In this paper, the research evolving on chaotic time series forecast is firstly analyzed, and then the grey forecast model of chaotic time series is set up and is applied to chaotic time series forecast to solve the grey forecast problem of chaotic time series.

Time Series Features Extraction and Forecast from Multi-feature Stocks with Hybrid Deep Neural Networks.

2020 ◽  
Vol 13 ◽  
Author(s):  
Ye Xu ◽  
Xun Yuan
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Hybrid Model ◽  
Deep Neural Networks ◽  
Arima Model ◽  
Forecast Accuracy ◽  
Forecast Model ◽  
Closing Price ◽  
Massive Information ◽  
Better Than

Background: Forecasting of time series stock data is important in financial related works. Stock data usually have multifeatures such as opening price, closing price and so on. The traditional forecast methods, however, is mainly applied to one feature – closing price, or a few, like four or five features. The massive information hidden in the multi-feature data is not thoroughly discovered and used. Objective: Find a method to make used of all information of multi-features and get a forecast model. Method: LSTM based models are introduced in this paper. For comparison, three models are used and they are single LSTM model, hybrid model of LSTM-CNN, and traditional ARIMA model. Results: Experiments with different models are performed on stock data with 50 and 230 features, respectively. Results show that MSE of single LSTM model is 2.4% lower than ARIMA model and MSE of LSTM-CNN model is 12.57% lower than that of single LSTM model on 50 features data. On 230 features data, LSTM-CNN model is found to be improved by 23.41% in forecast accuracy. Conclusion: In this paper, we use three different models – ARIMA, single LSTM and LSTM-CNN hybrid model – to forecast rise and fall of multi-features stock data. It’s found that single LSTM model is better than traditional ARIMA model on the average, and LSTM-CNN hybrid model is better than single LSTM model on 50-feature stock data. What’s more, we use LSTM-CNN model to perform experiments on stock data with 50 and 230 features, respectively. And is found that results of the same model on 230 features data is better than that on 50 features data. It’s proved in our work that the LSTM-CNN hybrid model is better than other models and experiments on stock data with more features could result in better outcomes. We’ll do more works on hybrid models next.

Time Series Forecast of Foundation Pit Deformation Based on BP Neural Network

2014 ◽  
Vol 556-562 ◽  
pp. 5979-5983 ◽  
Author(s):  
Jing Cao ◽  
Wen Yun Ding ◽  
Dang Shu Zhao ◽  
Hai Ming Liu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Bp Neural Network ◽  
Forecast Model ◽  
Measured Data ◽  
Engineering Optimization ◽  
Forecast Method ◽  
Foundation Pit ◽  
Time Series Forecast ◽  
Excavation Process

Combined with the advantage of BP neural network, a time series forecast method of foundation pit deformation based on BP neural network is proposed. According to the excavation process of foundation pit, the deformation forecast model is built by analyzing the measured data of early working stage. Then, the model is used to forecast the deformation of later working stage. Through an engineering optimization example, it is showed that this method is not only efficient, but also with good economic and practical value.

scholarly journals COMPARING THE PREDICTION ACCURACY OF LSTM AND ARIMA MODELS FOR TIME-SERIES WITH PERMANENT FLUCTUATION

2020 ◽  
Vol 9 (2) ◽  
Author(s):  
Ghahreman Abdoli ◽  
Mohsen MehrAra ◽  
Mohammad Ebrahim Ardalani
Keyword(s):  
Time Series ◽  
Economic System ◽  
Short Term Memory ◽  
Stock Exchange ◽  
Moving Average ◽  
Arima Model ◽  
Forecast Accuracy ◽  
Forecast Model ◽  
Economic Time Series ◽  
Intraday Data

In developing countries with an unstable economic system, permanent fluctuation in historical data is always a concern. Recognizing dependency and independency of variables are vague and proceeding a reliable forecast model is more complex than other countries. Although linearization of nonlinear multivariate economic time-series to predict, may give a result, the nature of data which shows irregularities in the economic system, should be ignored. New approaches of artificial neural network (ANN) help to make a prediction model with keeping data attributes. In this paper, we used the Tehran Stock Exchange (TSE) intraday data in 10 years to forecast the next 2 months. Long Short-Term Memory (LSTM) from ANN chooses and outputs compared with the autoregressive integrated moving average (ARIMA) model. The results show, although, in long term prediction, the forecast accuracy of both models reduce, LSTM outperforms ARIMA, in terms of error of accuracy, significantly.

scholarly journals Relationship Between Baroreflex and Cerebral Autoregulation in Patients With Cerebral Vasospasm After Aneurysmal Subarachnoid Hemorrhage

2022 ◽  
Vol 12 ◽  
Author(s):  
Agnieszka Uryga ◽  
Nathalie Nasr ◽  
Magdalena Kasprowicz ◽  
Karol Budohoski ◽  
Marek Sykora ◽  
...  
Keyword(s):  
Subarachnoid Hemorrhage ◽  
Cerebral Vasospasm ◽  
Cerebral Autoregulation ◽  
Cerebral Blood Flow Velocity ◽  
Aneurysmal Subarachnoid Hemorrhage ◽  
Linear Regression Analysis ◽  
Inverse Correlation ◽  
Arterial Line ◽  
Arterial Blood ◽  
The Impact

Introduction: Common consequences following aneurysmal subarachnoid hemorrhage (aSAH) are cerebral vasospasm (CV), impaired cerebral autoregulation (CA), and disturbance in the autonomic nervous system, as indicated by lower baroreflex sensitivity (BRS). The compensatory interaction between BRS and CA has been shown in healthy volunteers and stable pathological conditions such as carotid atherosclerosis. The aim of this study was to investigate whether the inverse correlation between BRS and CA would be lost in patients after aSAH during vasospasm. A secondary objective was to analyze the time-trend of BRS after aSAH.Materials and Methods: Retrospective analysis of prospectively collected data was performed at the Neuro-Critical Care Unit of Addenbrooke's Hospital (Cambridge, UK) between June 2010 and January 2012. The cerebral blood flow velocity (CBFV) was measured in the middle cerebral artery using transcranial Doppler ultrasonography (TCD). The arterial blood pressure (ABP) was monitored invasively through an arterial line. CA was quantified by the correlation coefficient (Mxa) between slow oscillations in ABP and CBFV. BRS was calculated using the sequential cross-correlation method using the ABP signal.Results: A total of 73 patients with aSAH were included. The age [median (lower-upper quartile)] was 58 (50–67). WFNS scale was 2 (1–4) and the modified Fisher scale was 3 (1–3). In the total group, 31 patients (42%) had a CV and 42 (58%) had no CV. ABP and CBFV were higher in patients with CV during vasospasm compared to patients without CV (p = 0.001 and p < 0.001). There was no significant correlation between Mxa and BRS in patients with CV, neither during nor before vasospasm. In patients without CV, a significant, although moderate correlation was found between BRS and Mxa (rS = 0.31; p = 0.040), with higher BRS being associated with worse CA. Multiple linear regression analysis showed a significant worsening of BRS after aSAH in patients with CV (Rp = −0.42; p < 0.001).Conclusions: Inverse compensatory correlation between BRS and CA was lost in patients who developed CV after aSAH, both before and during vasospasm. The impact of these findings on the prognosis of aSAH should be investigated in larger studies.

Sign in / Sign up

Export Citation Format

Share Document