AI and Dynamic Prediction of Deterioration in Covid-19

During the COVID-19 pandemic it became evident that outcome prediction of patients is crucial for triaging, when resources are limited and enable early start or increase of available therapeutic support. COVID-19 demographic risk factors for severe disease and death were rapidly established, including age and sex. Common Clinical Decision Support Systems (CDSS) and Early Warning Systems (EWS) have been used to triage based on demographics, vital signs and laboratory results. However, all of these have limitations, such as dependency of laboratory investigations or set threshold values, were derived from more or less specific cohort studies. Instead, individual illness dynamics and patterns of recovery might be essential characteristics in understanding the critical course of illness.The pandemic has been a game changer for data, and the concept of real-time massive health data has emerged as one of the important tools in battling the pandemic. We here describe the advantages and limitations of established risk scoring systems and show how artificial intelligence applied on dynamic vital parameter changes, may help to predict critical illness, adverse events and death in patients hospitalized with COVID-19.Machine learning assisted dynamic analysis can improve and give patient-specific prediction in Clinical Decision Support systems that have the potential of reducing both morbidity and mortality. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Gated Memory Unit: A Novel Recurrent Neural Network Architecture for Sequential Analysis

The predominant models used to analyze sequential data today are recurrent neural networks, specifically Long-Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, which utilize a temporal value known as the hidden state. These recurrent neural networks process sequential data by storing and modifying a hidden state through the use of mathematical functions known as gates. However, these networks hold many flaws such as limited temporal vision, insufficient memory capacity, and ineffective training times. In response, we propose a simple architecture, the Gated Memory Unit, which utilizes a new element, the hidden stack, a data stack implementation of the hidden state, as well as novel gates. This, along with a parameterized bounded activation function (PBA), allows the Gated Memory Unit (GMU) to outperform existing recurrent models effectively and efficiently. Trials on three datasets were used to display the new architecture's superior performance and reduced training time as well as the utility of the novel hidden stack compared to existing recurrent networks. On data which measures the daily death rate of SARS-Cov-2, the GMU was able to reduce losses to half that of comparable models and did so in nearly half the training time. Additionally, through the use of a generated spiking dataset, the GMU depicted its ability to use its hidden stack to store information past directly observable time steps. We prove that the Gated Memory Unit performs well on a variety of tasks and can outperform existing recurrent architectures. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Dynamic Emergency Transit Forecasting with IoT Sequential Data

Medical emergency transit counts minutes as real human lives. It is important to plan emergency transport routes according to real-time traffic flow status which leads to the the essential requirement of correct dynamic traffic prediction. Many Internet of Things (IoT) devices have been employed to assist emergency transit. Dynamic traffic flow patterns can be better predicted using data given by those devices. In small cities, however, the data are sent into separated management offices or just saved inside edge devices due to system compatibility or the cost of mobile network to computer centres. This condition leads to small and local datasets. Making full use of small local data to conduct prediction is one way to solve local emergency planning problems. In this work, we design a dynamic graph structure to work with Graph Neural Network (GNN) algorithm to forecast traffic flow levels considering this scenario. The proposed graph considers both geographical and time information with the potential to grow within a local mobile communication network. The commonly used Extreme Gradient Boosting (XGBoost) is included in the comparison. Experimental results show that our new design provides high prediction efficiency and accuracy.

Effectively and Efficiently Supporting Visual Big Data Analytics over Big Sequential Data: An Innovative Data Science Approach

In the current era of big data, huge volumes of valuable data have been generated and collected at a rapid velocity from a wide variety of rich data sources. In recent years, the willingness of many government, researchers, and organizations are led by the initiates of open data to share their data and make them publicly accessible. Healthcare, disease, and epidemiological data, such as privacy-preserving statistics on patients who suffered from epidemic diseases such as Coronavirus disease 2019 (COVID-19), are examples of open big data. Analyzing these open big data can be for social good. For instance, people get a better understanding of the disease by analyzing and mining the disease statistics, which may inspire them to take part in preventing, detecting, controlling and combating the disease. Having a pictorial representation further enhances the understanding of the data and corresponding results for analysis and mining because a picture is worth a thousand words. Hence, in this paper, we present a visual data science solution for the visualization and visual analytics of big sequential data. The visualization and visual analytics of sequences of real-life COVID-19 epidemiological data illustrate the ideas. Through our solution, we enable users to visualize the COVID-19 epidemiological data over time. It also allows people to visually analyze the data and discover relationships among popular features associated with the COVID-19 cases. The effectiveness of our visual data science solution in enhancing user experience in the visualization and visual analytics of big sequential data are demonstrated by evaluation of these real-life sequential COVID-19 epidemiological data. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Predicting Organization Performance Changes: A Sequential Data-Based Framework.

The business environment is increasingly uncertain due to the rapid development of disruptive information technologies, the changing global economy, and the COVID-19 pandemic. This brings great uncertainties to investors to predict the performance changes and risks of companies. This research proposes a sequential data-based framework that aggregates data from multiple sources including both structured and unstructured data to predict the performance changes. It leverages data generated from the early risk warning system in China stock market to measure and predict organization performance changes based on the risk warning status changes of public companies. Different from the models in existing literature that focus on the prediction of risk warning of companies, our framework predicts a portfolio of organization performance changes, including business decline and recovery, thus helping investors to not only predict public company risks, but also discover investment opportunities. By incorporating sequential data, our framework achieves 92.3% macro-F1 value on real-world data from listed companies in China, outperforming other static models.

Forecasting Covid-19 Infections in Ho Chi Minh City Using Recurrent Neural Networks

Coronavirus disease (Covid-19) has caused negative impacts on the economy, society and lives of people in Vietnam, especially in Ho Chi Minh City. Forecasting daily new Covid-19 infections is essential and important for prevention and social distancing purposes. Recurrent neural networks have been intensively used to process sequential data like voice, text, video and time series recently. In this paper, we present the forecasting models to predict new Covid-19 infected cases in Ho Chi Minh City using different recurrent neural networks (RNN). The experimental results show that the bidirectional long short-term memory network obtains better performance than the other models based on three statistical assessment criteria, the mean absolute error (MAE), symmetric mean absolute percentage error (sMAPE) and root mean square error (RMSE). The forecasting performance is also verified on the different forecasting horizons and multiple test runs. © 2021, Springer Nature Singapore Pte Ltd.

Sequential Data Assimilation of the Stochastic SEIR Epidemic Model for Regional COVID-19 Dynamics.

Newly emerging pandemics like COVID-19 call for predictive models to implement precisely tuned responses to limit their deep impact on society. Standard epidemic models provide a theoretically well-founded dynamical description of disease incidence. For COVID-19 with infectiousness peaking before and at symptom onset, the SEIR model explains the hidden build-up of exposed individuals which creates challenges for containment strategies. However, spatial heterogeneity raises questions about the adequacy of modeling epidemic outbreaks on the level of a whole country. Here, we show that by applying sequential data assimilation to the stochastic SEIR epidemic model, we can capture the dynamic behavior of outbreaks on a regional level. Regional modeling, with relatively low numbers of infected and demographic noise, accounts for both spatial heterogeneity and stochasticity. Based on adapted models, short-term predictions can be achieved. Thus, with the help of these sequential data assimilation methods, more realistic epidemic models are within reach.