Predictive healthcare modeling for early pandemic assessment leveraging deep auto regressor neural prophet

In this paper, NeuralProphet (NP), an explainable hybrid modular framework, enhances the forecasting performance of pandemics by adding two neural network modules; auto-regressor (AR) and lagged-regressor (LR). An advanced deep auto-regressor neural network (Deep-AR-Net) model is employed to implement these two modules. The enhanced NP is optimized via AdamW and Huber loss function to perform multivariate multi-step forecasting contrast to Prophet. The models are validated with COVID-19 time-series datasets. The NP's efficiency is studied component-wise for a long-term forecast for India and an overall reduction of 60.36% and individually 34.7% by AR-module, 53.4% by LR-module in MASE compared to Prophet. The Deep-AR-Net model reduces the forecasting error of NP for all five countries, on average, by 49.21% and 46.07% for short-and-long-term, respectively. The visualizations confirm that forecasting curves are closer to the actual cases but significantly different from Prophet. Hence, it can develop a real-time decision-making system for highly infectious diseases.

Time series models in prediction of severe fever with thrombocytopenia syndrome cases in Shandong province, China

Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus (SFTSV). Predicting the incidence of this disease in advance is crucial for policymakers to develop prevention and control strategies. In this study, we utilized historical incidence data of SFTS (2013-2020) in Shandong Province, China to establish three univariate prediction models based on two time-series forecasting algorithms Autoregressive Integrated Moving Average (ARIMA) and Prophet, as well as a special type of recurrent neural network Long Short-Term Memory (LSTM) algorithm. We then evaluated and compared the performance of these models. All three models demonstrated good predictive capabilities for SFTS cases, with the predicted results closely aligning with the actual cases. Among the models, the LSTM model exhibited the best fitting and prediction performance. It achieved the lowest values for mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). The number of SFTS cases in the subsequent 5 years in this area were also generated using this model. The LSTM model, being simple and practical, provides valuable information and data for assessing the potential risk of SFTS in advance. This information is crucial for the development of early warning systems and the formulation of effective prevention and control measures for SFTS.

Epidemiological characteristics and prediction model construction of hemorrhagic fever with renal syndrome in Quzhou City, China, 2005-2022

Background

Hemorrhagic fever with renal syndrome (HFRS) is one of the 10 major infectious diseases that jeopardize human health and is distributed in more than 30 countries around the world. China is the country with the highest number of reported HFRS cases worldwide, accounting for 90% of global cases. The incidence level of HFRS in Quzhou is at the forefront of Zhejiang Province, and there is no specific treatment for it yet. Therefore, it is crucial to grasp the epidemiological characteristics of HFRS in Quzhou and establish a prediction model for HFRS to lay the foundation for early warning of HFRS.

Methods

Descriptive epidemiological methods were used to analyze the epidemic characteristics of HFRS, the incidence map was drawn by ArcGIS software, the Seasonal AutoRegressive Integrated Moving Average (SARIMA) and Prophet model were established by R software. Then, root mean square error (RMSE) and mean absolute error (MAE) were used to evaluate the fitting and prediction performances of the model.

Results

A total of 843 HFRS cases were reported in Quzhou City from 2005 to 2022, with the highest annual incidence rate in 2007 (3.93/100,000) and the lowest in 2022 (1.05/100,000) (P trend<0.001). The incidence is distributed in a seasonal double-peak distribution, with the first peak from October to January and the second peak from May to July. The incidence rate in males (2.87/100,000) was significantly higher than in females (1.32/100,000). Farmers had the highest number of cases, accounting for 79.95% of the total number of cases. The incidence is high in the northwest of Quzhou City, with cases concentrated on cultivated land and artificial land. The RMSE and MAE values of the Prophet model are smaller than those of the SARIMA (1,0,1) (2,1,0)12 model.

Conclusion

From 2005 to 2022, the incidence of HFRS in Quzhou City showed an overall downward trend, but the epidemic in high-incidence areas was still serious. In the future, the dynamics of HFRS outbreaks and host animal surveillance should be continuously strengthened in combination with the Prophet model. During the peak season, HFRS vaccination and health education are promoted with farmers as the key groups.

Forecasting the Spread of COVID-19 Using Deep Learning and Big Data Analytics Methods

To contain the spread of the COVID-19 pandemic, there is a need for cutting-edge approaches that make use of existing technology capabilities. Forecasting its spread in a single or multiple countries ahead of time is a common strategy in most research. There is, however, a need for all-inclusive studies that capitalize on the entire regions on the African continent. This study closes this gap by conducting a wide-ranging investigation and analysis to forecast COVID-19 cases and identify the most critical countries in terms of the COVID-19 pandemic in all five major African regions. The proposed approach leveraged both statistical and deep learning models that included the autoregressive integrated moving average (ARIMA) model with a seasonal perspective, the long-term memory (LSTM), and Prophet models. In this approach, the forecasting problem was considered as a univariate time series problem using confirmed cumulative COVID-19 cases. The model performance was evaluated using seven performance metrics that included the mean-squared error, root mean-square error, mean absolute percentage error, symmetric mean absolute percentage error, peak signal-to-noise ratio, normalized root mean-square error, and the R2 score. The best-performing model was selected and used to make future predictions for the next 61 days. In this study, the long short-term memory model performed the best. Mali, Angola, Egypt, Somalia, and Gabon from the Western, Southern, Northern, Eastern, and Central African regions, with an expected increase of 22.77%, 18.97%, 11.83%, 10.72%, and 2.81%, respectively, were the most vulnerable countries with the highest expected increase in the number of cumulative positive cases.

Short term Markov corrector for building load forecasting system - Concept and case study of day-ahead load forecasting under the impact of the COVID-19 pandemic

In this paper, we present the concept and formulation of a short-term Markov corrector to an underlying day-ahead building load forecasting model. The models and the correctors are then integrated to the building supervision, control and data acquisition system to automate the self-updating and retraining processes. The proposed Markov corrector is experimentally proven to significantly improve the reactivity of the forecasting models with respect to untaught variations. Developed in a discrete manner over a continuous forecasting model, the corrector also helps to capture better the consumption peaks during the activity days. A proof-of-concept is demonstrated via the case study of the GreenER building, where the impact of the Markov correctors to the performance of the existing day-ahead load forecasting system (based on Prophet model) was analyzed during the 2021/2022 winter, under the influences of the Omicron wave of the COVID-19 pandemic.

Time series forecasting of temperature and turbidity due to global warming in river Ganga at and around Varanasi, India

The fluctuation in the river ecosystem network due to climate change-induced global warming affects aquatic organisms, water quality, and other ecological processes. Assessment of climate change-induced global warming impacts on regional hydrological processes is vital for effective water resource management and planning. The global warming effect on river water quality has been analyzed in this work. The river Ganga stretch near the Varanasi region has been chosen as the study area for this analysis. The air temperature has been predicted using the seasonal autoregressive integrated moving average (SARIMA) and the Prophet model. The Prophet model has shown better accuracy with a root mean square percent error (RMSPE) value of 3.2% compared to the SARIMA model, which has an RMPSE value of 7.54%. The river temperature, turbidity, and nighttime radiance values have been predicted for the years 2022 and 2025 using the long short-term memory (LSTM) algorithm. The anthropogenic effect on the river has been evaluated by using the nighttime radiance imageries. The predicted average river temperature shows an increment of 0.58 °C and 0.63 °C for the city and non-city river stretches, respectively, in 2025 compared to 2022. Similarly, the river turbidity shows an increment of 1.21 nephelometric turbidity units (NTU) and 1.17 NTU for the city and non-city stretch, respectively, in 2025 compared to 2022. For future predicted years, the nighttime radiance values for the region situated near the city river stretch show a significant rise compared to the region that lies nearby the non-city river stretch.

A hybrid forecasting model using LSTM and Prophet for energy consumption with decomposition of time series data

For decades, time series forecasting had many applications in various industries such as weather, financial, healthcare, business, retail, and energy consumption forecasting. An accurate prediction in these applications is a very important and also difficult task because of high sampling rates leading to monthly, daily, or even hourly data. This high-frequency property of time series data results in complexity and seasonality. Moreover, the time series data can have irregular fluctuations caused by various factors. Thus, using a single model does not result in good accuracy results. In this study, we propose an efficient forecasting framework by hybridizing the recurrent neural network model with Facebook's Prophet to improve the forecasting performance. Seasonal-trend decomposition based on the Loess (STL) algorithm is applied to the original time series and these decomposed components are used to train our recurrent neural network for reducing the impact of these irregular patterns on final predictions. Moreover, to preserve seasonality, the original time series data is modeled with Prophet, and the output of both sub-models are merged as final prediction values. In experiments, we compared our model with state-of-art methods for real-world energy consumption data of seven countries and the proposed hybrid method demonstrates competitive results to these state-of-art methods.

Prediction and analysis of COVID-19 daily new cases and cumulative cases: times series forecasting and machine learning models

BACKGROUND

COVID-19 poses a severe threat to global human health, especially the USA, Brazil, and India cases continue to increase dynamically, which has a far-reaching impact on people's health, social activities, and the local economic situation.

METHODS

The study proposed the ARIMA, SARIMA and Prophet models to predict daily new cases and cumulative confirmed cases in the USA, Brazil and India over the next 30 days based on the COVID-19 new confirmed cases and cumulative confirmed cases data set(May 1, 2020, and November 30, 2021) published by the official WHO, Three models were implemented in the R 4.1.1 software with forecast and prophet package. The performance of different models was evaluated by using root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE).

RESULTS

Through the fitting and prediction of daily new case data, we reveal that the Prophet model has more advantages in the prediction of the COVID-19 of the USA, which could compose data components and capture periodic characteristics when the data changes significantly, while SARIMA is more likely to appear over-fitting in the USA. And the SARIMA model captured a seven-day period hidden in daily COVID-19 new cases from 3 countries. While in the prediction of new cumulative cases, the ARIMA model has a better ability to fit and predict the data with a positive growth trend in different countries(Brazil and India).

CONCLUSIONS

This study can shed light on understanding the outbreak trends and give an insight into the epidemiological control of these regions. Further, the prediction of the Prophet model showed sufficient accuracy in the daily COVID-19 new cases of the USA. The ARIMA model is suitable for predicting Brazil and India, which can help take precautions and policy formulation for this epidemic in other countries.

Predicting the impact of the third wave of COVID-19 in India using hybrid statistical machine learning models: A time series forecasting and sentiment analysis approach

BACKGROUND

Since January 2020, India has faced two waves of COVID-19; preparation for the upcoming waves is the primary challenge for public health sectors and governments. Therefore, it is important to forecast future cumulative confirmed cases to plan and implement control measures effectively.

METHODS

This study proposed a hybrid autoregressive integrated moving average (ARIMA) and Prophet model to predict daily confirmed and cumulative confirmed cases. The built-in auto.arima function was first used to select the optimal hyperparameter values of the ARIMA model. Then, the modified ARIMA model was used to find the best fit between the test and forecast data to find the best model parameter combinations. Articles, blog posts, and news stories from virologists, scientists, and health experts related to the third wave of COVID-19 were gathered using the Python web scraping package Beautiful Soup. Their opinions (sentiments) toward the potential third wave were analyzed using natural language processing (NLP) libraries.

RESULTS

A spike in daily confirmed and cumulative confirmed cases was predicted in India in the next 180 days based on past time series data. The results were validated using various analytical tools and evaluation metrics, producing a root mean square error (RMSE) of 0.14 and a mean absolute percentage error (MAPE) of 0.06. The NLP processing results revealed negative sentiments in most articles and blogs, with few exceptions.

CONCLUSION

The findings of this study suggest that there will be more active cases in the upcoming days. The proposed models can forecast future daily confirmed and cumulative confirmed cases. This study will help the country and states plan appropriate public health measures for the upcoming waves of COVID-19.

Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant?

The ongoing outbreak of the COVID-19 pandemic prevails as an ultimatum to the global economic growth and henceforth, all of society since neither a curing drug nor a preventing vaccine is discovered. The spread of COVID-19 is increasing day by day, imposing human lives and economy at risk. Due to the increased enormity of the number of COVID-19 cases, the role of Artificial Intelligence (AI) is imperative in the current scenario. AI would be a powerful tool to fight against this pandemic outbreak by predicting the number of cases in advance. Deep learning-based time series techniques are considered to predict world-wide COVID-19 cases in advance for short-term and medium-term dependencies with adaptive learning. Initially, the data pre-processing and feature extraction is made with the real world COVID-19 dataset. Subsequently, the prediction of cumulative confirmed, death and recovered global cases are modelled with Auto-Regressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Stacked Long Short-Term Memory (SLSTM) and Prophet approaches. For long-term forecasting of COVID-19 cases, multivariate LSTM models is employed. The performance metrics are computed for all the models and the prediction results are subjected to comparative analysis to identify the most reliable model. From the results, it is evident that the Stacked LSTM algorithm yields higher accuracy with an error of less than 2% as compared to the other considered algorithms for the studied performance metrics. Country-specific analysis and city-specific analysis of COVID-19 cases for India and Chennai, respectively, are predicted and analyzed in detail. Also, statistical hypothesis analysis and correlation analysis are done on the COVID-19 datasets by including the features like temperature, rainfall, population, total infected cases, area and population density during the months of May, June, July and August to find out the best suitable model. Further, practical significance of predicting COVID-19 cases is elucidated in terms of assessing pandemic characteristics, scenario planning, optimization of models and supporting Sustainable Development Goals (SDGs).