Short-Term Forecasting of Monkeypox Cases Using a Novel Filtering and Combining Technique

Abstract

In the modern world, new technologies such as artificial intelligence, machine learning, and big data are essential to support healthcare surveillance systems, especially for monitoring confirmed cases of monkeypox. The statistics of infected and uninfected people worldwide contribute to the growing number of publicly available datasets that can be used to predict early-stage confirmed cases of monkeypox through machine-learning models. Thus, this paper proposes a novel filtering and combination technique for accurate short-term forecasts of infected monkeypox cases. To this end, we first filter the original time series of the cumulative confirmed cases into two new subseries: the long-term trend series and residual series, using the two proposed and one benchmark filter. Then, we predict the filtered subseries using five standard machine learning models and all their possible combination models. Hence, we combine individual forecasting models directly to obtain a final forecast for newly infected cases one day ahead. Four mean errors and a statistical test are performed to verify the proposed methodology’s performance. The experimental results show the efficiency and accuracy of the proposed forecasting methodology. To prove the superiority of the proposed approach, four different time series and five different machine learning models were included as benchmarks. The results of this comparison confirmed the dominance of the proposed method. Finally, based on the best combination model, we achieved a forecast of fourteen days (two weeks). This can help to understand the spread and lead to an understanding of the risk, which can be utilized to prevent further spread and enable timely and effective treatment.

Forecasting Day-Ahead Electricity Prices for the Italian Electricity Market Using a New Decomposition—Combination Technique

“…In general, the lower the MSPE, MAPE, MAE, and RMSE, the higher the forecasting accuracy of the model. In addition to the metrics mentioned above, the Diebold-Mariano (DM) [57] test is a commonly used statistical test for evaluating forecasts from different models in the electricity price and demand literature [58,59]. For instance, consider the two forecasts obtained from the two different time-series models, such as f1n (model 1) and f2n (model 2).…”

Retrospective evaluation of short-term forecast performance of ensemble sub-epidemic frameworks and other time-series models: The 2022-2023 mpox outbreak across multiple geographical scales, July 14th, 2022, through February 26th, 2023

“…The auto regressive integrate moving average (ARIMA) model is a tool for understanding and predicting future values in a time series. It is commonly employed in forecasting financial [54][55][56] and weather [57][58][59] trends, and have become a standard benchmark in disease forecasting [17,31,[33][34][35][36][37]60,61]. ARIMA models consist of three parts: the auto-regression (AR) part involving regressing on the most recent values of the series, the moving average (MA) of error terms occurring contemporaneously and at previous times, and the integration (I) or differencing to account for the overall trend in the data and to make the time series stable.…”

“…We selected the ARIMA model as baseline, as it has been frequently evaluated against other forecasting methodologies in the context of mpox [31,[33][34][35][36][37]. Therefore, its inclusion in skill score calculations provides a more in-depth quantitative evaluation of the forecasting abilities of the n-sub-epidemic and spatial-wave frameworks against a well-vetted methodology.…”

“…Several methodologies have been employed to forecast the case trajectory of the 2022-2023 mpox epidemic in various geographical regions, including, but not limited to, models focused on human judgment [29], deep learning, and artificial intelligence models (AI) [30][31][32], machine learning models [30][31][32][33][34][35], statistical models such as auto-regressive integrated moving average (ARIMA) models [31,[33][34][35][36][37], compartmental models [38], and semi-mechanistic sub-epidemic models [16]. Performance metrics employed have mainly included variations of mean absolute error (MAE) [16,30,31,[33][34][35]37], mean squared error (MSE) [16,[30][31][32][33][34][35][36][37], and mean absolute percentage error (MAPE) [16,31,[33][34][35], with only two studies also including probabilistic measures of performance such as the weighted interval score (WIS) [16,39]. Of the studies included here, four focused on the ascending phase of the epidemic (January 2022-Mid August 2022) [29,…”

“…Performance metrics employed have mainly included variations of mean absolute error (MAE) [16,30,31,[33][34][35]37], mean squared error (MSE) [16,[30][31][32][33][34][35][36][37], and mean absolute percentage error (MAPE) [16,31,[33][34][35], with only two studies also including probabilistic measures of performance such as the weighted interval score (WIS) [16,39]. Of the studies included here, four focused on the ascending phase of the epidemic (January 2022-Mid August 2022) [29,33,34,36], four evaluated forecasts of the ascending and peak of the epidemic (February 2022-September 2022) [30][31][32]39], and four focused on the ascending, peak and decline phases of the epidemic (January 2022-Present) [16,35,37,38].…”