Time series analysis and short-term forecasting of monkeypox outbreak trends in the 10 major affected countries

被引:5
|
作者
Munir, Tahir [1 ]
Khan, Maaz [1 ]
Cheema, Salman Arif [2 ]
Khan, Fiza [1 ]
Usmani, Ayesha [1 ]
Nazir, Mohsin [1 ]
机构
[1] Aga Khan Univ Hosp, Dept Anaesthesiol, Private Wing,Second Floor,Stadium Rd,POB 3500, Karachi 74800, Pakistan
[2] Natl Text Univ, Dept Appl Sci, Faisalabad 37610, Pakistan
关键词
Time Series Modelling; Monkeypox; ARIMA; Forecasting; Viral Transmission; COVID-19; INFECTION; VIRUS;
D O I
10.1186/s12879-023-08879-5
中图分类号
R51 [传染病];
学科分类号
100401 ;
摘要
BackgroundConsidering the rapidly spreading monkeypox outbreak, WHO has declared a global health emergency. Still in the category of being endemic, the monkeypox disease shares numerous clinical characters with smallpox. This study focuses on determining the most effective combination of autoregressive integrated moving average model to encapsulate time dependent flow behaviour of the virus with short run prediction.MethodsThis study includes the data of confirmed reported cases and cumulative cases from eight most burdened countries across the globe, over the span of May 18, 2022, to December 31, 2022. The data was assembled from the website of Our World in Data and it involves countries such as United States, Brazil, Spain, France, Colombia, Mexico, Peru, United Kingdom, Germany and Canada. The job of modelling and short-term forecasting is facilitated by the employment of autoregressive integrated moving average. The legitimacy of the estimated models is argued by offering numerous model performance indices such as, root mean square error, mean absolute error and mean absolute prediction error.ResultsThe best fit models were deduced for each country by using the data of confirmed reported cases of monkeypox infections. Based on diverse set of performance evaluation criteria, the best fit models were then employed to provide forecasting of next twenty days. Our results indicate that the USA is expected to be the hardest-hit country, with an average of 58 cases per day with 95% confidence interval of (00-400). The second most burdened country remained Brazil with expected average cases of 23 (00-130). The outlook is not much better for Spain and France, with average forecasts of 52 (00-241) and 24 (00-121), respectively.ConclusionThis research provides profile of ten most severely hit countries by monkeypox transmission around the world and thus assists in epidemiological management. The prediction trends indicate that the confirmed cases in the USA may exceed than other contemporaries. Based on the findings of this study, it remains plausible to recommend that more robust health surveillance strategy is required to control the transmission flow of the virus especially in USA.
引用
收藏
页数:14
相关论文
共 50 条
  • [41] A new method for short-term traffic flow forecasting based on chaotic time series analysis
    Jiang, HF
    Wei, XY
    Zhang, Y
    ICEMI 2005: CONFERENCE PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS, VOL 3, 2005, : 65 - 68
  • [42] Functional time series approach for forecasting very short-term electricity demand
    Shang, Han Lin
    JOURNAL OF APPLIED STATISTICS, 2013, 40 (01) : 152 - 168
  • [43] Stacked Denoising Auto-Encoders for Short-Term Time Series Forecasting
    Romeu, Pablo
    Zamora-Martinez, Francisco
    Botella-Rocamora, Paloma
    Pardo, Juan
    ARTIFICIAL NEURAL NETWORKS, 2015, : 463 - 486
  • [44] A Bayesian network approach to time series forecasting of short-term traffic flows
    Zhang, CS
    Sun, SL
    Yu, GQ
    ITSC 2004: 7TH INTERNATIONAL IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, PROCEEDINGS, 2004, : 216 - 221
  • [45] Short-term forecasting based on a transformation and classification of traffic volume time series
    Wild, D
    INTERNATIONAL JOURNAL OF FORECASTING, 1997, 13 (01) : 63 - 72
  • [46] Bayesian time-series model for short-term traffic flow forecasting
    Ghosh, Bidisha
    Basu, Biswajit
    O'Mahony, Margaret
    JOURNAL OF TRANSPORTATION ENGINEERING, 2007, 133 (03) : 180 - 189
  • [47] Short-Term Forecasting of Bicycle Traffic Using Structural Time Series Models
    Doorley, Ronan
    Pakrashi, Vikram
    Caulfield, Brian
    Ghosh, Bidisha
    2014 IEEE 17TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2014, : 1764 - 1769
  • [48] Short-term time series forecasting based on the identification of skeleton algebraic sequences
    Ragulskis, Minvydas
    Lukoseviciute, Kristina
    Navickas, Zenonas
    Palivonaite, Rita
    NEUROCOMPUTING, 2011, 74 (10) : 1735 - 1747
  • [49] MPM: Multi Patterns Memory Model for Short-Term Time Series Forecasting
    Wang, Dezheng
    Liu, Rongjie
    Chen, Congyan
    Li, Shihua
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2025, 37 (01) : 438 - 448
  • [50] Hybrid Models for Short-Term Load Forecasting Using Clustering and Time Series
    Alkhatib, Wael
    Alhamoud, Alaa
    Boehnstedt, Doreen
    Steinmetz, Ralf
    ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2017, PT II, 2017, 10306 : 104 - 115