Dataset Information

Modelling monthly influenza cases in Malaysia.

ABSTRACT: The increasing trend in the number new cases of influenza every year as reported by WHO is concerning, especially in Malaysia. To date, there is no local research under healthcare sector that implements the time series forecasting methods to predict future disease outbreak in Malaysia, specifically influenza. Addressing the problem could increase awareness of the disease and could help healthcare workers to be more prepared in preventing the widespread of the disease. This paper intends to perform a hybrid ARIMA-SVR approach in forecasting monthly influenza cases in Malaysia. Autoregressive Integrated Moving Average (ARIMA) model (using Box-Jenkins method) and Support Vector Regression (SVR) model were used to capture the linear and nonlinear components in the monthly influenza cases, respectively. It was forecasted that the performance of the hybrid model would improve. The data from World Health Organization (WHO) websites consisting of weekly Influenza Serology A cases in Malaysia from the year 2006 until 2019 have been used for this study. The data were recategorized into monthly data. The findings of the study showed that the monthly influenza cases could be efficiently forecasted using three comparator models as all models outperformed the benchmark model (Naïve model). However, SVR with linear kernel produced the lowest values of RMSE and MAE for the test dataset suggesting the best performance out of the other comparators. This suggested that SVR has the potential to produce more consistent results in forecasting future values when compared with ARIMA and the ARIMA-SVR hybrid model.

SUBMITTER: Norrulashikin MA

PROVIDER: S-EPMC8294481 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe Western Pacific Region (WPR) is exposed each year to seasonal influenza and is often the source of new influenza virus variants and novel pathogen emergence. National influenza surveillance systems play a critical role in detecting emerging viruses, monitoring influenza epidemics, improving public disease awareness and promoting pandemic preparedness, but vary widely across WPR countries. The aim of this study is to improve existing influenza surveillance systems by systematically comparing selected WPR influenza surveillance systems.MethodsThree national influenza surveillance systems with different levels of development (Australia, China and Malaysia) were compared and their adherence to World Health Organization (WHO) guidance was evaluated using a structured framework previously tested in several European countries consisting of seven surveillance sub-systems, 19 comparable outcomes and five evaluation criteria. Based on the results, experts from the Asia-Pacific Alliance for the Control of Influenza (APACI) issued recommendations for the improvement of existing surveillance systems.ResultsAustralia demonstrated the broadest scope of influenza surveillance followed by China and Malaysia. In Australia, surveillance tools covered all sub-systems. In China, surveillance did not cover non-medically attended respiratory events, primary care consultations, and excess mortality modelling. In Malaysia, surveillance consisted of primary care and hospital sentinel schemes. There were disparities between the countries across the 5 evaluation criteria, particularly regarding data granularity from health authorities, information on data representativeness, and data communication, especially the absence of publicly available influenza epidemiological reports in Malaysia. This dual approach describing the scope of surveillance and evaluating the adherence to WHO guidance enabled APACI experts to make a number of recommendations for each country that included but were not limited to introducing new surveillance tools, broadening the use of specific existing surveillance tools, collecting and sharing data on virus characteristics, developing immunization status registries, and improving public health communication.ConclusionsInfluenza monitoring in Australia, China, and Malaysia could benefit from the expansion of existing surveillance sentinel schemes, the broadened use of laboratory confirmation and the introduction of excess-mortality modelling. The results from the evaluation can be used as a basis to support expert recommendations and to enhance influenza surveillance capabilities.

Project description:BACKGROUND:Understanding seasonality of tuberculosis (TB) epidemics may lead to identify potentially modifiable risk factors. Studies conducted outside Japan have found seasonal variation among reported TB cases, with peaks in spring and summer and low prevalence in fall and winter. One hypothesis regarding spring or summer peaks in TB epidemics is that TB transmission likely increases in winter because of indoor crowding and poor ventilation, with development of primary TB among socially vulnerable people in spring and summer. Another plausible explanation is that vitamin D deficiency in winter depresses immunity, increasing the TB reactivation risk in these seasons. Previous studies suggest latitude-dependent factors, including reduced winter sunlight and its effect on vitamin D levels. Here, we investigated mechanisms of seasonality in TB epidemics in Japan, according to the effects of crowding and latitude. METHODS:We used time-series analysis consisting of spectral analysis and least-squares method, to analyse geographically specific monthly number of newly registered cases of all forms of active TB in all 47 prefectures of Japan during 1998-2015. RESULTS:In all power spectral densities for the 47 prefectures, spectral lines were observed at frequency positions corresponding to a 1-year cycle. The degree of this seasonality was associated with population density. We did not detect greater amplitude of seasonality at higher latitudes, suggesting that latitude-dependent factors, including reduced winter sunlight and its potential effect on vitamin D levels, do not contribute significantly to seasonality in Japan. DISCUSSION AND CONCLUSION:In districts with high population density, measures are needed to address two specific types of active infection risk in adolescents and middle-aged adults: (i) public transport use, and (ii) irregular employment with no periodic medical examinations. To control active TB epidemics, investigating periodic structures in the temporal patterns of active TB in each district and each age group is important.

Dataset Information

Modelling monthly influenza cases in Malaysia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets