METHODS: The most important climatic factors that contribute to dengue outbreaks were identified in the current work. Correlation analyses were performed in order to determine these factors and these factors were used as input parameters for machine learning models. Top five machine learning classification models (Bayes network (BN) models, support vector machine (SVM), RBF tree, decision table and naive Bayes) were chosen based on past research. The models were then tested and evaluated on the basis of 4-year data (January 2010 to December 2013) collected in Malaysia.
RESULTS: This research has two major contributions. A new risk factor, called the TempeRain factor (TRF), was identified and used as an input parameter for the model of dengue outbreak prediction. Moreover, TRF was applied to demonstrate its strong impact on dengue outbreaks. Experimental results showed that the Bayes Network model with the new meteorological risk factor identified in this study increased accuracy to 92.35% for predicting dengue outbreaks.
CONCLUSIONS: This research explored the factors used in dengue outbreak prediction systems. The major contribution of this study is identifying new significant factors that contribute to dengue outbreak prediction. From the evaluation result, we obtained a significant improvement in the accuracy of a machine learning model for dengue outbreak prediction.
MATERIALS AND METHODS: All suspected cases of COVID-19 that self-presented to hospitals or were cluster screened from 1st April to 31st May 2020 were included. Positive SARS-CoV-2 rRT-PCR was used as the diagnostic reference for COVID-19.
RESULTS: 540 individuals with suspected COVID-19 were recruited. Two-third of patients were identified through contact screening, while the rest presented sporadically. Overall COVID-19 positivity rate was 59.4% (321/540) which was higher in the cluster screened group (85.6% vs. 11.6%, p<0.001). Overall, cluster-screened COVID-19 cases were significantly younger, had fewer comorbidities and were less likely to be symptomatic than those present sporadically. Mortality was significantly lower in the cluster-screened COVID-19 cases (0.3% vs. 4.5%, p<0.05). A third of all chest radiographs in confirmed COVID-19 cases were abnormal, with consolidation, ground-glass opacities or both predominating in the peripheral lower zones. The WHO suspected case definition for COVID-19 accurately classified 35.4% of all COVID-19 patients, a rate not improved by the addition of baseline radiographic data. Misclassification rate was higher among the cluster-associated cases (80.6%) compared to sporadic cases (35.3%).
CONCLUSION: COVID-19 cases in Malaysia identified by active tracing of community cluster outbreaks had lower mortality rate. The WHO suspected COVID-19 performed poorly in this setting even when chest radiographic information was available, a finding that has implications for future spikes of the disease in countries with similar transmission characteristics.
METHODS: Data was sourced from the GitHub repository and the Ministry of Health's official COVID-19 website. The study period was from the beginning of the outbreak in Malaysia, which began during Epidemiological Week (Ep Wk) 4 in 2020, to the last Ep Wk 18 in 2022. Data were aggregated by Ep Wk and analyzed in terms of COVID-19 cases, deaths, ICU admissions, ventilator requirements, testing, incidence rate, death rate, case fatality rate (CFR) and test positivity rate by years (2020 and 2022) and for each outbreak of COVID-19.
RESULTS: A total of 4,456,736 cases, 35,579 deaths and 58,906,954 COVID-19 tests were reported for the period from 2020 to 2022. The COVID-19 incidence rate, death rate, CFR and test positivity rate were reported at 1.085 and 0.009 per 1,000 populations, 0.80 and 7.57%, respectively, for the period from 2020 to 2022. Higher cases, deaths, testing, incidence/death rate, CFR and test positivity rates were reported in 2021 and during the Delta outbreak. This is evident by the highest number of COVID-19 cases, ICU admissions, ventilatory requirements and deaths observed during the Delta outbreak.
CONCLUSION: The Delta outbreak was the most severe compared to other outbreaks in Malaysia's study period. In addition, this study provides evidence that outbreaks of COVID-19, which are caused by highly virulent and transmissible variants, tend to be more severe and devastating if these outbreaks are not controlled early on. Therefore, close monitoring of key epidemiological indicators, as reported in this study, is essential in the control and management of future COVID-19 outbreaks in Malaysia.