Search

Establishing reliable early warning models for severe dengue cases is a high priority to facilitate triage in dengue-endemic areas and optimal use of limited resources. However, few studies have identified the complex interactive relationship between potential risk factors and severe dengue. This research aimed to assess the potential risk factors and detect their high-order combinative effects on severe dengue. A structured questionnaire was used to collect detailed dengue outbreak data from eight representative hospitals in Dhaka, Bangladesh, in 2019. Logistic regression and machine learning models were used to examine the complex effects of demographic characteristics, clinical symptoms, and biochemical markers on severe dengue. A total of 1,090 dengue cases (158 severe and 932 non-severe) were included in this study. Dyspnoea (Odds Ratio [OR] = 2.87, 95% Confidence Interval [CI]: 1.72 to 4.77), plasma leakage (OR = 3.61, 95% CI: 2.12 to 6.15), and hemorrhage (OR = 2.33, 95% CI: 1.46 to 3.73) were positively and significantly associated with the occurrence of severe dengue. Classification and regression tree models showed that the probability of occurrence of severe dengue cases ranged from 7% (age >12.5 years without plasma leakage) to 92.9% (age ≤12.5 years with dyspnoea and plasma leakage). The random forest model indicated that age was the most important factor in predicting severe dengue, followed by education, plasma leakage, platelet, and dyspnoea. The research provides new evidence to identify key risk factors contributing to severe dengue cases, which could be beneficial to clinical doctors to identify and predict the severity of dengue early. Author summary: Dengue is a mosquito-borne viral infection mostly in warm and tropical regions, which has been listed as one of the top ten global health threats by the WHO. Among neglected tropical diseases, the mortality of dengue is on the rise. Severe dengue (typically manifested by bleeding, organ dysfunction, and plasma leakage) has become a leading cause of hospitalization for children and adults. There is a higher risk of death if severe dengue cases are not appropriately managed. Therefore, finding biomarkers that can reliably predict the development of severe dengue in symptomatic individuals is one of the main focuses of current research efforts. We found that dyspnoea, plasma leakage, and hemorrhage were the independent risk factors of severe dengue. The predictive probability of occurrence of severe dengue achieved 92.9% among people aged ≤ 12.5 years with dyspnoea and plasma leakage. Establishing an early warning system for severe dengue based on these factors is essential for triaging in endemic areas. The findings of this study identified possible combinations of severe dengue, which would provide enhanced insight into clinical management and inform prevention programming for severe dengue. [ABSTRACT FROM AUTHOR]