Assessing the risk of dengue severity using demographic information and laboratory test results with machine learning

Abstract

Background Dengue virus causes a wide spectrum of disease, which ranges from subclinical disease to severe dengue shock syndrome. However, estimating the risk of severe outcomes using clinical presentation or laboratory test results for rapid patient triage remains a challenge. Here, we aimed to develop prognostic models for severe dengue using machine learning, according to demographic information and clinical laboratory data of patients with dengue. Methodology/Principal findings Out of 1,581 patients in the National Cheng Kung University Hospital with suspected dengue infections and subjected to NS1 antigen, IgM and IgG, and qRT-PCR tests, 798 patients including 138 severe cases were enrolled in the study. The primary target outcome was severe dengue. Machine learning models were trained and tested using the patient dataset that included demographic information and qualitative laboratory test results collected on day 1 when they sought medical advice. To develop prognostic models, we applied various machine learning methods, including logistic regression, random forest, gradient boosting machine, support vector classifier, and artificial neural network, and compared the performance of the methods. The artificial neural network showed the highest average discrimination area under the receiver operating characteristic curve (0.8324 ± 0.0268) and balance accuracy (0.7523 ± 0.0273). According to the model explainer that analyzed the contributions/co-contributions of the different factors, patient age and dengue NS1 antigenemia were the two most important risk factors associated with severe dengue. Additionally, co-existence of anti-dengue IgM and IgG in patients with dengue increased the probability of severe dengue. Conclusions/Significance We developed prognostic models for the prediction of dengue severity in patients, using machine learning. The discriminative ability of the artificial neural network exhibited good performance for severe dengue prognosis. This model could help clinicians obtain a rapid prognosis during dengue outbreaks. However, the model requires further validation using external cohorts in future studies.

Assessment of the Risk of Severe Dengue Using Intrahost Viral Population in Dengue Virus Serotype 2 Patients via Machine Learning

“…In this study, we retrospectively included 65 patients from the 2015 Taiwan outbreak, but all patients were infected by the Cosmopolitan genotype strains of DENV-2 in a close cluster. In addition to potential bias arising due to a single predominant strain in the outbreak, elderly individuals constituted the major age group among the patients with severe dengue in the Taiwan outbreak, in contrast to the severe cases in children in southeastern Asia (Hoang et al, 2010) and South America (Allonso et al, 2014) as previously described (Tsai et al, 2016;Huang S. W. et al, 2020). Our dataset only came from the patients who seek medical advice in the hospital, which might exclude the mild cases who did not go to the hospital and resulted in the potential loss of true intrahost dynamics among mild cases.…”

Different Profiles of Cytokines, Chemokines and Coagulation Mediators Associated with Severity in Brazilian Patients Infected with Dengue Virus

“…Although it has been established that the circulating levels of NS1 antigen are positively correlated with DENV viremia [ 36 ] and are associated with severity [ 37 , 38 ], there is still debate about its usefulness as a biomarker [ 39 ]. In our study, no significant difference was found in the circulating levels of the NS1 antigen between the dengue patient groups.…”

Which Plagues are Coming Next?

“…Dengue virus (DENV) occurs in over 100 countries causing nearly 100 million acute infections and half a million deaths each year [26,27]. The disease itself is characterized by an acute fever which is transmitted from mosquitos (Ae.…”

“…Unfortunately, individuals infected with one serotype only produce antibodies capable of neutralizing that specific serotype, leaving the individual unprotected against the other 3 serotypes. Moreover, through antibody-dependent enhancement, re-infection by a different serotype increases the risk of severe dengue disease [26]. In 2019 a vaccine against DENV was approved for individuals aged 9-45 years and who had experienced a prior DENV infection.…”