Proposal of a Clinical Decision Tree Algorithm Using Factors Associated with Severe Dengue Infection

Abstract

BackgroundWHO’s new classification in 2009: dengue with or without warning signs and severe dengue, has necessitated large numbers of admissions to hospitals of dengue patients which in turn has been imposing a huge economical and physical burden on many hospitals around the globe, particularly South East Asia and Malaysia where the disease has seen a rapid surge in numbers in recent years. Lack of a simple tool to differentiate mild from life threatening infection has led to unnecessary hospitalization of dengue patients.MethodsWe conducted a single-centre, retrospective study involving serologically confirmed dengue fever patients, admitted in a single ward, in Hospital Kuala Lumpur, Malaysia. Data was collected for 4 months from February to May 2014. Socio demography, co-morbidity, days of illness before admission, symptoms, warning signs, vital signs and laboratory result were all recorded. Descriptive statistics was tabulated and simple and multiple logistic regression analysis was done to determine significant risk factors associated with severe dengue.Results657 patients with confirmed dengue were analysed, of which 59 (9.0%) had severe dengue. Overall, the commonest warning sign were vomiting (36.1%) and abdominal pain (32.1%). Previous co-morbid, vomiting, diarrhoea, pleural effusion, low systolic blood pressure, high haematocrit, low albumin and high urea were found as significant risk factors for severe dengue using simple logistic regression. However the significant risk factors for severe dengue with multiple logistic regressions were only vomiting, pleural effusion, and low systolic blood pressure. Using those 3 risk factors, we plotted an algorithm for predicting severe dengue. When compared to the classification of severe dengue based on the WHO criteria, the decision tree algorithm had a sensitivity of 0.81, specificity of 0.54, positive predictive value of 0.16 and negative predictive of 0.96.ConclusionThe decision tree algorithm proposed in this study showed high sensitivity and NPV in predicting patients with severe dengue that may warrant admission. This tool upon further validation study can be used to help clinicians decide on further managing a patient upon first encounter. It also will have a substantial impact on health resources as low risk patients can be managed as outpatients hence reserving the scarce hospital beds and medical resources for other patients in need.

Predicting suicide attempts in adolescents with longitudinal clinical data and machine learning

“…Details on this algorithm will be described in Methods and in an online supplementary Appendix , but it is important to note that decision trees and their related ensemble, random forests – a collection of decision trees, are well‐validated and accepted machine learning approaches in biomedicine and in mental health applications. They have been used in genetic phenotyping, in infectious disease, in identifying factors of resilience in depression, and in suicide risk prediction including our prior research in an adult population (Bureau et al., ; Jeste et al., ; Tamibmaniam, Hussin, Cheah, Ng, & Muninathan, ; Walsh et al., ). They are favored for their ability to handle large datasets and the fact that they do not rely on specific assumptions for the underlying data that may or may not fit the data in question (Strobl, Malley, & Tutz, ).…”

Diagnostic accuracy and predictive value in differentiating the severity of dengue infection

“…A total of 26 included studies conducted between 1994 and 2017 were published between 2008 and 2018 . However, two studies were related, leaving a total of 25 studies of different settings .…”

Predicting the severity of dengue fever in children on admission based on clinical features and laboratory indicators: application of classification tree analysis

“…Another recent study, by Tamibmaniam et al, used simple logistic regression and identified three parameters, including vomiting, pleural effusion, and low systolic blood pressure, to predict severe dengue based on the 2009 WHO criteria [ 32 ]. This study did not specifically focus on children and included only female patients.…”