Decision Algorithms for Diagnosing and Predicting Outcomes of Dengue Fever
Author Information
Author(s): Tanner Lukas, Schreiber Mark, Low Jenny G. H., Ong Adrian, Tolfvenstam Thomas, Lai Yee Ling, Ng Lee Ching, Leo Yee Sin, Thi Puong Le, Vasudevan Subhash G., Simmons Cameron P., Hibberd Martin L., Ooi Eng Eong
Primary Institution: Novartis Institute for Tropical Diseases, Singapore
Hypothesis
Can decision tree algorithms effectively differentiate dengue from other febrile illnesses and predict severe disease in adults during the early phase of illness?
Conclusion
The study demonstrates that decision algorithms using simple clinical and haematological parameters can effectively predict the diagnosis and prognosis of dengue disease.
Supporting Evidence
- The diagnostic algorithm achieved an accuracy of 84.7% in differentiating dengue from non-dengue febrile illness.
- The algorithm predicted severe disease with a sensitivity of 78.2% and specificity of 80.2%.
- The study included a diverse cohort from both Singapore and Vietnam, enhancing its applicability.
Takeaway
Doctors can use a special set of rules to tell if someone has dengue fever early on, which helps them take better care of patients.
Methodology
The study used a C4.5 decision tree classifier to analyze clinical, haematological, and virological data from patients presenting with acute febrile illness.
Potential Biases
Potential biases in patient selection and data collection methods could affect the results.
Limitations
The study primarily focused on adult cases in Singapore and may not be generalizable to all populations.
Participant Demographics
The study included 1,200 patients, with 1,012 from Singapore and 188 from Vietnam, primarily adults over 18 years old.
Statistical Information
P-Value
p<0.05
Confidence Interval
95% CI
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website