Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness

Lukas Tanner, Mark Schreiber, Jenny G.H. Low, Adrian Ong, Thomas Tolfvenstam, Yee Ling Lai, Lee Ching Ng, Yee Sin Leo, Le Thi Puong, Subhash G. Vasudevan, Cameron P. Simmons, Martin L. Hibberd, Eng Eong Ooi

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background: Dengue is re-emerging throughout the tropical world, causing frequent recurrent epidemics. The initial clinical manifestation of dengue often is confused with other febrile states confounding both clinical management and disease surveillance. Evidence-based triage strategies that identify individuals likely to be in the early stages of dengue illness can direct patient stratification for clinical investigations, management, and virological surveillance. Here we report the identification of algorithms that differentiate dengue from other febrile illnesses in the primary care setting and predict severe disease in adults. Methods and Findings: A total of 1,200 patients presenting in the first 72 hours of acute febrile illness were recruited and followed up for up to a 4-week period prospectively; 1,012 of these were recruited from Singapore and 188 from Vietnam. Of these, 364 were dengue RT-PCR positive; 173 had dengue fever, 171 had dengue hemorrhagic fever, and 20 had dengue shock syndrome as final diagnosis. Using a C4.5 decision tree classifier for analysis of all clinical, haematological, and virological data, we obtained a diagnostic algorithm that differentiates dengue from non-dengue febrile illness with an accuracy of 84.7%. The algorithm can be used differently in different disease prevalence to yield clinically useful positive and negative predictive values. Furthermore, an algorithm using platelet count, crossover threshold value of a real-time RT-PCR for dengue viral RNA, and presence of pre-existing anti-dengue IgG antibodies in sequential order identified cases with sensitivity and specificity of 78.2% and 80.2%, respectively, that eventually developed thrombocytopenia of 50,000 platelet/mm3 or less, a level previously shown to be associated with haemorrhage and shock in adults with dengue fever. Conclusion: This study shows a proof-of-concept that decision algorithms using simple clinical and haematological parameters can predict diagnosis and prognosis of dengue disease, a finding that could prove useful in disease management and surveillance.

Original languageEnglish
Article numbere196
JournalPLoS Neglected Tropical Diseases
Volume2
Issue number3
DOIs
Publication statusPublished - 1 Mar 2008

Cite this

Tanner, L., Schreiber, M., Low, J. G. H., Ong, A., Tolfvenstam, T., Lai, Y. L., ... Ooi, E. E. (2008). Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness. PLoS Neglected Tropical Diseases, 2(3), [e196]. https://doi.org/10.1371/journal.pntd.0000196
Tanner, Lukas ; Schreiber, Mark ; Low, Jenny G.H. ; Ong, Adrian ; Tolfvenstam, Thomas ; Lai, Yee Ling ; Ng, Lee Ching ; Leo, Yee Sin ; Puong, Le Thi ; Vasudevan, Subhash G. ; Simmons, Cameron P. ; Hibberd, Martin L. ; Ooi, Eng Eong. / Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness. In: PLoS Neglected Tropical Diseases. 2008 ; Vol. 2, No. 3.
@article{ab381bb54b804f47aadd4460134d3925,
title = "Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness",
abstract = "Background: Dengue is re-emerging throughout the tropical world, causing frequent recurrent epidemics. The initial clinical manifestation of dengue often is confused with other febrile states confounding both clinical management and disease surveillance. Evidence-based triage strategies that identify individuals likely to be in the early stages of dengue illness can direct patient stratification for clinical investigations, management, and virological surveillance. Here we report the identification of algorithms that differentiate dengue from other febrile illnesses in the primary care setting and predict severe disease in adults. Methods and Findings: A total of 1,200 patients presenting in the first 72 hours of acute febrile illness were recruited and followed up for up to a 4-week period prospectively; 1,012 of these were recruited from Singapore and 188 from Vietnam. Of these, 364 were dengue RT-PCR positive; 173 had dengue fever, 171 had dengue hemorrhagic fever, and 20 had dengue shock syndrome as final diagnosis. Using a C4.5 decision tree classifier for analysis of all clinical, haematological, and virological data, we obtained a diagnostic algorithm that differentiates dengue from non-dengue febrile illness with an accuracy of 84.7{\%}. The algorithm can be used differently in different disease prevalence to yield clinically useful positive and negative predictive values. Furthermore, an algorithm using platelet count, crossover threshold value of a real-time RT-PCR for dengue viral RNA, and presence of pre-existing anti-dengue IgG antibodies in sequential order identified cases with sensitivity and specificity of 78.2{\%} and 80.2{\%}, respectively, that eventually developed thrombocytopenia of 50,000 platelet/mm3 or less, a level previously shown to be associated with haemorrhage and shock in adults with dengue fever. Conclusion: This study shows a proof-of-concept that decision algorithms using simple clinical and haematological parameters can predict diagnosis and prognosis of dengue disease, a finding that could prove useful in disease management and surveillance.",
author = "Lukas Tanner and Mark Schreiber and Low, {Jenny G.H.} and Adrian Ong and Thomas Tolfvenstam and Lai, {Yee Ling} and Ng, {Lee Ching} and Leo, {Yee Sin} and Puong, {Le Thi} and Vasudevan, {Subhash G.} and Simmons, {Cameron P.} and Hibberd, {Martin L.} and Ooi, {Eng Eong}",
year = "2008",
month = "3",
day = "1",
doi = "10.1371/journal.pntd.0000196",
language = "English",
volume = "2",
journal = "PLoS Neglected Tropical Diseases",
issn = "1935-2727",
publisher = "Public Library of Science",
number = "3",

}

Tanner, L, Schreiber, M, Low, JGH, Ong, A, Tolfvenstam, T, Lai, YL, Ng, LC, Leo, YS, Puong, LT, Vasudevan, SG, Simmons, CP, Hibberd, ML & Ooi, EE 2008, 'Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness' PLoS Neglected Tropical Diseases, vol. 2, no. 3, e196. https://doi.org/10.1371/journal.pntd.0000196

Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness. / Tanner, Lukas; Schreiber, Mark; Low, Jenny G.H.; Ong, Adrian; Tolfvenstam, Thomas; Lai, Yee Ling; Ng, Lee Ching; Leo, Yee Sin; Puong, Le Thi; Vasudevan, Subhash G.; Simmons, Cameron P.; Hibberd, Martin L.; Ooi, Eng Eong.

In: PLoS Neglected Tropical Diseases, Vol. 2, No. 3, e196, 01.03.2008.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness

AU - Tanner, Lukas

AU - Schreiber, Mark

AU - Low, Jenny G.H.

AU - Ong, Adrian

AU - Tolfvenstam, Thomas

AU - Lai, Yee Ling

AU - Ng, Lee Ching

AU - Leo, Yee Sin

AU - Puong, Le Thi

AU - Vasudevan, Subhash G.

AU - Simmons, Cameron P.

AU - Hibberd, Martin L.

AU - Ooi, Eng Eong

PY - 2008/3/1

Y1 - 2008/3/1

N2 - Background: Dengue is re-emerging throughout the tropical world, causing frequent recurrent epidemics. The initial clinical manifestation of dengue often is confused with other febrile states confounding both clinical management and disease surveillance. Evidence-based triage strategies that identify individuals likely to be in the early stages of dengue illness can direct patient stratification for clinical investigations, management, and virological surveillance. Here we report the identification of algorithms that differentiate dengue from other febrile illnesses in the primary care setting and predict severe disease in adults. Methods and Findings: A total of 1,200 patients presenting in the first 72 hours of acute febrile illness were recruited and followed up for up to a 4-week period prospectively; 1,012 of these were recruited from Singapore and 188 from Vietnam. Of these, 364 were dengue RT-PCR positive; 173 had dengue fever, 171 had dengue hemorrhagic fever, and 20 had dengue shock syndrome as final diagnosis. Using a C4.5 decision tree classifier for analysis of all clinical, haematological, and virological data, we obtained a diagnostic algorithm that differentiates dengue from non-dengue febrile illness with an accuracy of 84.7%. The algorithm can be used differently in different disease prevalence to yield clinically useful positive and negative predictive values. Furthermore, an algorithm using platelet count, crossover threshold value of a real-time RT-PCR for dengue viral RNA, and presence of pre-existing anti-dengue IgG antibodies in sequential order identified cases with sensitivity and specificity of 78.2% and 80.2%, respectively, that eventually developed thrombocytopenia of 50,000 platelet/mm3 or less, a level previously shown to be associated with haemorrhage and shock in adults with dengue fever. Conclusion: This study shows a proof-of-concept that decision algorithms using simple clinical and haematological parameters can predict diagnosis and prognosis of dengue disease, a finding that could prove useful in disease management and surveillance.

AB - Background: Dengue is re-emerging throughout the tropical world, causing frequent recurrent epidemics. The initial clinical manifestation of dengue often is confused with other febrile states confounding both clinical management and disease surveillance. Evidence-based triage strategies that identify individuals likely to be in the early stages of dengue illness can direct patient stratification for clinical investigations, management, and virological surveillance. Here we report the identification of algorithms that differentiate dengue from other febrile illnesses in the primary care setting and predict severe disease in adults. Methods and Findings: A total of 1,200 patients presenting in the first 72 hours of acute febrile illness were recruited and followed up for up to a 4-week period prospectively; 1,012 of these were recruited from Singapore and 188 from Vietnam. Of these, 364 were dengue RT-PCR positive; 173 had dengue fever, 171 had dengue hemorrhagic fever, and 20 had dengue shock syndrome as final diagnosis. Using a C4.5 decision tree classifier for analysis of all clinical, haematological, and virological data, we obtained a diagnostic algorithm that differentiates dengue from non-dengue febrile illness with an accuracy of 84.7%. The algorithm can be used differently in different disease prevalence to yield clinically useful positive and negative predictive values. Furthermore, an algorithm using platelet count, crossover threshold value of a real-time RT-PCR for dengue viral RNA, and presence of pre-existing anti-dengue IgG antibodies in sequential order identified cases with sensitivity and specificity of 78.2% and 80.2%, respectively, that eventually developed thrombocytopenia of 50,000 platelet/mm3 or less, a level previously shown to be associated with haemorrhage and shock in adults with dengue fever. Conclusion: This study shows a proof-of-concept that decision algorithms using simple clinical and haematological parameters can predict diagnosis and prognosis of dengue disease, a finding that could prove useful in disease management and surveillance.

UR - http://www.scopus.com/inward/record.url?scp=48949118005&partnerID=8YFLogxK

U2 - 10.1371/journal.pntd.0000196

DO - 10.1371/journal.pntd.0000196

M3 - Article

VL - 2

JO - PLoS Neglected Tropical Diseases

JF - PLoS Neglected Tropical Diseases

SN - 1935-2727

IS - 3

M1 - e196

ER -