Sheng-Wen Huang1, Huey-Pin Tsai2,3, Su-Jhen Hung1, Wen-Chien Ko4, Jen-Ren Wang2,3,5,6. 1. National Mosquito-Borne Diseases Control Research Center, National Health Research Institutes, Tainan, Taiwan. 2. Department of Pathology, National Cheng Kung University Hospital, and College of Medicine, National Cheng Kung University, Tainan, Taiwan. 3. Department of Medical Laboratory Science and Biotechnology, National Cheng Kung University, Tainan, Taiwan. 4. Department of Internal Medicine, National Cheng Kung University Hospital, and College of Medicine, National Cheng Kung University, Tainan, Taiwan. 5. National Institute of Infectious Diseases and Vaccinology, National Health Research Institutes, Tainan, Taiwan. 6. Center of Infectious Disease and Signaling Research, National Cheng Kung University, Tainan, Taiwan.
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.
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.
Authors: Angel Balmaseda; Samantha N Hammond; Leonel Pérez; Yolanda Tellez; Saira Indira Saborío; Juan Carlos Mercado; Ricardo Cuadra; Julio Rocha; Maria Angeles Pérez; Sheyla Silva; Crisanta Rocha; Eva Harris Journal: Am J Trop Med Hyg Date: 2006-03 Impact factor: 2.345
Authors: Diego Allonso; Marcelo D F Meneses; Carlos A Fernandes; Davis F Ferreira; Ronaldo Mohana-Borges Journal: PLoS One Date: 2014-11-20 Impact factor: 3.240
Authors: Peifang Sun; Josefina García; Guillermo Comach; Maryanne T Vahey; Zhining Wang; Brett M Forshey; Amy C Morrison; Gloria Sierra; Isabel Bazan; Claudio Rocha; Stalin Vilcarromero; Patrick J Blair; Thomas W Scott; Daria E Camacho; Christian F Ockenhouse; Eric S Halsey; Tadeusz J Kochel Journal: PLoS Negl Trop Dis Date: 2013-07-11
Authors: Yiran E Liu; Sirle Saul; Shirit Einav; Purvesh Khatri; Aditya Manohar Rao; Makeda Lucretia Robinson; Olga Lucia Agudelo Rojas; Ana Maria Sanz; Michelle Verghese; Daniel Solis; Mamdouh Sibai; Chun Hong Huang; Malaya Kumar Sahoo; Rosa Margarita Gelvez; Nathalia Bueno; Maria Isabel Estupiñan Cardenas; Luis Angel Villar Centeno; Elsa Marina Rojas Garrido; Fernando Rosso; Michele Donato; Benjamin A Pinsky Journal: Genome Med Date: 2022-03-29 Impact factor: 11.117
Authors: Victor Edgar Fiestas Solórzano; Nieli Rodrigues da Costa Faria; Caroline Fernandes Dos Santos; Gladys Corrêa; Márcio da Costa Cipitelli; Marcos Dornelas Ribeiro; Luiz José de Souza; Paulo Vieira Damasco; Rivaldo Venâncio da Cunha; Flavia Barreto Dos Santos; Luzia Maria de Oliveira Pinto; Elzinandes Leal de Azeredo Journal: Viruses Date: 2021-09-08 Impact factor: 5.048