Comparing machine learning with case-control models to identify confirmed dengue cases

• Published in: PLoS neglected tropical diseases Vol. 14; no. 11; p. e0008843
• Main Authors: Ho, Tzong-Shiann, Weng, Ting-Chia, Wang, Jung-Der, Han, Hsieh-Cheng, Cheng, Hao-Chien, Yang, Chun-Chieh, Yu, Chih-Hen, Liu, Yen-Jung, Hu, Chien Hsiang, Huang, Chun-Yu, Chen, Ming-Hong, King, Chwan-Chuen, Oyang, Yen-Jen, Liu, Ching-Chuan
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.11.2020; Public Library of Science (PLoS)
• Subjects: Adolescent; Adult; Aged; Algorithms; Biology and life sciences; Blood tests; Case-Control Studies; Computer and Information Sciences; Datasets; Decision making; Dengue; Dengue - diagnosis; Dengue - epidemiology; Dengue fever; Developing Countries; Disease Outbreaks - statistics & numerical data; Epidemics; Epidemiological Monitoring; Feature selection; Female; Gender; Health surveillance; Hospitals; Human diseases; Humans; Illnesses; Laboratories; Learning algorithms; Machine Learning; Male; Medical research; Medicine and Health Sciences; Middle Aged; Models, Statistical; Patients; Physical Sciences; Public health; Public Health - methods; Research and Analysis Methods; Resource allocation; Statistical methods; Surveillance; Tropical diseases; Variables; Vector-borne diseases; Vital signs; Young Adult; Taiwan
• ISSN: 1935-2735; 1935-2727; 1935-2735
• DOI: 10.1371/journal.pntd.0008843

In recent decades, the global incidence of dengue has increased. Affected countries have responded with more effective surveillance strategies to detect outbreaks early, monitor the trends, and implement prevention and control measures. We have applied newly developed machine learning approaches to identify laboratory-confirmed dengue cases from 4,894 emergency department patients with dengue-like illness (DLI) who received laboratory tests. Among them, 60.11% (2942 cases) were confirmed to have dengue. Using just four input variables [age, body temperature, white blood cells counts (WBCs) and platelets], not only the state-of-the-art deep neural network (DNN) prediction models but also the conventional decision tree (DT) and logistic regression (LR) models delivered performances with receiver operating characteristic (ROC) curves areas under curves (AUCs) of the ranging from 83.75% to 85.87% [for DT, DNN and LR: 84.60% ± 0.03%, 85.87% ± 0.54%, 83.75% ± 0.17%, respectively]. Subgroup analyses found all the models were very sensitive particularly in the pre-epidemic period. Pre-peak sensitivities (<35 weeks) were 92.6%, 92.9%, and 93.1% in DT, DNN, and LR respectively. Adjusted odds ratios examined with LR for low WBCs [≤ 3.2 (x10 3 / μL )], fever (≥38°C), low platelet counts [< 100 (x10 3 / μL )], and elderly (≥ 65 years) were 5.17 [95% confidence interval (CI): 3.96–6.76], 3.17 [95%CI: 2.74–3.66], 3.10 [95%CI: 2.44–3.94], and 1.77 [95%CI: 1.50–2.10], respectively. Our prediction models can readily be used in resource-poor countries where viral/serologic tests are inconvenient and can also be applied for real-time syndromic surveillance to monitor trends of dengue cases and even be integrated with mosquito/environment surveillance for early warning and immediate prevention/control measures. In other words, a local community hospital/clinic with an instrument of complete blood counts (including platelets) can provide a sentinel screening during outbreaks. In conclusion, the machine learning approach can facilitate medical and public health efforts to minimize the health threat of dengue epidemics. However, laboratory confirmation remains the primary goal of surveillance and outbreak investigation.