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

Abstract

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 (x103/μL)], fever (≥38°C), low platelet counts [< 100 (x103/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.

Machine learning and deep learning techniques to support the clinical diagnosis of arboviral diseases: A systematic review

“…Although these three are common arboviral diseases, no studies were found that carried out multi-classification considering these arboviral diseases or other arboviral types, such as West Nile virus, yellow fever virus, Saint Louis Encephalitis virus, Mayaro virus, Oropouche virus and others, showing that there are space for further investigations in this area. Most of works presented models for binary classification: Dengue or not [40][41][42][43][44][45]; DHF or not [46]; Chikungunya or not [47]; and Zika classified between "Discarded cases" and "Somewhat probable" for CZS [48]. It is interesting to note that the only work that deals with Zika is focused on CZS, not covering Zika in general.…”

“…As disadvantages, this type of model does not generalise well when using a large number of features, it is vulnerable to overfitting, and cannot solve non-linear problems, requiring a transformation of non-linear resources [74]. Two works employed Logistic Regression in the sample - [45] and [50].…”

“…Even when techniques are used to select attributes resulting in good model performance, the relationships between those attributes and the output classification may not directly track causal relationships in the real world [77]. One paper in the sample, Ho et al [45], uses a CNN, DenseNet. DenseNet is a CNN architecture in which each layer is connected to all the others within a dense block [78].…”

“…The data set comprised 4,894 records of clinical and laboratory data including 2,942 cases of laboratory-confirmed Dengue cases and 1,952 non-Dengue cases. Ho et al [45] analysed odds ratios to select four attributes and create a subset of data; two additional subsets were created with six and 11 attributes based on the initial subset. In the experiments, the data set with all attributes was also used for comparison purposes however there was no evidence that more attributes contributed to improved model performance.…”

“…Three exceptions were identified in our sample. Gambhir et al [43] and Ho et al [45] used data sets in which the number of Dengue cases is larger than non-Dengue; and Fahmi et al [50] used a large data set, in which there were more DHF cases than DF.…”