Severity Index for Suspected Arbovirus (SISA): Machine learning for accurate prediction of hospitalization in subjects suspected of arboviral infection

Abstract

Background Dengue, chikungunya, and Zika are arboviruses of major global health concern. Decisions regarding the clinical management of suspected arboviral infection are challenging in resource-limited settings, particularly when deciding on patient hospitalization. The objective of this study was to determine if hospitalization of individuals with suspected arboviral infections could be predicted using subject intake data. Methodology/Principal findings Two prediction models were developed using data from a surveillance study in Machala, a city in southern coastal Ecuador with a high burden of arboviral infections. Data were obtained from subjects who presented at sentinel medical centers with suspected arboviral infection (November 2013 to September 2017). The first prediction model-called the Severity Index for Suspected Arbovirus (SISA)-used only demographic and symptom data. The second prediction model-called the Severity Index for Suspected Arbovirus with Laboratory (SISAL)-incorporated laboratory data. These models were selected by comparing the prediction ability of seven machine learning algorithms; the area under the receiver operating characteristic curve from the prediction of a test dataset was used to

SIMON: open-source knowledge discovery platform

“…The drowsiness contributed the most to the top-performing SISA model, confirming the findings from the original study 44 (Supplementary table 12). To standardize the process for evaluation of the features and their contribution to the models, we implemented the variable importance score evaluation functions from the caret library 33 .…”

“…Training set is used for building models, validation set is used for hyperparameter tuning and finally, models are evaluated in an unbiased way using the test, also known as holdout set that has never been used in training. Beside the standardized ML process, the initial install version offers a set of core components specifically suited for analysis of biomedical data, such as multiset intersection function for integration of data with many missing values 41 (https://cran.r-project.org/web/packages/mulset/index.html), method for identifying differentially expressed genes using significance analysis in microarrays (SAM) 42 We demonstrate the accuracy, ease of use and power of SIMON on five different biomedical datasets and build predictive models for arboviral infection severity (SISA) 44 , the identification of the cellular immune signature associated with a high-level of physical activity (Cyclists) 45 , the determination of the humoral responses that mediate protection against Salmonella Typhi infection (VAST) 46 , early-stage detection of colorectal cancer from microbiome data (Zeller) 47,48 , and for the detection of liver hepatocellular carcinoma cells (LIHC) 49 ( Fig. 1 b, c, d, e, Supplementary protocol).…”

SIMON: Open-Source Knowledge Discovery Platform

“…We demonstrate the accuracy, ease of use, and power of SIMON on five different biomedical datasets and build predictive models for arboviral infection severity (SISA), 42 the identification of the cellular immune signature associated with a high-level of physical activity (Cyclists), 43 the determination of the humoral responses that mediate protection against Salmonella Typhi infection (VAST), 44 early stage detection of colorectal cancer from microbiome data (Zeller), 45 , 46 and the detection of liver hepatocellular carcinoma cells (LIHC) 47 ( Figure 1 B–1E; Supplemental Information , Videos S1 and S6 ). To build models using the SISA dataset containing clinical parameters (described in the Experimental Procedures and available as Table S2 ), 11 ML algorithms were used, 5 from the original publication 42 (treebag, k nearest neighbors, random forest, stochastic generalized boosting model, and neural network) and, in addition, “sda,” shrinkage discriminant analysis; “hdda,” high-dimensional discriminant analysis; “svmLinear2,” support vector machine with linear kernel; “pcaNNet,” neural networks with feature extraction; “LogitBoost,” boosted logistic regression, and naive Bayes. Due to the unified ML process for training, tuning, and evaluating predictive models, users can test a variety of ML algorithms in SIMON.…”

Assessing the risk of dengue severity using demographic information and laboratory test results with machine learning

“…In addition to the soluble markers in patient serum, recent investigations have identified biomarkers associated with severe dengue development via microarray-based analysis to analyze host gene expression in peripheral blood samples from patients with different disease severities [57][58][59][60][61][62][63][64][65][66][67]. By combining results retrieved from patients, including demographic characteristics, dengue warning signs, other symptoms or signs, and laboratory features associated with severe dengue, researchers have further applied scoring systems to evaluate the potential for severe dengue with high performance [36,58,68]. In contrast, our prediction system applied patient information, including demographic characteristics (age and sex) and laboratory test results (NS1 antigen and anti-DENV IgM/IgG antibodies) obtained from rapid tests.…”

“…The advantages of artificial intelligence include improved medical treatment of patients and reduced duration of diagnosis after patients are examined using medical imaging or laboratory tests. However, very few artificial intelligence-based approaches or ML methods have been developed to predict dengue severity thus far [ 36 ]. Accordingly, in this study, we retrospectively established a rapid prognosis system for severe dengue using an ML approach according to rapid diagnostic test results and demographic characteristics of the patients.…”