4
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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 (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.

          Author summary

          Identifying dengue cases early is crucial but challenging for healthcare professionals. This challenge is increased during large epidemics and is a particular problem in non-endemic areas with limited experienced staff. To improve dengue diagnosis, we investigated how to exploit machine learning (ML)-based prediction models and identified four key variables [age, fever, white blood cell counts (WBCs), and platelet counts], which are compatible with clinical and epidemiological knowledge. With these variables, the ML prediction models [decision tree (DT), deep neural network (DNN)] and the logistic regression model developed for identifying laboratory-confirmed dengue cases produced areas under curve (AUCs) of the receiver operating characteristic (ROC) curves ranging from 83.75% to 85.87%. This implies that the prediction models may serve as a pivotal component of an integrated dengue surveillance system and they required only a single complete blood count (CBC) examination. The sensitivities, positive prediction values, and accuracies for major risk factors in the two machine learning models were close to those of the regression models. For future applications, the DNN models with superior performance can be employed at epidemic sites with adequate computer facilities, while the DT and regression models with interpretable prediction logic can be employed at sites with limited or no computer facilities. Artificial intelligence and clinical parameters identified from this study may aid when laboratories are overwhelmed, but should never replace laboratory confirmation.

          Related collections

          Most cited references63

          • Record: found
          • Abstract: found
          • Article: not found

          Epidemiological and clinical characteristics of 99 cases of 2019 novel coronavirus pneumonia in Wuhan, China: a descriptive study

          Summary Background In December, 2019, a pneumonia associated with the 2019 novel coronavirus (2019-nCoV) emerged in Wuhan, China. We aimed to further clarify the epidemiological and clinical characteristics of 2019-nCoV pneumonia. Methods In this retrospective, single-centre study, we included all confirmed cases of 2019-nCoV in Wuhan Jinyintan Hospital from Jan 1 to Jan 20, 2020. Cases were confirmed by real-time RT-PCR and were analysed for epidemiological, demographic, clinical, and radiological features and laboratory data. Outcomes were followed up until Jan 25, 2020. Findings Of the 99 patients with 2019-nCoV pneumonia, 49 (49%) had a history of exposure to the Huanan seafood market. The average age of the patients was 55·5 years (SD 13·1), including 67 men and 32 women. 2019-nCoV was detected in all patients by real-time RT-PCR. 50 (51%) patients had chronic diseases. Patients had clinical manifestations of fever (82 [83%] patients), cough (81 [82%] patients), shortness of breath (31 [31%] patients), muscle ache (11 [11%] patients), confusion (nine [9%] patients), headache (eight [8%] patients), sore throat (five [5%] patients), rhinorrhoea (four [4%] patients), chest pain (two [2%] patients), diarrhoea (two [2%] patients), and nausea and vomiting (one [1%] patient). According to imaging examination, 74 (75%) patients showed bilateral pneumonia, 14 (14%) patients showed multiple mottling and ground-glass opacity, and one (1%) patient had pneumothorax. 17 (17%) patients developed acute respiratory distress syndrome and, among them, 11 (11%) patients worsened in a short period of time and died of multiple organ failure. Interpretation The 2019-nCoV infection was of clustering onset, is more likely to affect older males with comorbidities, and can result in severe and even fatal respiratory diseases such as acute respiratory distress syndrome. In general, characteristics of patients who died were in line with the MuLBSTA score, an early warning model for predicting mortality in viral pneumonia. Further investigation is needed to explore the applicability of the MuLBSTA score in predicting the risk of mortality in 2019-nCoV infection. Funding National Key R&D Program of China.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            An introduction to ROC analysis

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Mastering the game of Go with deep neural networks and tree search.

              The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses 'value networks' to evaluate board positions and 'policy networks' to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.
                Bookmark

                Author and article information

                Contributors
                Role: ConceptualizationRole: Data curationRole: Funding acquisitionRole: Writing – original draftRole: Writing – review & editing
                Role: ConceptualizationRole: Data curationRole: Writing – original draft
                Role: ConceptualizationRole: Writing – review & editing
                Role: Data curationRole: Project administration
                Role: Data curationRole: Formal analysisRole: MethodologyRole: SoftwareRole: Validation
                Role: Data curationRole: Formal analysisRole: Validation
                Role: Data curationRole: Writing – original draft
                Role: Data curationRole: Validation
                Role: Data curationRole: Software
                Role: Data curationRole: Formal analysisRole: SoftwareRole: Validation
                Role: Data curationRole: Software
                Role: ConceptualizationRole: SupervisionRole: Writing – original draftRole: Writing – review & editing
                Role: ConceptualizationRole: SupervisionRole: Writing – original draftRole: Writing – review & editing
                Role: ConceptualizationRole: ResourcesRole: SupervisionRole: Writing – review & editing
                Role: Editor
                Journal
                PLoS Negl Trop Dis
                PLoS Negl Trop Dis
                plos
                plosntds
                PLoS Neglected Tropical Diseases
                Public Library of Science (San Francisco, CA USA )
                1935-2727
                1935-2735
                10 November 2020
                November 2020
                : 14
                : 11
                : e0008843
                Affiliations
                [1 ] Department of Pediatrics, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan, Republic of China
                [2 ] Center of Infectious Disease and Signaling Research, National Cheng Kung University, Tainan, Taiwan, Republic of China
                [3 ] Department of Occupational and Environmental Medicine, National Cheng Kung University Hospital, Tainan, Taiwan, Republic of China
                [4 ] Department of Family Medicine, National Cheng Kung University Hospital, Tainan, Taiwan, Republic of China
                [5 ] Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan, Republic of China
                [6 ] Department of Public Heath, College of Medicine, National Cheng Kung University, Tainan, Taiwan, Republic of China
                [7 ] Research Center for Applied Sciences, Academia Sinica, Taipei, Taiwan, Republic of China
                [8 ] Institute of Biomedical Electronics and Bioinformatics, College of Electrical Engineering & Computer Science, National Taiwan University, Taipei, Taiwan, Republic of China
                [9 ] Department of Medical Informatics, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan, Republic of China
                [10 ] Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan University, Taipei, Taiwan, Republic of China
                University of Rhode Island, UNITED STATES
                Author notes

                The authors have declared that no competing interests exist.

                Author information
                https://orcid.org/0000-0003-2951-6679
                https://orcid.org/0000-0003-2285-4413
                https://orcid.org/0000-0002-3176-4500
                https://orcid.org/0000-0003-2356-4493
                Article
                PNTD-D-20-00034
                10.1371/journal.pntd.0008843
                7654779
                33170848
                80cbd77d-293f-4fcf-a4eb-c17567d8fb12
                © 2020 Ho et al

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                History
                : 8 January 2020
                : 1 October 2020
                Page count
                Figures: 3, Tables: 2, Pages: 21
                Funding
                Funded by: funder-id http://dx.doi.org/10.13039/501100004663, Ministry of Science and Technology, Taiwan;
                Award ID: MOST-103-2314-B-006-009-MY3
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/501100004663, Ministry of Science and Technology, Taiwan;
                Award ID: MOST-107-2923-B-006-001
                Award Recipient :
                Funded by: funder-id http://dx.doi.org/10.13039/501100004663, Ministry of Science and Technology, Taiwan;
                Award ID: MOST-108-2923-B-006-001
                Award Recipient :
                Funded by: National Health Research Institute, Taiwan
                Award ID: MR-109-CO-08
                Award Recipient :
                The authors sincerely appreciate the financial support from the research grants of National Health Research Institutes ( www.nhri.org.tw) (MR-108-GP-14 (CCK), NHRI-108A1-MRCO-0319191 (TSH)) and the Ministry of Science and Technology ( www.most.gov.tw) (MOST-103-2314-B-006-009-MY3(TSH), MOST-107-2923-B-006-001(TSH), MOST-108-2923-B-006-001 (TSH)), Taiwan, which made this investigation possible. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
                Categories
                Research Article
                Medicine and Health Sciences
                Medical Conditions
                Tropical Diseases
                Neglected Tropical Diseases
                Dengue Fever
                Medicine and Health Sciences
                Medical Conditions
                Infectious Diseases
                Viral Diseases
                Dengue Fever
                Research and Analysis Methods
                Mathematical and Statistical Techniques
                Statistical Methods
                Forecasting
                Physical Sciences
                Mathematics
                Statistics
                Statistical Methods
                Forecasting
                Physical Sciences
                Mathematics
                Applied Mathematics
                Algorithms
                Machine Learning Algorithms
                Research and Analysis Methods
                Simulation and Modeling
                Algorithms
                Machine Learning Algorithms
                Computer and Information Sciences
                Artificial Intelligence
                Machine Learning
                Machine Learning Algorithms
                Biology and life sciences
                Organisms
                Viruses
                RNA viruses
                Flaviviruses
                Dengue Virus
                Biology and Life Sciences
                Microbiology
                Medical Microbiology
                Microbial Pathogens
                Viral Pathogens
                Flaviviruses
                Dengue Virus
                Medicine and Health Sciences
                Pathology and Laboratory Medicine
                Pathogens
                Microbial Pathogens
                Viral Pathogens
                Flaviviruses
                Dengue Virus
                Biology and Life Sciences
                Organisms
                Viruses
                Viral Pathogens
                Flaviviruses
                Dengue Virus
                Computer and Information Sciences
                Artificial Intelligence
                Machine Learning
                Medicine and Health Sciences
                Nephrology
                Renal Diseases
                Chronic Kidney Disease
                Medicine and Health Sciences
                Endocrinology
                Endocrine Disorders
                Diabetes Mellitus
                Medicine and Health Sciences
                Medical Conditions
                Metabolic Disorders
                Diabetes Mellitus
                Biology and Life Sciences
                Anatomy
                Body Fluids
                Blood
                Blood Counts
                Medicine and Health Sciences
                Anatomy
                Body Fluids
                Blood
                Blood Counts
                Biology and Life Sciences
                Physiology
                Body Fluids
                Blood
                Blood Counts
                Custom metadata
                All relevant data are full available within the manuscript and its Supporting Information files.

                Infectious disease & Microbiology
                Infectious disease & Microbiology

                Comments

                Comment on this article