Predicting Case Fatality of Dengue Epidemic: Statistical Machine Learning Towards a Virtual Doctor
DOI:
https://doi.org/10.12974/2311-8792.2021.07.2Keywords:
Statistical machine learning, Dengue epidemic, Multiple linear regressions, Multinomial logistic regressionsAbstract
Dengue fever is a self-limiting communicable viral disease, transmitted through mosquito bites. Its Case Fatality Grade (CFG) varies across population due to variations in viral load, immunity of the patient, early diagnosis, and availability of high-end treatment facility. This study describes an initial effort to automate the process of Dengue CFG predictions. Two established Statistical Machine Learning (SML) algorithms, Multiple Linear Regressions (MLR) and Multinomial Logistic Regressions (MnLR), are combined to substitute the existing Deep Learning methods for clinical decision making. We consider a vector of eleven sign-symptoms (independent variables), each weighted between [0,1] on a 3-point scale - ‘Mild’ (CFG<=0.33), ‘Moderate’ (0.33<CFG< 0.66), and ‘Severe’ (CFG>0.66). Results show that both classifiers are effective in early screening with similar accuracy levels (68% for MLR versus 72% for MnLR) although precision levels are far superior with MnLR (88%) than MLR (61%). This study is a futuristic step towards Machine Learning (ML) aided clinical diagnostic paradigms, as an alternative to computationally intensive Artificial Intelligence.
References
Ahmed A, Jalal A, & Kim K. A Novel Statistical Method for Scene Classification Based on Multi-Object Categorization and Logistic Regression. Sensors, 2020; 20(14): 3871. https://doi.org/10.3390/s20143871
Akazawa M, & Hashimoto K. Artificial Intelligence in Ovarian Cancer Diagnosis. Anticancer Research, 2020; 40(8): 4795- 4800. https://doi.org/10.21873/anticanres.14482
Anirudh VK. (2020). What is Machine Learning: Definitions, Types, Applications And Examples. Retrieved Feb 9, 2021, from Potential Analytics Artificial Intelligence for Healthcare: https://www.toolbox.com/tech/artificial-intelligence/tech- 101/what-is-machine-learning-definition-types-applicationsand- examples/
Ashish K, Chattopadhyay S, Gao XZ, & Hui NB. Neural Network-based Diagnostic Tool for Identifying the Factors Responsible for Depression. International Journal of Computational Intelligence and Applications, 2019; 18(2): 195001-14. https://doi.org/10.1142/S1469026819500147
Chattopadhyay AK, Choudhury D, Ghosh G, Kundu B & Nath SK. Infection kinetics of Covid-19 and containment strategy. Scientific Reports 2021; 11: 11606: 398. https://doi.org/10.1038/s41598-021-90698-2
Chattopadhyay AK. & Chattopadhyay S. VIRDOCD: A VIRtual DOCtor to predict Dengue fatality. Expert Systems. 2021;e12796.
Chattopadhyay S. Mathematical Modelling of Doctors' Perceptions in the Diagnosis of Depression: A Novel Approach. International Journal of Biomedical Engineering and Technology, 2013; 11(1): 1-17. https://doi.org/10.1504/IJBET.2013.053702
Chattopadhyay S. A Neuro-fuzzy Approach for the Diagnosis of Depression. Applied computing and Informatics, 2017; 13(1): 10-18. https://doi.org/10.1016/j.aci.2014.01.001
Comert G, Begashaw N, & Turhan-Comert A. (2020, July 21). Malaria Outbreak Detection With Machine Learning Methods. Retrieved Feb 8, 2021, from BioRxiv: https://www.biorxiv.org/content/10.1101/2020.07.21.214213v 1.full.pdf https://doi.org/10.1101/2020.07.21.214213
Dacosta-Aguayo R, Wylie G, DeLuca J, & Genova H. Anatomical Covariance Analysis: Detection of Disrupted Correlation Network Related to Clinical Trait Fatigue in Multiple Sclerosis: A Pilot Study. Behavioural Neurology, 2020 Article ID 5807496, 1-9. https://doi.org/10.1155/2020/5807496
Dezfouli A, Nock R. & Dayan P. Adversarial vulnerabilities of human decision-making. PNAS 2020; 117 (46): 29221- 29228. https://doi.org/10.1073/pnas.2016921117
Esteves L, Caramelo F, & Ribeiro I. (2020). Probability distribution of copy number alterations along the genome: an algorithm to distinguish different tumour profiles. 10(14868). https://doi.org/10.1038/s41598-020-71859-1
Farafonov VS & Neruhk D. MS2 bacteriophage capsid studied using all-atom Molecular Dynamics. Interface Focus, 2019; 9(3). https://doi.org/10.1098/rsfs.2018.0081
Fuhad KM, Tuba JF, Sarker MR, Momen S, Mohammed N, & T R. Deep Learning Based Automatic Malaria Parasite Detection from Blood Smear and Its Smartphone Based Application. Diagnostics, 2020; 10(5): 329. https://doi.org/10.3390/diagnostics10050329
Grela E, Stich M. and Chattopadhyay AK. Epidemiological impact of waning immunization on a vaccinated population. The European Physical Journal 2018; B 91: 267-279. https://doi.org/10.1140/epjb/e2018-90136-3
Kapoor R, Ahuja S, & Kadyan V. Fuzzy Multiple Rules based Machine Learning Diagnostic Prediction Model for Dengue disease in India. International Journal of Advanced Science and Technology, 2020; 29(11s): 2083-2106.
Khalavati K, Park, et al. Modeling other minds: Bayesian infreence explains human choices in group decision-making. Science Advances in Cognitive Neuroscience 2019; 5(11): eaax8783. https://doi.org/10.1126/sciadv.aax8783
Krittanawong C, Virk HU, Bangalore S, Wang Z, Johnson KW, Pinotti R, Tang WH. (2020). Machine learning prediction in cardiovascular diseases: a meta-analysis. Scientific Reports, 10, 16057. https://doi.org/10.1038/s41598-020-72685-1
Miguel-Hurtado O, Guest R, Stevenage SV, Neil GJ, & Black S. Comparing Machine Learning Classifiers and Linear/Logistic Regression to Explore the Relationship between Hand Dimensions and Demographic Characteristics. PLoS ONE, 2016; 11(11): e0165521. https://doi.org/10.1371/journal.pone.0165521
Murray JD. (2002). Mathematical Biology I: An Introduction. Springer. https://doi.org/10.1007/b98868
Murray JD. (2003). Mathematical Biology: Spatial Models and Biological Applications. Springer.
Naeem S, Jamil N, Khan HU, & Nazir S. (2020). Complexity of Deep Convolutional Neural Networks in Mobile Computing. Complexity, 2020 (Article ID 3853780), 1-8. https://doi.org/10.1155/2020/3853780
Nagar PK, Savargaonkar D, & Anvikar AK. Detection of Dengue Virus-Specific IgM and IgG Antibodies through Peptide Sequences of Envelope and NS1 Proteins for Serological Identification. Journal of Immunology Research, 2020; 1-8. https://doi.org/10.1155/2020/1820325
Narayanan BN, Ali R, & Hardie RC. Performance analysis of machine learning and deep learning architectures for malaria detection on cell images. Proceedings Volume 11139, Applications of Machine Learning; 111390W (2019) (pp. -). San Diego, California, United States: Proc. SPIE 11139. https://doi.org/10.1117/12.2524681
Raizada S, Mala S, & Shankar A. (2020). Vector Borne Disease Outbreak Prediction by Machine Learning. 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE) (pp. 213- 218). Bengaluru: IEEE. https://doi.org/10.1109/ICSTCEE49637.2020.9277286
Reda C, Kaufmann E, & Delahaye-Duriez A. Machine learning applications in drug development. Computational and Structural Biotechnology Journal, 2020; 18: 241-252. https://doi.org/10.1016/j.csbj.2019.12.006
Richens JG, Lee CM, & Johri S. Improving the accuracy of medical diagnosis with causal machine learning . Nature Communications, 2020; 1-9. https://doi.org/10.1038/s41467-020-17419-7
Salim NA, Wah YB, Reeves C, Smith M, Yaacob WF, Mudin RN, Haque U. Prediction of dengue outbreak in Selangor Malaysia using machine learning techniques. Scientific Reports, 2021; 11(939). https://doi.org/10.1038/s41598-020-79193-2
Sanders M, Servaas S, & Slagt C. Accuracy and precision of non-invasive cardiac output monitoring by electrical cardiometry: a systematic review and meta-analysis. Journal of Clinical Monitoring and Computing, 2020; 34: 433-460. https://doi.org/10.1007/s10877-019-00330-y
Saturi S. (2020). Development of Prediction and Forecasting Model for Dengue Disease using Machine Learning Algorithms. 2020 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER) (pp. 6-11). Udupi: IEEE. https://doi.org/10.1109/DISCOVER50404.2020.9278079
Schrider DR, & Kern AD. Supervised Machine Learning for Population Genetics: A New Paradigm. Trends in Genetics, 2018; 34(4): 301-312. https://doi.org/10.1016/j.tig.2017.12.005
Smith DS, Mariano DJ, Teautwein ML, Shepherd SM, Hinfey PM, & Shoff WH. (2019, May 03). /what-is-the-mortality-ratefor- dengue. (M. S. Bronze, Ed.) Retrieved Feb 7, 2021, from https://www.medscape.com: https://www.medscape.com/answers/215840-43425/what-isthe- mortality-rate-fordengue#:~: text=Dengue%20fever%20is%20typically%20a,is %20as%20high%20as%2020%25.
Sumair M, Alzed T, Gardezi SA, Bhutta MM, Rehman SM, & Rehman SU. (2020, July). Application of five continuous distributions and evaluation of wind potential at five stations using normal distribution. Energy Exploration and Exploitation. https://doi.org/10.1177/0144598720939373
Swathi P, & Pothuganti K. Overview on Principal Compnent Analysis Algorithm in Machine Learning. International Research Journal of Modernization in Engineering Technology and Science, 2020; 2(10): 241-246.
Tarasova E & Nerukh D. All-Arom Molecular Dynamics Simulations of Whole Viruses. The Journal of Physical Chemistry Letters, 2018; 9: 5805-5809. https://doi.org/10.1021/acs.jpclett.8b02298
Tarasova E, Farafonov V, Khayat R, Okimoto N, Komatsu TS, Taiji M & Nerukh D. All-Atom Molecular Dynamics Simulations of Entire Virus Capsid Reveal the Role of Ion Distribution in Capsid s Stability. The Journal of Physical Chemistry Letters, 2017; 8(4): 779-784. https://doi.org/10.1021/acs.jpclett.6b02759
Vaka AR, Soni B, & Reddy SK. Breast cancer detection by leveraging Machine Learning. ICT Express, 2020; 6(4): 320- 324. https://doi.org/10.1016/j.icte.2020.04.009
Valavi R, Elith J, Lahoz-Monfot JJ, & Guillera-Arroita G. blockCV: An r package for generating spatially or environmentally separated folds for k‐fold cross‐validation of species distribution models. Methods in Ecology and Evolution, 2020; 10(2): 225-232. https://doi.org/10.1111/2041-210X.13107
Zhao N, Charland K, Carabali M, Nsoesie EO, Maheeu- Giroux M, Rees E, Zinszer K. Machine learning and dengue forecasting: Comparing random forests and artificial neural networks for predicting dengue burden at national and subnational scales in Colombia. PLOS Neglected Tropical Diseases, 2020; 14(9): e0008056. https://doi.org/10.1371/journal.pntd.0008056
Zhen Sh, Cheng M, Yb T, Wang Yf, Juengpanich S, Jiang Zy, Cai Xj. Deep Learning for Accurate Diagnosis of Liver Tumor Based on Magnetic Resonance Imaging and Clinical Data. Frontiers in Oncology, 2020; 10(680). https://doi.org/10.3389/fonc.2020.00680
