Environmental Analysis of Hemorrhagic Fever in Iraq Using Machine Learning
DOI:
https://doi.org/10.29304/jqcm.2023.15.3.1264Keywords:
Iraq hemorrhagic fever, Satellite imagery, Data Analysis, Risk Assessment, Spatio-temporal PatternsAbstract
Crimean-Congo Hemorrhagic Fever (CCHF) is a viral disease with rising prevalence in Iraq. This research focused on investigating factors influencing CCHF spread in Dhi Qar Governorate, which has seen a substantial surge in cases. The problem was to uncover which environmental and climatic factors correlate with CCHF outbreaks. Meteorological data, rodent populations, vegetation indices, and epidemiological records were analyzed using data preprocessing techniques like interpolation and ARIMA modeling. Pearson correlation analysis was applied to quantify associations between CCHF cases and factors like temperature, humidity, rodent prevalence, and vegetation lushness. Results showed strong positive correlations of CCHF with rodent populations, temperature, solar radiation, and evapotranspiration. Negative correlations were found with humidity and vegetation health. The conclusions indicate environmental factors significantly influence CCHF outbreaks in Dhi Qar. This can inform prevention strategies targeting ecological and climatic drivers of the disease.
Downloads
References
[2] E. Sylvestre et al., “Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review,” PLoS Neglected Tropical Diseases, vol. 16, no. 1. Public Library of Science, p. e0010056, Jan. 01, 2022. doi: 10.1371/journal.pntd.0010056.
[3] Minnesota Department of Health, “Viral Hemorrhagic Fevers (VHFs),” Minnesota Department of Health. https://www.health.state.mn.us/diseases/vhf/vhf.html (accessed Mar. 06, 2023).
[4] K. Tallam and M. P. Quang, “Applications of artificial intelligence in predicting dengue outbreaks in the face of climate change: a case study along coastal India,” medRxiv, p. 2023.01.18.23284134, Jan. 2023, doi: 10.1101/2023.01.18.23284134.
[5] A. Fanelli and D. Buonavoglia, “Risk of Crimean Congo haemorrhagic fever virus (CCHFV) introduction and spread in CCHF-free countries in southern and Western Europe: A semi-quantitative risk assessment,” One Health, vol. 13, p. 100290, Dec. 2021, doi: 10.1016/j.onehlt.2021.100290.
[6] “WHO | Situation Report Iraq | Week 31 | United Nations in Iraq.” https://iraq.un.org/en/194395-who-situation-report-iraq-week-31 (accessed Mar. 09, 2023).
[7] “Crimean-Congo Hemorrhagic Fever - Iraq,” World Health Organization (WHO). https://www.who.int/emergencies/disease-outbreak-news/item/2022-DON386 (accessed Mar. 13, 2023).
[8] R. A. Alhilfi, H. A. Khaleel, B. M. Raheem, S. G. Mahdi, C. Tabche, and S. Rawaf, “Large outbreak of Crimean-Congo haemorrhagic fever in Iraq, 2022,” IJID Regions, vol. 6, pp. 76–79, Mar. 2023, doi: 10.1016/J.IJREGI.2023.01.007.
[9] “Situation Report Iraq Week 31 (ending 7 August 2022),” World Health Organization, Accessed: Mar. 11, 2023. [Online]. Available: https://iraq.un.org/sites/default/files/2022-08/WHO-Iraq-SitRep_Week-31.pdf
[10] V. Andreo, M. Belgiu, D. B. Hoyos, F. Osei, C. Provensal, and A. Stein, “Rodents and satellites: Predicting mice abundance and distribution with Sentinel-2 data,” Ecol Inform, vol. 51, pp. 157–167, May 2019, doi: 10.1016/j.ecoinf.2019.03.001.
[11] H. Jamil et al., “Knowledge, attitudes, and practices regarding Crimean-Congo hemorrhagic fever among general people: A cross-sectional study in Pakistan,” PLoS Negl Trop Dis, vol. 16, no. 12, p. e0010988, Dec. 2022, doi: 10.1371/journal.pntd.0010988.
[12] F. Duygu, T. Sari, T. Kaya, O. Tavsan, and M. Naci, “The relationship between crimean-congo hemorrhagic fever and climate: Does climate affect the number of patients?,” Acta Clin Croat, vol. 57, no. 3, pp. 443–448, Sep. 2018, doi: 10.20471/acc.2018.57.03.06.
[13] M. Okely, R. Anan, S. Gad-Allah, and A. M. Samy, “Mapping the environmental suitability of etiological agent and tick vectors of Crimean-Congo hemorrhagic fever,” Acta Trop, vol. 203, p. 105319, Mar. 2020, doi: 10.1016/J.ACTATROPICA.2019.105319.
[14] M. A. ; Majeed et al., “A Deep Learning Approach for Dengue Fever Prediction in Malaysia Using LSTM with Spatial Attention,” International Journal of Environmental Research and Public Health 2023, Vol. 20, Page 4130, vol. 20, no. 5, p. 4130, Feb. 2023, doi: 10.3390/IJERPH20054130.
[15] K. Roster, C. Connaughton, and F. A. Rodrigues, “Machine-Learning–Based Forecasting of Dengue Fever in Brazilian Cities Using Epidemiologic and Meteorological Variables,” Am J Epidemiol, vol. 191, no. 10, pp. 1803–1812, Sep. 2022, doi: 10.1093/AJE/KWAC090.
[16] Z. Li and J. Dong, “Big Geospatial Data and Data-Driven Methods for Urban Dengue Risk Forecasting: A Review,” Remote Sensing 2022, Vol. 14, Page 5052, vol. 14, no. 19, p. 5052, Oct. 2022, doi: 10.3390/RS14195052.
[17] S. K. Dey et al., “Prediction of dengue incidents using hospitalized patients, metrological and socioeconomic data in Bangladesh: A machine learning approach,” PLoS One, vol. 17, no. 7 July, p. e0270933, Jul. 2022, doi: 10.1371/journal.pone.0270933.
[18] “Dhi Qar Map - State - Iraq - Mapcarta.” https://mapcarta.com/12539716 (accessed Mar. 10, 2023).
[19] “Al-Nāṣiriyyah | Iraq | Britannica.” https://www.britannica.com/place/Al-Nasiriyyah (accessed Mar. 10, 2023).
[20] “Climate Dhi Qar: Temperature, climate graph, Climate table for Dhi Qar - Climate-Data.org.” https://en.climate-data.org/asia/iraq/dhi-qar-2055/ (accessed Mar. 10, 2023).
[21] “الموجز الاحصائي ذي قار2018 - الجهاز المركزي للاحصاء.” https://cosit.gov.iq/ar/1216-16-6-2021 (accessed Mar. 10, 2023).
[22] N. Agarwal, S. R. Koti, S. Saran, and A. Senthil Kumar, “Data mining techniques for predicting dengue outbreak in geospatial domain using weather parameters for New Delhi, India,” Curr Sci, vol. 114, no. 11, pp. 2281–2291, Jun. 2018, doi: 10.18520/cs/v114/i11/2281-2291.
[23] S. Chae, S. Kwon, and D. Lee, “Predicting infectious disease using deep learning and big data,” Int J Environ Res Public Health, vol. 15, no. 8, p. 1596, Jul. 2018, doi: 10.3390/ijerph15081596.
[24] Y. Ince et al., “Crimean-Congo hemorrhagic fever infections reported by ProMED,” International Journal of Infectious Diseases, vol. 26, pp. 44–46, Sep. 2014, doi: 10.1016/j.ijid.2014.04.005.
[25] P. Weidinger et al., “Potentially Zoonotic Viruses in Wild Rodents, United Arab Emirates, 2019—A Pilot Study,” Viruses 2023, Vol. 15, Page 695, vol. 15, no. 3, p. 695, Mar. 2023, doi: 10.3390/V15030695.
[26] M. Aminikhah et al., “Rodent host population dynamics drive zoonotic Lyme Borreliosis and Orthohantavirus infections in humans in Northern Europe,” Sci Rep, vol. 11, no. 1, pp. 1–11, Aug. 2021, doi: 10.1038/s41598-021-95000-y.
[27] H. Dahmana, L. Granjon, C. Diagne, B. Davoust, F. Fenollar, and O. Mediannikov, “Rodents as hosts of pathogens and related zoonotic disease risk,” Pathogens, vol. 9, no. 3, p. 202, Mar. 2020, doi: 10.3390/pathogens9030202.
[28] X. Deng et al., “Distinct Genotype of Hantavirus Infection in Rodents in Jiangxi Province, China, in 2020–2021,” Zoonoses, vol. 2, no. 1, Sep. 2022, doi: 10.15212/zoonoses-2022-0034.
[29] J. F. Vesgan et al., “Transmission dynamics and vaccination strategies for Crimean-Congo haemorrhagic fever virus in Afghanistan: A modelling study,” PLoS Negl Trop Dis, vol. 16, no. 5, p. e0010454, May 2022, doi: 10.1371/JOURNAL.PNTD.0010454.
[30] Q. Dong and Q. Zhang, “The Estimation of a Remote Sensing Model of Three-Dimensional Green Space Quantity and Research into Its Cooling Effect in Hohhot, China,” Land 2022, Vol. 11, Page 1437, vol. 11, no. 9, p. 1437, Aug. 2022, doi: 10.3390/LAND11091437.
[31] S. Li, L. Zhu, L. Zhang, G. Zhang, H. Ren, and L. Lu, “Urbanization-Related Environmental Factors and Hemorrhagic Fever with Renal Syndrome: A Review Based on Studies Taken in China,” Int J Environ Res Public Health, vol. 20, no. 4, p. 3328, Feb. 2023, doi: 10.3390/IJERPH20043328/S1.
[32] K. K. Al-jabery, T. Obafemi-Ajayi, G. R. Olbricht, and D. C. Wunsch II, “Data preprocessing,” Computational Learning Approaches to Data Analytics in Biomedical Applications, pp. 7–27, Jan. 2020, doi: 10.1016/B978-0-12-814482-4.00002-4.
[33] N. Bokde, M. W. Beck, F. Martínez Álvarez, and K. Kulat, “A novel imputation methodology for time series based on pattern sequence forecasting,” Pattern Recognit Lett, vol. 116, p. 88, Dec. 2018, doi: 10.1016/J.PATREC.2018.09.020.
[34] Z. Zhang, “Missing data imputation: focusing on single imputation,” Ann Transl Med, vol. 4, no. 1, p. 9, Jan. 2016, doi: 10.3978/J.ISSN.2305-5839.2015.12.38.
[35] R. Kohn and C. F. Ansley, “Estimation, prediction, and interpolation for ARIMA models with missing data,” J Am Stat Assoc, vol. 81, no. 395, pp. 751–761, 1986, doi: 10.1080/01621459.1986.10478332.
[36] L. Kong et al., “Time-Aware Missing Healthcare Data Prediction Based on ARIMA Model,” IEEE/ACM Trans Comput Biol Bioinform, 2022, doi: 10.1109/TCBB.2022.3205064.
[37] A. Choudhary, S. Kumar, M. Sharma, and K. P. Sharma, “A Framework for Data Prediction and Forecasting in WSN with Auto ARIMA,” Wirel Pers Commun, vol. 123, no. 3, pp. 2245–2259, Apr. 2022, doi: 10.1007/S11277-021-09237-X/METRICS.
[38] S. Mancini, A. B. Francavilla, A. Longobardi, G. Viccione, and C. Guarnaccia, “Predicting daily water tank level fluctuations by using ARIMA model. A case study,” J Phys Conf Ser, vol. 2162, no. 1, p. 012007, Jan. 2022, doi: 10.1088/1742-6596/2162/1/012007.
[39] S. Sivaramakrishnan, T. F. Fernandez, R. G. Babukarthik, and S. Premalatha, “Forecasting Time Series Data Using ARIMA and Facebook Prophet Models,” Big Data Management in Sensing: Applications in AI and IoT, pp. 75–87, Jan. 2021, doi: 10.1201/9781003337355-4/FORECASTING-TIME-SERIES-DATA-USING-ARIMA-FACEBOOK-PROPHET-MODELS-SIVARAMAKRISHNAN-TERRANCE-FREDERICK-FERNANDEZ-BABUKARTHIK-PREMALATHA.
[40] L. Hansson, “Field Signs as Indicators of Vole Abundance,” J Appl Ecol, vol. 16, no. 2, p. 339, Aug. 1979, doi: 10.2307/2402512.
[41] B. Takele, M. Yihune, and A. Bekele, “Composition, abundance and distribution of rodent species in Alemsaga Priority State Forest and farmlands, northwestern Ethiopia,” Afr J Ecol, vol. 60, no. 3, pp. 447–455, Sep. 2022, doi: 10.1111/AJE.12976.
[42] “Help Online - Origin Help - Digitizer.” https://www.originlab.com/doc/Origin-Help/Tool-Digitizer (accessed Mar. 16, 2023).
[43] “Help Online - Tutorials - Digitizer Tool.” https://www.originlab.com/doc/Tutorials/Digitizer-Tool (accessed Mar. 16, 2023).
[44] “Interpolation.” https://www.originlab.com/videos/details.aspx?pid=1889 (accessed Mar. 16, 2023).
[45] “Help Online - Origin Help - Interpolate/Extrapolate Y from X.” https://www.originlab.com/doc/origin-help/math-inter-extrapoltate-yfromx (accessed Mar. 16, 2023).
[46] M. Drusch et al., “Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services,” Remote Sens Environ, vol. 120, pp. 25–36, May 2012, doi: 10.1016/J.RSE.2011.11.026.
[47] B. E. Smith, A. Gardner, A. Schneider, and M. Flanner, “Modeling biases in laser-altimetry measurements caused by scattering of green light in snow,” Remote Sens Environ, vol. 215, pp. 398–410, Sep. 2018, doi: 10.1016/J.RSE.2018.06.012.
[48] M. Imran and A. Ahmad, “Enhancing data quality to mine credible patterns,” https://doi.org/10.1177/01655515211013693, Jun. 2021, doi: 10.1177/01655515211013693.
[49] “The Python Language Reference — Python 3.10.10 documentation.” https://docs.python.org/3.10/reference/ (accessed Mar. 16, 2023).
[50] “OriginLab - Origin and OriginPro - Data Analysis and Graphing Software.” https://www.originlab.com/ (accessed Mar. 16, 2023).
[51] “KNIME | Open for Innovation.” https://www.knime.com/ (accessed Mar. 16, 2023).
[52] “Google Earth Engine.” https://earthengine.google.com/ (accessed Mar. 16, 2023).
[53] “pandas - Python Data Analysis Library.” https://pandas.pydata.org/ (accessed Mar. 16, 2023).