ارائه مدلی برای پیش بینی بیماری لیشمانیوز جلدی (سالک) با استفاده از سامانه اطلاعات مکانی و الگوریتم شبکه عصبی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری سامانه اطلاعات مکانی، دانشکده مهندسی نقشه برداری- دانشگاه صنعتی خواجه نصیرالدین طوسی

2 استادیار گروه سامانه اطلاعات مکانی دانشکده نقشه برداری، دانشگاه صنعتی خواجه نصیرالدین طوسی

10.22131/sepehr.2019.35635

چکیده

بیماری سالک، از بیماریهای انگلی میباشد که در شمار بیماریهای مشترک بین انسان و حیوان قرار میگیرد. این بیماری از شایعترین فرم بیماری لیشمانیوز است که توسط گونههای مختلف انگل لیشمانیا ایجاد شده و با نیش زدن گونههای مختلف پشه خاکیهای ماده عامل فلبوتومینه به انسان، شخص را دچار ابتلا به این بیماری میکند. استان گلستان همواره یکی از کانونهای اصلی بروز بیماری سالک در ایران بوده است و به دلیل دارابودن شرایط محیطی و آب و هوایی مساعد، سالانه تعدادی از موارد ابتلا به این بیماری در این استان گزارش میگردد. هدف اساسی این تحقیق تحلیل سالانه توزیع مکانی-زمانی بیماری سالک، بررسی تأثیر عوامل محیطی و آب و هوایی با بروز بیماری و در نهایت ارائه مدلی جهت تهیه نقشه پیشبینی و آسیبپذیری بیماری طی دوره آماری 1392 تا 1394 در سطح دهستانهای استان گلستان میباشد. به منظور بررسی ارتباط میان بروز بیماری سالک با متغیرهای محیطی و آب و هوایی و همچنین بررسی وجود خودهمبستگی مکانی میان موارد بروز بیماری، تحلیلهای آماری و مکان-آماری به کار گرفته شدهاند. جهت مدلسازی بیماری، الگوریتم شبکه عصبی پرسپترون چندلایه مورد استفاده قرار گرفت. به منظور ارزیابی دقت مدل بدست آمده، معیارهایی همچون RMSE،MAPE و AUCاستفاده گردیدند و همچنین جهت تعیین مؤثرترین متغیرها در مدلسازی بیماری، آنالیز حساسیت اجرا شده است. معیارهای ارزیابی گویای این حقیقت بودند که مدل به دست آمده قدرت تشخیص قابل قبولی در پیشبینی بروز بیماری در سطح دهستانهای استان گلستان دارد (RMSE1392 = 0.019, RMSE1393 = 0.013, RMSE1394 = 0.017, MAPE1392 = 1.43, MAPE1393 = 1.34, MAPE1394 = 1.40, AUC1392 = 0.846, AUC1393 = 0.873, AUC1394 = 0.859). همچنین آنالیز حساسیت نشان داد که متغیرهای پوشش گیاهی و متوسط رطوبت هوا مهمترین عوامل در تهیه نقشه پیشبینی و آسیبپذیری توزیع مکانی بیماری سالک در استان گلستان میباشند.

کلیدواژه‌ها


عنوان مقاله [English]

Providing a model for Cutaneous Leishmaniasis risk mapping using GIS and neural network algorithm

نویسندگان [English]

  • Mehrdad AhangarCani 1
  • Mahdi Farnaghi 2
1 Ph.D student of geographic information system, Faculty of Geodesy and Geomatics, K. N. Toosi University of Technology
2 Assitant Professor, Faculty of Geodesy and Geomatics, K. N. Toosi University of Technology
چکیده [English]

Introduction
Introduction and Objectives: Cutaneous Leishmaniasis (CL) is a vector-borne disease, endemic of the Middle East. The spread of CL is highly associated with the socio-ecological interactions of vectors, hosts and environmental conditions. CL is the most frequent vector-borne disease in Iran and especially in the north-eastern province, Golestan, which has long been known as one of the most important endemic areas for CL dispersion. Therefore, Golestan province was selected as the study area of this research. The main objectives of the study are to analyze annual spatial distribution of CL, investigate the relations between environmental/climate factors and incidence rate of CL and also provide a model to predict CL distribution at rural district level in Golestan province.
 
Materials and methods
Data: CL incidences, census data, environmental and climate factors have been used in this study to provide a model and produce a map to predict the CL distribution. The CL incidences are continuously recorded by the Center for Disease Control and Prevention (CDC) of Golestan province. The population and census data for 2013-2015 period were obtained from Iranian Statistical Center. Environmental and climate data such as vegetation, average humidity, average temperature, precipitation, number of rainy days, number of freezing days, maximum wind speed and evaporation rate were used as parameters affecting the model.
 
Methodology
The statistical and geo-statistical analyses were used to investigate the relation between environmental/climate factors and CL incidence rate, and to investigate the existence of spatial autocorrelation between CL cases, respectively. Additionally, Multilayer perceptron (MLP) neural network was used to model the relation between the distribution of CL incidences with environmental/climate factors, and also to generate the risk maps of CL. MLP is a type of neural network which consists of multiple layers of neurons or processing elements connected in a feed forward fashion. It encompasses three types of layers: input, hidden, and output. It has a unidirectional flow of information. Generally, information flow starts from input layer, goes through hidden layer, and then to output layer, which provides the response of the network to the input stimuli. In this type of network, there are generally three distinct types of neurons in layers. The input layer contains some neurons as the input variables. The hidden neurons, which are contained in one or more hidden layers, process and encode information within the network. The hidden layer receives, processes, and passes the input data to the output layer. Number of hidden layers and number of neurons within each layer affect the accuracy and functionality of the network. The output layer contains target output vector. In this study, effective parameters along with CL incidence rate of 2013-2014 were fed to the MLP as training data. The trained MLP was used afterward to generate the risk map of 2015 and test accuracy of the model. In order to determine the optimal parameters of the MLP, the grid-search and cross-validation techniques were used on 25% of the training dataset in the training phase. The performance of MLP was investigated using the root mean square error (RMSE), mean absolute percentage error (MAPE) and area under curve (AUC) of receiver operating characteristic (ROC) measures. Sensitivity analysis was also used to determine most effective variables regarding predictive mapping of CL distribution
 
Results and Discussion
Results of global Moran’s I index indicated that there is spatial autocorrelation among CL cases, and also distribution of CL cases in Golestan province in each 3 years is clustered. Moreover, statistical analyses showed that majority of the incidences belonged to rural districts of Gonbad-Kavos and Maraveh-Tappeh. Based on the results of statistical analyses (including Pearson correlation and Spearman rank correlation), positive correlations were observed between the CL incidence rate and average temperature, maximum wind speed and evaporation. In addition, negative correlation was found between the CL incidence rate and average humidity, precipitation, number of rainy days, number of freezing days and vegetation. According to the results of evaluation criteria including RMSE, MAPE and AUC, the trained MLP model was able to generate risk maps of CL in 2013-2015 for each rural district with acceptable accuracy. Additionally, results of sensitivity analysis indicate that vegetation and average humidity are the most influencing variables in the incidence of CL and in predictive mapping of CL distribution in Golestan province.
 
Conclusion and Future works
In this study, the global Moran’s I index indicated the presence of spatial autocorrelation among CL cases, and clustered distribution of disease in the study area. The statistical analyses showed that environmental and climate factors greatly affect the spatial distribution of CL. The MLP method, used to generate CL distribution risk maps, was able to generate the study area risk maps with acceptable accuracy. Results highlight the potential high risk areas requiring special plans and resources for monitoring and control of the disease. As a future work, we suggest that the effects of other environmental and socio-economic parameters should be evaluated to improve the accuracy of the model. It is also recommended that other methods such as regression and other neural network techniques be used to generate CL risk maps.
 

کلیدواژه‌ها [English]

  • Cutaneous leishmaniasis
  • Geographical Information System
  • Multilayer perceptron neural network
1- AhangarCani, Farnaghi& Shirzadi, M., M., M.R. (2016). Predictive Map of Spatio-Temporal Distribution of Leptospirosis Using Geographical Weighted Regression and Multilayer Perceptron Neural Network Methods. Journal of Geomatics Science and Technology, 6(2), 79-98.

2- Antonialli, Torres, Paranhos Filho& Tolezano, S. A. C., T. G., A. C., J. E. (2007). Spatial analysis of American visceral leishmaniasis in Mato Grosso do Sul state, Central Brazil. Journal of infection, 54(5), 509-514.

3- Assimina, Charilaos& Fotoula, Z., K., B. (2008). Leishmaniasis: an overlooked public health concern. Health Science Journal, 2(4).

4- Bavia, Carneiro, da Costa Gurgel, Filho& Barbosa, M., D., H., C. M., M. R. (2005). Remote sensing and geographic information systems and risk of American visceral leishmaniasis in Bahia, Brazil. Parassitologia, 47(1), 165.

5- Bayatani & Sadeghi, A., A. (2012). Spatial Analysis of Environmental Factors of Cutaneous Leishmaniasis in Iran Using GIS. Hakim Research Journal, 15, 158-165.

6- Chaves & Pascual, L. F., M. (2006). Climate cycles and forecasts of cutaneous leishmaniasis, a nonstationary vector-borne disease. PLoS Med, 3(8), e295.

7- Cherabin, Palideh, Gharavi, Gharavi & mahmood, m. A. S., A, A, A. (2012). Epidemiological characteristics of Cautaneous Leishmaniasis in Maraveh tapeh district, Golestan province during 2006-2010. Journal of zabol university of medical sciences and health services, 4(1), 19-27.

8- Draper & Smith, N., H. (1998). Applied regression analysis, Wiley Interscience. New York, 505-553.

9- Gordis, L. (2000). Epidemiology WB Saunders. Philadelphia, PA.

10- Hagan, Demuth, Beale & De Jesús, M. T., H. B., M. H., O. (1996). Neural network design, Vol. 20, PWS publishing company Boston.

11- Hassan, Kenawy, Kamal, Abdel Sattar& Sowilem, A., M., H., A., M. (2003). GIS-based prediction of malaria risk in Egypt. Eastern Mediterranean Health Journal, 9(4), 11.

12- Herbreteau, Demoraes, Khaungaew, Hugot, Gonzalez, Kittayapong& Souris, V., F., W., J.-P., J.-P., P., M. (2006). Use of geographic information system and remote sensing forassessing environment influence on leptospirosis incidence, Phrae province, Thailand. International Journal of Geoinformatics, 2(4), 43-50.

13- Holakouie-Naieni, Mostafavi, Boloorani, Mohebali& Pakzad, K., E., A. D., M., R. (2017). Spatial modeling of cutaneous leishmaniasis in Iran from 1983 to 2013. Acta Tropica, 166, 67-73.

14- Hornik, Stinchcombe& White, K., M., H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, 2(5), 359-366.

15- Hsu, Chang& Lin, C.-W., C.-C., C.-J. (2003). A practical guide to SVM classification. Department of Computer Science and Information Technology, National Taiwan University. Paper available a t http, (www. csie. ntu. edu. tw/~ cjlin/papers/guide/guide. pdf, 16).

16- Hyndman & Koehler, R. J., A. B. (2006). Another look at measures of forecast accuracy. International journal of forecasting, 22(4), 679-688.

17- Massoomy & Mesgari, Z., M. S. (2006). PREDICTION OF SKIN CANCER EPIDEMIOLOGY FOR DECISION MAKING USING GEOSTATISTICAL ANALYSES. Paper presented at the ASPRS 2006 Annual Conference, Reno, Nevada.

18- McLafferty, S. L. (2003). GIS and health care, Annual review of public health, 24(1), 25-42.

19- Menhaj, M. (1998). Fundamentals of neural networks. Computational intelligence, 1(1).

20- Mesgari & Masoomi, M., Z. (2008). GIS applications in public health as a decision making support system and it’s limitation in Iran. World appl Sci J (Supple 1), 3, 73-77.

21- Mitchell, A. (2005). The ESRI guide to GIS analysis, Volume 2, Spatial Measurements and Statistics. Redlands: CA: Esri Press.

22- Mohammady& Delavar, S., M. (2014). Urban Expansion Modeling with Logistic Regression. Journal of Geomatics Science and Technology, 4(2), 77-86.

23- MOLLALO, A. (2014). Spatio-Temporal Analyses and Modeling of Cutaneous Leishmaniasis Disease, Alimohammadi., Malek., A., M.R., K.N. Toosi University of Technology, Civil-Surveying Engineering In GIS.

24- Mollalo, Alimohammadi, Shirzadi& Malek, A., A., M., M. (2015). Geographic Information System-Based Analysis of the Spatial and Spatio-Temporal Distribution of Zoonotic Cutaneous Leishmaniasis in Golestan Province, North-East of Iran. Zoonoses and public health, 62(1), 18-28.

25- Moran, P. A. (1950). Notes on continuous stochastic phenomena. Biometrika, 37(1/2), 17-23.

26- Morrone, Pitidis, Pajno, Dassoni, Latini, Ab Barnabas& Padovese, A., A., M. C., F., O., G., V. (2011). Epidemiological and geographical aspects of leishmaniasis in Tigray, northern Ethiopia: a retrospective analysis of medical records, 2005-2008. Transactions of the Royal Society of Tropical Medicine and Hygiene, 105(5), 273-280.

27- Mozaffari, BAKHSHIZADEH& GHEIBI, G., F., M. (2012). Analysis relationship between vegetation cover and Salak skin disease in Yazd-Ardakanplain. 22(4), 167-178.

28- Organization, W. H. (2009). A human rightsbased approach to neglected tropical diseases: WHO.

29- Rajabi, Mansourian, Pilesjö& Bazmani, M., A., P., A. (2014). Environmental modelling of visceral leishmaniasis by susceptibility-mapping using neural networks: a case study in north-western Iran. Geospatial health, 9(1), 179-191.

30- Rajabi, Pilesjö, Shirzadi, Fadaei& Mansourian, M., P., M. R., R., A. (2016). A spatially explicit agent-based modeling approach for the spread of CutaneousLeishmaniasis disease in central Iran, Isfahan. Environmental Modelling & Software, 82, 330-346.

31- Ramezankhani, Hosseini, Sajjadi, Khoshabi& Ramezankhani, R., A., N., M., A. (2017). Environmental risk factors for the incidence of cutaneous leishmaniasisin an endemic area of Iran: A GIS-based approach. Spatial and Spatio-temporal Epidemiology, 21, 57-66.

32- Raoufy, Vahdani, Alavian, Fekri, Eftekhari, & Gharibzadeh, M. R., P., S. M., S., P., S. (2011). A novel method for diagnosing cirrhosis in patients with chronic hepatitis B: artificial neural network approach. Journal of medical systems, 35(1), 121-126.

33- Rassi, Javadian, Jalali, Motazedian& Vatndoost, Y., E., M., M., H. (2004). Investigation on Zoonotic Cutaneous Leishm-aniasis, Southern Iran. Iranian Journal of Public Health, 33(1), 31-35.

34- Ribeiro Jr, & Diggle, P., P. (2001). geoR: A package for geostatistical analysis, 2001: ISSN.

35- Ripley, B. (1981). Spatial statistics, 252 pp: John Wiley, New York.

36- Ruiz, Tedesco, McTighe, Austin& Kitron, M. O., C., T. J.,C., U. (2004). Environmental and social determinants of human risk during a West Nile virus outbreak in the greater Chicago area, 2002. International Journal of Health Geographics, 3(1), 8.

37- Saltelli, A. (2002). Sensitivity analysis for importance assessment. Risk Analysis, 22(3), 579-590.

38- Saltelli, Ratto, Andres, Campolongo, Cariboni, Gatelli& Tarantola, A., M., T., F., J., D., S. (2008). Global sensitivity analysis: the primer: John Wiley & Sons.

39- Shirzadi, Mollalo& Yaghoobi-Ershadi, M. R., A., M. R. (2015). Dynamic relations between incidence of zoonotic cutaneous leishmaniasis and climatic factors in Golestan Province, Iran. Journal of arthropod-borne diseases, 9(2), 148.

40- Skapura, D. M. (1996). Building neural networks: Addison-Wesley Professional.

41- Soccol, de Castro, e Schühli, de Carvalho, Marques, de Fátima Pereira& Membrive, V. T., E. A., G. S., Y., E., E., N. (2009). A new focus of cutaneous leishmaniasis in the central area of Paraná State, southern Brazil. Acta Tropica. 111(3), 308-315.

42- Tobler, W. R. (1970). A computer movie simulating urban growth in the Detroit region. Economic Geography, 46(sup1), 234-240.

43- Tofallis, C. (2015). A better measure of relative prediction accuracy for model selection and model estimation. Journal of the Operational Research Society, 66(8), 1352-1362.

44- Williams & Hinton, D., G. (1986). Learning representations by back-propagating errors. Nature, 323, 533-536.

45- Yilmaz, I. (2009). Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: a case study from Kat landslides (Tokat—Turkey). Computers & Geosciences, 35(6), 1125-1138.

46- Zare, Shamszadeh& Najjari, M., P., A. (2006). Providing the opportunity to use GIS in decision-making in the health sector management. Hakim, 9(1), 58-63.