Predicting the Best Hospital Sites in Visakhapatnam through Machine Learning Analysis

IJEP 43(12): 1074-1085 : Vol. 43 Issue. 12 (December 2023)

Abhishek Dondapati1, Aneesah Rahaman2, Ratnaprabha Jadhav3, Brototi Biswas4* and Sabirul Sk5

1. University of Madras, Department of Management Studies, Chennai – 600 005, Tamil Nadu, India
2. University of Madras, The Centre for Natural Hazards and Disaster Studies (CNHDS), Chennai – 600 005, Tamil Nadu, India
3. SNDT Women’s University, Department of Geography, Pune – 411 038, Maharashtra, India
4. Mizoram University, Department of Geography and Resource Management, Aizawl – 796 004, Mizoram, India
5. Indian Institute of Technology Bombay, Mumbai – 400 076, Maharashtra, India


This study aimed to evaluate the suitability of different locations in Visakhapatnam city for hospital sites using three machine learning algorithms, including support vector machine (SVM), multi-layer perceptron (MLP) and random forest (RF). The results showed that the SVM model had the highest accuracy in classifying suitable and non-suitable locations compared to the other two models, with an area under the curve (AUC) of 0.95. The study also analysed the relative influence of different parameters on the suitability of hospital sites, with population density being the most significant factor affecting suitability. The study highlights the potential of machine learning approaches for hospital site suitability assessment and the significance of population density as a factor affecting hospital site suitability. The SVM model, which performed the best, can be used as a tool for site selection and planning. Analysing the relative influence of parameters can help stakeholders make informed decisions for hospital development. However, the study has limitations, including a limited sample size and using only five parameters for evaluation.


Hospital site suitability, Support vector machines, Random forest, Multi-layered perceptron, Area under curve


  1. Kumar, M., et al. 2019. Site suitability analysis for urban development using geospatial technologies and AHP: A case study in Prayagraj, Uttar Pradesh, India. Pharma. Innovations J., 8:676-681.
  2. Ahmed, S., et al. 2019. Impact of traffic variability on geographic accessibility to 24/7 emergency healthcare for the urban poor: A GIS study in Dhaka, Bangladesh. PLoS ONE. 14(10):e0222488.
  3. Ministry of Health and Family Welfare. 2021. National health profile 2021. Available at: https://nhp.
  4. WHO. 2021. Health in India. World Health Organization, Geneva.
  5. National Rural Health Mission. 2021. Rural health statistics in India. Available at: https://www.nrhm.
  6. WHO. 2017. Health systems strengthening. World Health Organization, Geneva. Available at:
  7. Zhou, L. and J. Wu. 2012. GIS-based multi-criteria analysis for hospital site selection in Haidian district of Beijing. Masters Thesis. University of Gävle, Sweden.
  8. Maantay, J.A., A.R. Maroko and C. Herrmann. 2007. Mapping population distribution in the urban environment: The cadastral-based expert dasyme-tric system (CEDS). Cartography Geogr. Inf. Sci., 34(2): 77-102.
  9. Mojaddadi, H.R. 2018. Flood risk assessment using multi-sensor remote sensing, geographic information system, 2D hydraulic and machine learning based models. Ph.D. Thesis. University of Technology Sydney (UTS), Australia.
  10. McLafferty, S.L. 2003. GIS and healthcare. Annual Review Public Health. 24: 25-42.
  11. Chatterjee, D. and B. Mukherjee. 2013. Potential hospital location selection using AHP: A study in rural India. Int. J. Computer Applications. 71(18): 1-7.
  12. Kahraman, C., et al. 2019. Hospital location selection using spherical fuzzy TOPSIS. Proceedings of 11th Conference of the European society for fuzzy logic and technology (EUSFLAT 2019). DOI: 10.2991/eusflat-19.2019.12
  13. Wu, C.R., C.T. Lin and H.C. Chen. 2007. Optimal selection of location for Taiwanese hospitals to ensure a competitive advantage by using the analytic hierarchy process and sensitivity analysis. Build. Env., 42:1431-1444.
  14. Vahidnia, M.H., A.A. Alesheikh and A. Alimoham-madi. 2009. Hospital site selection using fuzzy AHP and its derivatives. J. Env. Manage., 90:3048-3056.
  15. Chen, Y.F., Y.H. Huang and Y.C. Hsu. 2017. An assessment of hospital location planning in Taiwan using GIS and multi-criteria decision analysis. Health Place. 45:78-86.
  16. Mohammad, R., M.A. Neda and B. Mojtaba. 2019. Site selection for new hospitals in Iran using GIS and AHP. Int. J. Health Geogr., 18(1):11.
  17. Zhang, L., Y. Tan and X. Li. 2020. Site selection of new hospitals in China based on GIS and machine learning. Appl. Geogr., 126:102097.
  18. Hussein, M.A., M.A. Al-Kayed and Z. Al-Salti. 2021. Accessibility assessment of potential hospital sites in Jordan using GIS and machine learning algorithms. Health Place. 67:102144.
  19. Tan, Y.S., S. Ismail and C.Y. Lee. 2018. Evaluating the suitability of potential hospital sites in Malaysia using GIS and weighted linear combination (WLC). Geospatial Health. 13(2):519-529.
  20. Tripathi, A.K., S. Agrawal and R.D. Gupta. 2021. Comparison of GIS-based AHP and fuzzy AHP methods for hospital site selection: a case study for Prayagraj city, India. Geo. J., 87:3507–3528.
  21. Wang, J., J. Kim and Y. Lee. 2023. Evaluating the suitability of potential hospital sites in South Korea using GIS and artificial neural networks (ANN). Geospatial Health. 18(2): 554-564.
  22. Almansi, M., A. Al-Sulaiman and N. Al-Zaid. 2021. A comparative analysis of SVM, MLP and LR models for evaluating the suitability of potential hospital sites in Saudi Arabia. Geospatial Health. 16(3): 789-801.
  23. Tehrany, M.S., L. Kumar and F. Shabani. 2019. A novel GIS-based ensemble technique for flood susceptibility mapping using evidential belief function and support vector machine: Brisbane, Australia. Peer J., 7:7653.
  24. Jebur, M. N., B. Pradhan and M.S. Tehrany. 2014. Detection of vertical slope movement in highly vegetated tropical area of Gunung pass landslide, Malaysia, using L-band InSAR technique. Geosci. J., 18:61-68.
  25. Rizeei, M.H. 2018. Flood risk assessment using multi-sensor remote sensing, geographic information system, 2D hydraulic and machine learning based models. PhD Thesis. University of Technology Sydney (UTS), New South Wales, Australia.
  26. Hall, M.A. 1999. Correlation-based feature selection for machine learning. Ph.D. Thesis. University of Waikato, Hamilton, New Zealand.
  27. Sadeghi, R., et al. 2013. Application of genetic algorithm and greedy stepwise to select input variables in classification tree models for the prediction of habitat requirements of Azolla filiculoides (Lam.) in Anzali wetland, Iran. Ecol. Modelling. 251: 44-53.
  28. Sahoo, G. and Y. Kumar. 2012. Analysis of parametric and non-parametric classifiers for classification technique using WEKA. Int. J. Inf. Tech. Computer Sci., 4:43.
  29. Cortes, C. and V. Vapnik. 1995. Support-vector networks. Machine Learning. 20(3):273-297.
  30. Kecman, V. 2001. Support vector machines. Harvard Business Review. 79(1): 53-60.
  31. Hastie, T., R. Tibshirani and J. Friedman. 2017. The elements of statistical learning: Data mining, inference and prediction. Springer. DOI: 10.1007/978-0-387-84858-7.
  32. Chang, C.C. and C.J. Lin. 2011. LIBSVM: A library for support vector machines. ACM Trans. Intelligent Systems Tech., 2(3):1-27.
  33. Suykens, J.A. and J. Vandewalle. 2002. Least squares support vector machine classifiers. Neural Processing Letters. 15(3):261-271.
  34. Cristianini, N. and S.J. Taylor. 2000. An introduction to support vector machines and other kernel-based learning methods. Cambridge university press.
  35. Smola, A.J. and B. Schölkopf. 2004. A tutorial on support vector regression. Statistics Computing. 14(3): 199-222.
  36. Breiman, L. 2001. Random forests. Machine learning. 45(1): 5-32.
  37. Cutler, A. and B. Edelman. 1997. Random forests. In Technical report (vol. 1198). Department of Statistics, University of California, Berkeley.
  38. Liaw, A. and M. Wiener. 2002. Classification and regression by random forest. 2(3):18-22.
  39. Quinlan, J.R. 1993. C4.5: programmes for machine learning. Morgan Kaufmann Publishers Inc., San Francisco, USA.
  40. Rumelhart, D.E., G.E. Hinton and R.J. Williams. 1986. Learning internal representations by error propagation. In Parallel distributed processing: Explorations in the microstructure of cognition. Ed D.E. Rumelhart and J.L. McClelland. MIT Press, Cambridge, Massachusetts. pp 318-362.
  41. Haykin, S. 1999. An introduction to neural networks. Prentice Hall Press.
  42. Goodfellow, I., Y. Bengio and A. Courville. 2016. Deep learning. MIT press.
  43. LeCun, Y., Y. Bengio and G. Hinton. 2015. Deep learning. Nature. 521(7553): 436-444.
  44. Miller, A.J. 2013. Assessing landslide susceptibility by incorporating the surface cover index as a measurement of vegetative cover. Land Degrad. Develop., 24: 205-227.
  45. Ornella, L. and E. Tapia. 2010. Supervised machine learning and heterotic classification of maise (Zea mays L.) using molecular marker data. Comput. Electron. Agric., 74: 250-257.
  46. Tehrany, M.S., B. Pradhan and M.N. Jebur. 2014. Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS. J. Hydrol., 512: 332-343.
  47. Katla, S., et al. 2017. DPWeka: Achieving differential privacy in WEKA. 2017 IEEE Symposium on Privacy-aware computing. Washington DC, USA.
  48. Kalantar, B., et al. 2020. Forest fire susceptibility prediction based on machine learning models with resampling algorithms on remote sensing data. Remote Sens., 12(22): 3682.
  49. Guyon, I. and A. Elisseeff. 2003. An introduction to variable and feature selection. J. Mach. Learn. Res., 3:1157-1182.
  50. Zandi, I. and P. Pahlavani. 2021. Spatial modelling and prioritization of potential areas for determining location of hospitals by a GIS-based multi-criteria decision making analyses: A case study of the 5th district of Tehran. Town Country Planning. 13(1):247-280.
  51. Mayfield, C.J. 2015. Automating the classification of thematic rasters for weighted overlay analysis in GeoPlanner for ArcGIS. Ph.D. Thesis. University of Redlands, California, USA.
  52. Xiong, Y., et al. 2020. Spatial statistics and influencing factors of the novel Corona virus pneumonia 2019 epidemic in Hubei province, China. Research Square. DOI: 10.21203/
  53. Ahmed, N., M.R. Islam and M.A. Hossain. 2017. Hospital site selection using GIS and decision tree algorithm: A case study in Bangladesh. J. King Saud Univ. Computer Inf. Sci., 29(4): 474-484.