Hybrid Prediction Models for Suicide Mortality Levels in Iranian Provinces: Spatial Econometrics vs. Random Forests

Document Type : Original Research Articles

Authors
Mohadeseh Farzammehr 1
Geoffrey J McLachlan 2
1 1 Judiciary Research Institute, Tehran, Islamic Republic of Iran
2 2 Department of Mathematics, University of Queensland, Brisbane, Australia
10.22059/jsciences.2025.397759.1007936
Abstract
With the growing utilization of advanced machine-learning techniques, such as random forests, understanding the significance of spatial factors within these models is increasingly imperative. This study proposes a novel approach to develop spatially explicit classification random forest models by integrating spatially lagged variables, mirroring various spatial panel data econometric specifications. We assess the comparative performance of these models against traditional spatial and non-spatial regression methods to predict suicide mortality rates across 31 provinces in Iran, utilizing data from 2011 to 2021. Results reveal that the spatial random forest model, incorporating spatial lag parameters, achieves a remarkable accuracy of 89.19% in predicting suicide mortality levels, surpassing traditional spatial econometric models (46.51%) and non-spatial random forest models (27.03%). While highlighting the effectiveness of spatial random forest models with spatial lag parameters, this study also recognizes the continued relevance of traditional spatial econometric models in predicting suicide mortality rates. These findings offer valuable insights into the interplay between spatial considerations and predictive modeling, providing essential guidance for researchers in selecting appropriate models for spatial data analysis.
Keywords
Spatial Econometrics models
Machine-Learning Techniques
Random Forests
Iran
Subjects
  1. Openshaw S, Openshaw C. Artificial intelligence in geography. New York (NY): John Wiley & Sons Inc; 1997.
  2. Breiman L. Random forests. Mach Learn. 2001;45:5-32.
  3. Breiman L. Statistical modeling: the two cultures. Stat Sci. 2001;16:199-231.
  4. Shojaei A, Moradi S, Alaeddini F, Khodadoost M, Barzegar A, Khademi A. Association between suicide method and gender, age, and education level in Iran over 2006–2010. Asia Pac Psychiatry. 2014;6:18-22.
  5. Khademi AMS. Statistical investigation of unnatural deaths in Iran (2001–2010). Tehran: Forensic Medicine Organization; 2012.
  6. Rey S. Geographical analysis: reflections of a recovering editor. Geogr Anal. 2019;1-9. doi:10.1111/gean.12193.
  7. Singleton A, Arribas-Bel D. Geographic data science. Geogr Anal. 2019;1-15. doi:10.1111/gean.12194.
  8. Adin A, Retegui G, Villegas AS, Ugarte MD. Suicide Mortality in Spain (2010-2022): Temporal Trends, Spatial Patterns, and Risk Factors. arXiv preprint arXiv:2509.01342. 2025.
  9. Al-Remawi M, Agha ASA, Al-Akayleh F, Aburub F, Abdel-Rahem RA. Artificial intelligence and machine learning techniques for suicide prediction: Integrating dietary patterns and environmental contaminants. Heliyon. 2024;10(24).
  10. Ehtemam H, Sadeghi Esfahlani S, Sanaei A, Ghaemi MM, Hajesmaeel-Gohari S, Rahimisadegh R, et al. Role of machine learning algorithms in suicide risk prediction: a systematic review and meta-analysis of clinical studies. BMC Med Inform Decis Mak. 2024;24(1):138.
  11. Prateek J. Artificial intelligence with Python: a comprehensive guide to building intelligent apps for Python beginners and developers. Birmingham (UK): Packt Publishing; 2017. p. 49-67.
  12. Géron A. Hands-on machine learning with Scikit-Learn & TensorFlow: concepts, tools, and techniques to build intelligent systems. Boston (MA): O’Reilly Media; 2017. p. 3-224.
  13. Janowicz K, Gao S, McKenzie G, Hu Y, Bhaduri B. GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond. Int J Geogr Inf Sci. 2019;34:625-36. doi:10.1080/13658816.2019.1684500.
  14. Credit K. Transitive properties: a spatial econometric analysis of new business creation around transit. Spatial Econ Anal. 2019;14:26-52.
  15. Hengl T, Nussbaum M, Wright MN, Heuvelink GBM, Gräler B. Random forests as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ. 2018;6:e5518. doi:10.7717/peerj.5518.
  16. Georganos S, Grippa T, Gadiaga N, Linard C, Lennert M, Vanhuysse S, et al. Geographical random forests: a spatial extension to the random forests algorithm to address spatial heterogeneity in remote sensing and population modeling. Geocarto Int. 2019. doi:10.1080/10106049.2019.1595177.
  17. Yan B, Janowicz K, Mai G, Zhu R. A spatially explicit reinforcement learning model for geographic knowledge graph summarization. Trans GIS. 2019;29:620-40.
  18. Farzammehr MA, Moradi S. Classical and spatial cluster analysis of smuggling in Iranian provinces. Reg Sci Policy Pract. 2022;16(2):12609.
  19. Anselin L. Spatial econometrics: methods and models. Dordrecht: Kluwer Academic Publishers; 1988. p. 169-79.

 
  1. Probst P, Wright MN, Boulesteix AL. Hyperparameters and tuning strategies for random forest. Wiley Interdisciplinary Reviews: data mining and knowledge discovery. 2019 May;9(3):e1301.
  2. Elhorst JP. Spatial econometrics: from cross-sectional data to spatial panels. Heidelberg: Springer; 2014 Jan 16.
  3. LeSage JP, Pace RK. Introduction to spatial econometrics. New York (NY): CRC Press; 2009. p. 25-75.
  4. Haining RP. Spatial data analysis: theory and practice. Cambridge university press; 2003 Apr 17.
  5. Tobler WR. A computer movie simulating urban growth in the Detroit region. Econ Geogr. 1970;46:234-40.
  6. Anselin L, Rey S. Modern spatial econometrics in practice. Chicago (IL): GeoDa Press LLC; 2014. p. 1-43.
  7. LeSage JP. Spatial econometric panel data model specification: a Bayesian approach. Spatial Stat. 2014;9:122-45.
  8. Krzywinski M, Altman N. Classification and regression trees. Nat Methods. 2017;14:757-8.
  9. Fox EW, Ver Hoef JM, Ohlen AR. Comparing spatial regression to random forests for large environmental data sets. PLoS One. 2020;15(3):e0229509.
  10. Lagomarsino D, Tofani V, Segoni S, Catani F, Casagli N. A tool for classification and regression using random forest methodology: applications to landslide susceptibility mapping and soil thickness modeling. Environ Model Assess. 2017;22:201-14.
  11. Talebi H, Peeters LJ, Otto A, Tolosana-Delgado R. A truly spatial random forests algorithm for geoscience data analysis and modelling. Math Geosci. 2022;54(1):1-22.
  12. Madadi M, Motarjem K. Survival data analysis using statistical learning methods. J Stat Sci. 2025;18(2).
  13. Wang Y, Yin Y, Gao B, Zeng Y, Zhao Y, Chen Z, et al. A novel spatial prediction method integrating Exploratory Spatial Data Analysis into Random Forest for large-scale daily air temperature mapping. IEEE Trans Geosci Remote Sens. 2025.
  14. Anselin L, Bera AK, Florax R, Yoon MJ. Simple diagnostic tests for spatial dependence. Reg Sci Urban Econ. 1996;26:77-104. doi:10.1016/0166-0462(95)02111-6.
  15. Nock MK, Borges G, Bromet EJ, Cha CB, Kessler RC, Lee S. Suicide and suicidal behavior. Epidemiologic reviews. 2008 Jul 24;30(1):133.
  16. Bilsen J. Suicide and youth: risk factors. Frontiers in psychiatry. 2018 Oct 30;9:540.
  17. Credit K. Spatial models or random forests? Evaluating spatially explicit machine learning methods to predict employment density around new transit stations in Los Angeles. Geogr Anal. 2022;54:58-83.
  18. Stack S. Contributing factors to suicide: Political, social, cultural and economic. Preventive medicine. 2021 Nov 1;152:106498.
Journal of Sciences, Islamic Republic of Iran
Volume 36, Issue 1
Winter 2025
Pages 39-49