Journal of Artificial Intelligence and Computing Applications (2025) - Special Issue - 3(2): 10 Conference abstract Analyzing municipal patterns of suicide and depression in mexico: a multilayer network approach Jorge Manuel Pool Cen 1,*, Hugo Carlos Mart´ınez 1, Gandhi Samuel Hern´andez Chan 1, Alfredo Alejandro Montero Arciniega 2, Pedro Alberto Mendoza Pablo 3, and Martha Cordero Oropeza 4 1Centro de Investigaci´on en Ciencias de Informaci´on Geoespacial (Centro Geo); Laboratorio Nacional de Geointeligencia 2EPO 339; Colegio de Bachilleres 3Escuela Militar de Graduados de Sanidad 4Instituto Nacional de Psiquiatr´ıa ”Ram´on de la Fuente Mu˜niz” ABSTRACT This study analyzes the territorial patterns of suicide and depression in Mexican municipalities from 2015 to 2020 using a multilayer network approach. A panel dataset was constructed with variables grouped into three categories: mental health cases (suicide and depression rates), substance use (alcoholism, tobacco use, and drug use), and infrastructure availability (mental health services and resources). Cosine similarity was used to generate multilayer graphs, and the Infomap algorithm was applied to identify clusters of municipalities with similar structural characteristics. The results show clear differences across clusters in both levels and temporal dynamics of the indicators. Notably, Clusters 1 and 2 consistently exhibited higher rates of substance use and mental health indicators. These findings highlight the value of network-based approaches to understanding the territorial and temporal dimensions of mental health. Keywords: clustering, multilayer graph, mental health This work corresponds to a paper presented at the International Conference on Artificial Intelligence for Mental Health (ICAIMH) 2025, where it was selected as one of the recipients of the Best Paper Award. The complete version is expected to be published soon after the conference. E-mail address:
[email protected] https://doi.org/10.5281/zenodo.17229663 ©2025 The Author(s). Published by Maikron. This is an open access article under the CC BY license. This article is part of the Special Issue on ICAIMH 2025. ISSN: 3061-8843
