BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.cienciaenmexico.com//igisc-2026//speaker//YCGTRP
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=5SU;BYMONTH=10;UNTIL=20001029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20010930T030000
RRULE:FREQ=YEARLY;BYDAY=5SU;BYMONTH=9;UNTIL=20010930T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20021027T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20000402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20010506T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=5;UNTIL=20010506T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20020407T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20220403T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-igisc-2026-KKVUM8@pretalx.cienciaenmexico.com
DTSTART;TZID=CST:20261112T113000
DTEND;TZID=CST:20261112T114500
DESCRIPTION:## Introduction\n\n### The spatial scale problem in official st
 atistics\n\nGeographic scale plays a fundamental role in spatial epidemiol
 ogy because it determines the ability to identify territorial disease patt
 erns and support public health interventions [1]\, [2]. When health inform
 ation is reported at aggregated spatial levels\, important local variation
 s may remain hidden\, limiting the identification of municipalities where 
 suicide risk differs substantially from expected levels [3].\n\nIn Mexico\
 , the National Institute of Statistics and Geography (INEGI) publishes off
 icial suicide statistics primarily as age-standardized mortality rates at 
 the state level [4]. Although these statistics describe the overall patter
 n of suicide and allow comparisons among states\, they do not capture loca
 l variations in suicide risk or incorporate information on mental health c
 onditions and territorial characteristics.\n\nConsequently\, state-level i
 ndicators may provide an incomplete picture of the phenomenon. States with
  relatively low suicide rates\, such as Guerrero\, Oaxaca\, or the State o
 f Mexico\, may still contain municipalities with substantially elevated ri
 sks. Conversely\, high state-level rates do not necessarily imply a homoge
 neous spatial distribution\, since excess risk may be concentrated in only
  a few municipalities. This aggregation limits the identification of prior
 ity municipalities for territorial analysis and suicide prevention.\n\n## 
 Research gap\n\nRelative risk estimation is widely used in epidemiology to
  identify areas where disease occurrence is higher or lower than expected 
 after accounting for demographic structure [5]. Count regression models ha
 ve been successfully applied to estimate disease risk at small geographica
 l scales [6].\n\nHowever\, our literature review did not identify publishe
 d studies proposing a methodology to estimate municipal suicide relative r
 isk in Mexico by integrating administrative health records\, demographic i
 nformation\, and territorial indicators within a count regression framewor
 k. One reason is the absence of municipal-level prevalence estimates for m
 ental disorders.\n\nTo overcome this limitation\, this study uses administ
 rative healthcare records as **indirect indicators** of population mental 
 health conditions. Although these records do not measure prevalence direct
 ly\, they provide a continuous\, standardized\, and geographically referen
 ced source of information.\n\nThe objective of this work is therefore to d
 evelop a reproducible methodology for estimating municipal suicide relativ
 e risk using administrative health records\, demographic information\, and
  territorial indicators.\n\n## Methodological framework\n\nThe proposed me
 thodology estimates municipal suicide relative risk for the period 2013–
 2023 through four stages.\n\n**Stage 1. Expected cases.** Expected suicide
 s were estimated through indirect standardization [5]. National age- and s
 ex-specific suicide rates were computed as\n\n$\n$r_{jt}=\n\\frac{\\sum_i 
 y_{ijt}}\n{\\sum_i n_{ijt}}\n$$\n\nand expected cases as\n\n$$\nE_{it}=\\s
 um_j r_{jt}n_{ijt}\,\n$$\n\nwhere $E_{it}$ denotes the expected number of 
 suicides in municipality $i$ during year $t$. Expected cases constitute th
 e epidemiological baseline and were incorporated into the regression model
  as an exposure (*offset*) term.\n\n**Stage 2. Analytical dataset.** A mun
 icipality–year database was built by integrating observed suicides\, exp
 ected cases\, administrative healthcare records compiled by the National I
 nstitute of Psychiatry Ramón de la Fuente Muñiz\, and territorial indica
 tors from CONAPO. Administrative records included depression\, legal and i
 llegal substance use\, domestic violence\, and the availability of psychol
 ogists and psychiatrists. The final dataset comprised **1\,399 municipalit
 y–year observations** from **198 municipalities** across Mexico.\n\n**St
 age 3. Variable selection.** Lasso regularization for count regression mod
 els was applied to identify informative explanatory variables while reduci
 ng multicollinearity [7].\n\n**Stage 4. Relative risk estimation.** Owing 
 to overdispersion in suicide counts\, a Negative Binomial regression model
  was fitted [8]\, [9]:\n\n$$\nY_i\\sim NB(\\mu_i\,\\theta)\n$$\n\nwith\n\n
 $$\n\\log(\\mu_i)=\\log(E_i)+\\mathbf{x}_i^\\top\\boldsymbol{\\beta}\,\n$$
 \n\nwhere $\\log(E_i)$ is the offset term. Municipal relative risk was est
 imated as\n\n$$\nRR_i=\\exp(\\mathbf{x}_i^\\top\\boldsymbol{\\beta})\,\n$$
 \n\nwhere $RR_i>1$ indicates higher-than-expected risk and $RR_i<1$ lower-
 than-expected risk.\n\n## Main findings\n\nThe proposed methodology estima
 ted municipal suicide relative risk for 198 municipalities and generated a
 nnual risk maps for 2013–2023. Results revealed substantial local spatia
 l variation that remains hidden when analyses rely exclusively on state-le
 vel statistics.\n\nThe final model identified psychiatrist availability as
  a protective factor (IRR = 0.774)\, whereas psychologist availability (IR
 R = 1.765)\, illegal substance use (IRR = 1.138)\, domestic violence (IRR 
 = 1.128)\, households with dirt floors (IRR = 1.246)\, and households with
 out drainage (IRR = 1.561) were associated with increased relative risk.\n
 \nAs an illustration\, Acapulco de Juárez exhibited a relative risk appro
 ximately four times higher than expected at the beginning of the study per
 iod and more than nine times higher than expected in 2023\, despite belong
 ing to Guerrero\, one of the Mexican states with the lowest official suici
 de mortality rates.\n\n## Contributions\n\nThis work develops a reproducib
 le methodology for estimating municipal suicide relative risk by integrati
 ng indirectly standardized expected cases\, administrative healthcare reco
 rds as indirect indicators of mental health conditions\, and territorial i
 ndicators within a Negative Binomial regression framework. To the best of 
 our knowledge\, our literature review did not identify published studies p
 roposing a comparable methodological framework for municipal suicide risk 
 estimation in Mexico.\n\nThe methodology complements official statistics b
 y producing municipal-level estimates and maps of suicide relative risk\, 
 allowing local spatial variations to be identified that remain hidden in s
 tate-level analyses. The proposed framework provides a reproducible approa
 ch for territorial analyses of suicide and for identifying municipalities 
 with elevated relative risk.\n\n## References\n\n[1] Elliott et al.\, *Spa
 tial Epidemiology*\, 2000.\n\n[2] Waller and Gotway\, *Applied Spatial Sta
 tistics for Public Health Data*\, 2004.\n\n[3] Openshaw\, *The Modifiable 
 Areal Unit Problem*\, 1984.\n\n[4] INEGI\, *Suicide Statistics*\, 2025.\n\
 n[5] Moraga\, *Geospatial Health Data*\, 2023.\n\n[6] Cameron and Trivedi\
 , *Regression Analysis of Count Data*\, 2013.\n\n[7] Wang et al.\, *Statis
 tical Methods in Medical Research*\, 2016.\n\n[8] McCullagh and Nelder\, *
 Generalized Linear Models*\, 1989.\n\n[9] Hilbe\, *Negative Binomial Regre
 ssion*\, 2011.
DTSTAMP:20261122T123844Z
LOCATION:Multifuncional (Remoto)
SUMMARY:Estimation of Suicide Relative Risk at the Municipal Level Using Ad
 ministrative Health Records and Count Regression Models - Jorge Pool
URL:https://pretalx.cienciaenmexico.com/igisc-2026/talk/KKVUM8/
END:VEVENT
END:VCALENDAR
