{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:10:02Z","timestamp":1784182202821,"version":"3.55.0"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Epidemiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The Cox proportional hazards (PH) model is widely used in time-to-event research, but its validity depends on the PH assumption, which can be violated in child mortality studies where hazards vary with age. Piecewise exponential models (PEMs) relax this assumption by partitioning follow-up time into intervals. However, standard formulations impose constant hazards within each interval and typically ignore spatial heterogeneity, limiting their usefulness for public health analyses in which geographical variation in risk is important. Existing extensions address non-proportional hazards or spatial dependence separately, but rarely combine a smooth baseline hazard, interval-level temporal heterogeneity, and structured spatial frailty within a single, computationally tractable Bayesian framework. This study proposes and applies such a framework to under-five mortality (U5M) in Nigeria.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We formulated a Bayesian spline-augmented PEM incorporating a cubic-spline-smoothed baseline hazard, interval-specific Gaussian random effects, and a spatial frailty term with an intrinsic conditional autoregressive (ICAR) prior, within the latent Gaussian modeling framework of integrated nested Laplace approximation (INLA), with survival reformulated as a Poisson likelihood. The model was applied to U5M data for 103,439 children from the 2024 Nigeria Demographic and Health Survey (NDHS). Five nested model specifications (basic PEM, spline-augmented, spline plus interval effects, spline plus spatial effects, and the full spline-interval-spatial model) were compared across three sample sizes using DIC, WAIC, conditional predictive ordinates, posterior predictive checks, and calibration metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The global test of the PH assumption was significant (\u03c7\n                      <jats:sup>2<\/jats:sup>\n                      \u2009=\u2009898.66,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&amp;lt;\u20092 x 10\n                      <jats:sup>-16<\/jats:sup>\n                      ), with all individual covariates significant at\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt; 0.05. Across all three sample sizes, the full spline-interval-spatial model achieved the lowest DIC and WAIC, the lowest CPO, and the highest posterior predictive correlation and calibration R\n                      <jats:sup>2<\/jats:sup>\n                      among the five candidates, with the largest single reduction in DIC (approximately 17,884 units at n\u2009=\u2009104,557) attributable to the addition of interval-specific random effects. In the fitted model, twin birth (HR\u2009=\u20092.82; 95% CrI: 2.62\u20133.03), breastfeeding status (HR\u2009=\u20090.45; 95% CrI: 0.42\u20130.49), and term delivery (HR\u2009=\u20090.47; 95% CrI: 0.41\u20130.53) had the largest effects on U5M, with additional protective effects for longer birth intervals and higher maternal education, and elevated risk in the North West (HR\u2009=\u20091.39) and North East (HR\u2009=\u20091.43) relative to the North Central region. Posterior spatial frailty estimates showed positive residual clustering concentrated in the North West and North East zones.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results indicate that jointly modeling temporal and spatial heterogeneity yields the best-fitting and best-calibrated specification, although spatial frailty adds comparatively little once interval-level temporal effects are included, suggesting that residual heterogeneity in this setting is predominantly temporal rather than spatial. The Poisson-INLA formulation provides a computationally efficient alternative to MCMC-based spatial survival models, making it well suited to large-scale demographic surveys. From a public health perspective, the identified biological, maternal, and socioeconomic determinants point to the need for integrated interventions, while the persistence of unexplained spatial clustering after covariate adjustment indicates structural or contextual vulnerabilities in the northern zones in Nigeria.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fepid.2026.1826352","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:39:25Z","timestamp":1784180365000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Bayesian spline-augmented piecewise exponential model with spatial frailty for under-five mortality in Nigeria"],"prefix":"10.3389","volume":"6","author":[{"given":"Peter Enesi","family":"Omaku","sequence":"first","affiliation":[{"name":"Department of Mathematical Statistics and Actuarial Sciences, University of the Free State","place":["Bloemfontein, South Africa"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph Odunayo","family":"Braimah","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, Ambrose Alli University","place":["Ekpoma, Edo State, Nigeria"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio Mathias","family":"Correa","sequence":"additional","affiliation":[{"name":"Department of Mathematical Statistics and Actuarial Sciences, University of the Free State","place":["Bloemfontein, South Africa"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","article-title":"Regression models and life-tables","volume":"34","author":"Cox","year":"1972","journal-title":"J R Stat Soc Ser B"},{"key":"B2","doi-asserted-by":"crossref","DOI":"10.1201\/b18041","volume-title":"Modelling Survival Data in Medical Research","author":"Collett","year":"2015"},{"key":"B3","first-page":"109","author":"Demarqui","year":"2011"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.1002\/sim.1203","article-title":"Flexible parametric proportional-hazards and proportional-odds models for censored survival data, with application to prognostic modelling and estimation of treatment effects","volume":"21","author":"Royston","year":"2002","journal-title":"Stat Med"},{"key":"B5","doi-asserted-by":"crossref","DOI":"10.1201\/9781315370279","volume-title":"Generalized Additive Models: An Introduction with R","author":"Wood","year":"2017"},{"key":"B6","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s10985-016-9361-4","article-title":"Generalized accelerated failure time spatial frailty model for arbitrarily censored data","volume":"23","author":"Zhou","year":"2017","journal-title":"Lifetime Data Anal"},{"key":"B7","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1177\/1536867X0900900206","article-title":"Further development of flexible parametric models for survival analysis","volume":"9","author":"Lambert","year":"","journal-title":"Stata J"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e1443","DOI":"10.1002\/wics.1443","article-title":"Spatial modeling with R-INLA: a review","volume":"10","author":"Bakka","year":"2018","journal-title":"WIREs Comput Stat"},{"key":"B9","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1111\/j.1467-9868.2008.00700.x","article-title":"Approximate Bayesian inference for latent Gaussian models by using integrated nested laplace approximations","volume":"71","author":"Rue","year":"2009","journal-title":"J R Stat Soc Ser B"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v014.i11","article-title":"BayesX: analyzing Bayesian structured additive regression models","volume":"14","author":"Brezger","year":"2005","journal-title":"J Stat Softw"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v092.i09","article-title":"spBayesSurv: fitting Bayesian spatial survival models using R","volume":"92","author":"Zhou","year":"2020","journal-title":"J Stat Softw"},{"key":"B12","doi-asserted-by":"publisher","first-page":"3975","DOI":"10.1002\/sim.10160","article-title":"Bayesian survival analysis with INLA","volume":"43","author":"Alvares","year":"2024","journal-title":"Stat Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"40","DOI":"10.4103\/bjhs.bjhs_54_19","article-title":"Piecewise hazard model for under-five child mortality","volume":"5","author":"Saroj","year":"2020","journal-title":"BLDE Univ J Health Sci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"89","DOI":"10.2307\/2529620","article-title":"Covariance analysis of censored survival data","volume":"30","author":"Breslow","year":"1974","journal-title":"Biometrics"},{"key":"B15","doi-asserted-by":"publisher","first-page":"13497","DOI":"10.1038\/s41598-021-92606-0","article-title":"Approximation of the Cox survival regression model by MCMC Bayesian Hierarchical Poisson modelling of factors associated with childhood mortality in Nigeria","volume":"11","author":"Fagbamigbe","year":"2021","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1177\/1536867X0900900206","article-title":"Further development of flexible parametric models for survival analysis","volume":"9","author":"Lambert","year":"","journal-title":"Stata J"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BF00116466","article-title":"Bayesian image restoration, with two applications in spatial statistics","volume":"43","author":"Besag","year":"1991","journal-title":"Ann Inst Stat Math"},{"key":"B18","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1214\/ss\/1038425655","article-title":"Flexible smoothing with B-splines and penalties","volume":"11","author":"Eilers","year":"1996","journal-title":"Stat Sci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2555","DOI":"10.1002\/1097-0258","article-title":"Bayesian modelling of inseparable space-time variation in disease risk","volume":"19","author":"Knorr-Held","year":"2000","journal-title":"Stat Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s10182-012-0196-3","article-title":"Spatio-temporal modeling of particulate matter concentration through the SPDE approach","volume":"97","author":"Cameletti","year":"2013","journal-title":"AStA Adv Stat Anal"},{"key":"B21","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1214\/06-BA117A","article-title":"Prior distributions for variance parameters in hierarchical models","volume":"1","author":"Gelman","year":"2006","journal-title":"Bayesian Anal"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1002\/sim.4780131007","article-title":"Assessing time-by-covariate interactions in proportional hazards regression models using cubic spline functions","volume":"13","author":"Hess","year":"1994","journal-title":"Stat Med"},{"key":"B23","doi-asserted-by":"publisher","first-page":"299","DOI":"10.2307\/2529982","article-title":"The analysis of rates and of survivorship using log-linear models","volume":"36","author":"Holford","year":"1980","journal-title":"Biometrics"},{"key":"B24","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1214\/11-AOAS498","article-title":"Estimation and extrapolation of time trends in registry data\u2014Borrowing strength from related populations","volume":"6","author":"Riebler","year":"2012","journal-title":"Ann Appl Stat"},{"key":"B25","doi-asserted-by":"publisher","first-page":"247","DOI":"10.2174\/1874944501912010247","article-title":"A Bayesian hierarchical analysis of geographical patterns for child mortality in Nigeria","volume":"12","author":"Adeyemi","year":"2019","journal-title":"Open Public Health J"},{"key":"B26","doi-asserted-by":"publisher","first-page":"322","DOI":"10.4314\/tjs.v49i2.4","article-title":"Identifying factors contributing to under-five mortality in Nigeria","volume":"49","author":"Bamigbala","year":"2023","journal-title":"Tanzan J Sci"},{"key":"B27","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.ssmph.2018.09.004","article-title":"Spatio-temporal patterns of under 5 mortality in Nigeria","volume":"6","author":"Ayoade","year":"2018","journal-title":"SSM - Popul Health"}],"container-title":["Frontiers in Epidemiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fepid.2026.1826352\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:39:26Z","timestamp":1784180366000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fepid.2026.1826352\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":27,"alternative-id":["10.3389\/fepid.2026.1826352"],"URL":"https:\/\/doi.org\/10.3389\/fepid.2026.1826352","relation":{},"ISSN":["2674-1199"],"issn-type":[{"value":"2674-1199","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]},"article-number":"1826352"}}