Published in PLOS One on 2025-10-16, this study is presented as an attributed evidence briefing. The excerpts below are the original researchers’ words, reproduced under their Creative Commons Attribution licence. HealthSignal has selected the abstract and, where needed, opening background paragraphs; the complete methods, results, limitations and references remain in the linked paper.
Original authors: Jibril Abdikadir Ali, Mukhtaar Axmed Cumar, Mustafe Khadar Abdi, Abdisalam Hassan Muse, Hodo Abdikarim
Source: PLOS One • DOI 10.1371/journal.pone.0326958
Read the complete primary study ↗ · Creative Commons Attribution licence
From the researchers
Abstract
In fragile states like Somalia, the link between poor health and educational exclusion is critical yet poorly understood. This study uses a novel machine learning approach to identify and rank the most significant barriers to school attendance. We analyzed nationally representative data from 10,511 children aged 6–18 in the 2022 Somalia Integrated Household Budget Survey (SIHBS). Ten supervised machine learning models were employed to predict school attendance, with the Random Forest model emerging as the top performer (AUC = 0.86). Contrary to conventional wisdom, our findings reveal a clear hierarchy of barriers where structural and demographic factors are the most powerful predictors. A child’s age (non-attendance rises from 6% in 6–10 year-olds to 25% in 15–18 year-olds), geographic region (non-attendance reaches 30.5% in Middle Shabelle), and residence type (nomadic children face triple the non-attendance risk of their peers) were the dominant determinants. These factors significantly outweighed the direct predictive power of individual health status or household poverty. The results indicate that while health is important, educational exclusion in Somalia is more fundamentally driven by where a child lives, how old they are, and their family’s mode of life. Policy interventions must therefore shift from broad, single-sector approaches to geographically-targeted, age-specific strategies. To effectively address the root causes of educational inequality, efforts should prioritize service delivery in marginalized regions and provide tailored support for nomadic and adolescent populations.
Introduction
Health and education constitute the foundational pillars of human capital, engaging in a cycle of mutual reinforcement that shapes both individual prosperity and national development. Globally, higher educational attainment is correlated with improved health outcomes, while poor health can significantly impede a child’s ability to learn and achieve academic success [1,2]. This synergy is particularly critical, yet fragile, in low- and middle-income countries (LMICs), where systemic stressors frequently undermine progress in both sectors. [3] contend that understanding these systems is essential for effective intervention. In many developing regions, the connection between health systems and educational stability is severely tested by disease outbreaks, climate shocks, and conflict [4,5]. These crises expose and exacerbate existing inequalities. For instance, gender-related barriers, including early marriage and the burden of domestic labor, consistently hinder girls from completing their education across Sub-Saharan Africa [6,7]. Furthermore, the rise of the digital divide introduces an additional layer of exclusion, as a lack of access to technology further marginalizes the most vulnerable students [8]. These challenges are magnified in conflict-affected nations. In contexts such as Nigeria, socio-economic precarity and regional insecurity are primary drivers of educational exclusion [9].
Similarly, the weaponization of public services in Syria has devastated health professional education, disrupting human capital development for an entire generation [10,11]. Such systemic fragility creates a persistent gap between policy aspirations and the lived realities of households, where interconnected factors related to health, economics, and security combine to keep children out of school. This reality is starkly evident in Somalia, a nation grappling with the legacy of a three-decade-long conflict. The country’s health system is one of the most fragmented globally, with less than 30% of the population having access to basic care [12]. This systemic collapse has precipitated a severe mental health crisis, widespread psychosocial trauma, and one of the highest rates of mental illness worldwide [13,14]. The humanitarian health and nutrition response is hampered by chronic shortages of resources, poor infrastructure, and pervasive insecurity, making it difficult to reach vulnerable populations [15,16]. For the millions of internally displaced persons (IDPs) in Somalia, these barriers are even more acute. Displaced women and children face formidable challenges in accessing maternal and child health services due to security risks, prohibitive costs, and traditional beliefs [17–19]. This environment of systemic collapse raises a critical question: what are the primary drivers of educational exclusion in Somalia? While the nexus between health and education is globally acknowledged, its mechanisms in a context of such profound and overlapping crises remain poorly quantified [7,20].
Reading this evidence
Use the full paper to check the study design, participant selection, comparator and outcome definitions before drawing a practical conclusion. An association does not by itself show cause and effect. A reported performance measure needs its denominator and uncertainty. A finding from a particular facility, sample or time period should retain that scope when it is discussed elsewhere.
This briefing makes the source accessible within the wider technology & industry desk. It does not assess an individual patient or certify a product. When considering relevance to another health system, examine the original authors’ account of context and limitations, then seek local implementation evidence. The related reporting below provides other studies to read alongside this one; it is a topic connection, rather than a claim that their results are directly comparable.
© 2025 Jibril Abdikadir Ali, Mukhtaar Axmed Cumar, Mustafe Khadar Abdi, Abdisalam Hassan Muse, Hodo Abdikarim. Excerpts reproduced under CC BY. Selection, formatting and contextual notes by HealthSignal. The researchers are the authors of the source study, not members of HealthSignal’s staff.
Explore connected evidence
- Evidence brief: Coverage and determinants of deworming uptake among under-five children in Somalia: A multilevel analysis of the 2020 SDHS data
- Evidence brief: Predicting severe stunting and its determinants among under-five in Eastern African Countries: A machine learning algorithms
- Evidence brief: Geospatial variation and machine learning approaches to predict open defecation practice in Zambia


