Development Of A Stunting Risk Prediction Model Using Binary Logistic Regression In The Working Area Of Public Health Center Marawola, Sigi Biromaru Regency

Abstract

Stunting remains a major health problem in Indonesia, with a national prevalence of 19.8% (SSGI, 2024) and Central Sulawesi Province reaching 26.1%. Sigi Regency has the second-highest prevalence of stunting, reaching 33.0% (SSGI, 2024). This condition affects long-term child growth and development. To identify risk factors, an appropriate prediction model is needed, one of which is binary logistic regression, which is able to map the relationship between various determinants and the incidence of stunting. This study aimed to predict early risk factors for stunting using binary logistic regression in the working area of Public Health Center Marawola, Sigi Biromaru Regency. The method used was a quantitative study with a cross-sectional design. The sample consisted of 40 mothers with toddlers. Data analysis was performed using the Binary Logistic Regression Test. The results of the study showed that the determinants proven to be significant and could be used as early prediction indicators for stunting risk were cigarette smoke exposure (smoking behavior of the toddler’s parents) (p = 0.010; Exp(B) = 24.8) and family income (p = 0.012; Exp(B) = 0.024). Meanwhile, maternal height was not a risk factor for stunting (p = 0.329; Exp(B) = 1.9). Thus, stunting prevention efforts should focus on controlling exposure to cigarette smoke in the household environment and improving household economic welfare through community empowerment programs.