BackgroundEarly recovery is a performance indicator of quality care for children under five admitted due to severe acute malnutrition (SAM) at therapeutic feeding centers. Despite the available interventions to tackle such nutritional problems, there is limited information on the time to recovery and its predictors among children with severe acute malnutrition in Ethiopia, more particularly in the study setting.ObjectiveThe study aimed to assess the time to recovery from severe acute malnutrition and its predictors among children aged 6–59 months admitted to the therapeutic feeding center (TFC) of Hiwot Fana Comprehensive Specialized Hospital (HFCSH), eastern Ethiopia, from 1st September 2019 to 1st March 012024.MethodsA retrospective cohort study was conducted at the therapeutic feeding center of HFCSH among a randomly selected sample of 349 patients with severe acute malnutrition who were undergoing therapeutic feeding. Data were collected using a data abstraction tool and then stored in Epi-data version 4.6 and STATA version 17.0 statistical software. Descriptive statistics, Kaplan–Meier (KM) plots, median survival times, the log-rank test, and the Cox proportional hazards regression model were used to report the findings of this study. After performing the Cox proportional hazards regression, the model goodness of fit and assumptions were checked. Finally, the association between independent variables and the time to recovery in days was assessed using the multivariable Cox proportional hazards model, and the variables with a p-value <0.05 were considered statistically significant.ResultsThe median survival time to recovery among the patients with severe acute malnutrition was 17 days [95% confidence interval (CI): 16–18]. The incidence density recovery rate was 5.7 (95%CI, 4.9–6.6) per 100 person-days of observation. Factors that affected the time to recovery included residing in rural areas [adjusted hazard ratio (AHR) = 2.072; 95%CI = 1.336–3.215], being vaccinated according to age (AHR = 1.848; 95%CI = 1.162–2.939), and lack of analgesic administration (AHR = 0.685; 95%CI = 0.472–0.995).ConclusionThe median survival time to recovery in this study was found to be optimal. Residency, vaccination status of the child, and analgesic administration were the determinant factors. Paying attention to vaccination coverage, fever management, and pain management as part of the protocol helps reduce the length of hospital stay by facilitating recovery rates among severely malnourished children under five in Ethiopia.