<p>Data set.</p>

The collected data were entered into Epi-Data version 4.7 and then exported to STATA version 14 for further statistical analysis. The Kaplan–Meier curve was used to estimate recovery time. Both bivariable and multivariable Cox regression models were applied to analyze the data.

Finally, the results were reported with 95% confidence intervals, and variables with a p-value < 0.05 were considered statistically significant.</p> <p>Result</p><p>The recovery rate among pediatric patients was 85.2%, with a median recovery time of 5 days. The overall incidence of recovery rate was 16.30 per 100 person days observation (95% CI: 14.43–18.40). Being rural residence (AHR = 0.69;95%CI (0.53–0.90), late presenter to seeking care (AHR = 0.56; 95% CI (0.35–0.88), absence of danger sign (AHR = 1.48; 95% CI: 1.07–2.05)), absence of comorbidity (AHR = 3.02; 95% CI: 2.15–4.22) and not receiving oxygen therapy (AHR = 1.71; 95% CI: 1.20–2.41), were significant predictors.</p> <p>Conclusions</p><p>The median recovery time of patients was considerably high.

Rural residence, late presentation for care, absence of danger signs, absence of comorbidity, and not receiving oxygen therapy were statistically significant predictors of recovery time.</p></div>