Introduction <p>Neonatal jaundice affects up to 85% of live births and is largely preventable and treatable when identified and managed early. Delayed or inadequate treatment, however, may lead to irreversible complications and death. Despite the availability of effective interventions, treatment outcomes in many developing countries remain suboptimal. Moreover, evidence on treatment outcomes and their predictors among jaundiced neonates in the study area is limited. Therefore, this study aimed to determine the treatment outcomes of neonatal jaundice and identify associated predictors among neonates admitted to public hospitals in Bahir Dar City, Ethiopia, in 2024.</p> Method <p>A retrospective follow-up study was conducted among 420 jaundiced neonates admitted to public hospitals in Bahir Dar city from January 1, 2020, to December 30, 2023. Study participants were selected using a simple random sampling technique. Data were entered into Epi-Data 4.6 and analyzed using SPSS version 26. Both descriptive and inferential statistical analysis was performed. Binary logistic regression with 95% confidence interval (CI) was used to identify predictors of poor treatment outcomes. Variables with a p-value &lt; 0.20 in the bivariable analysis were included in the multivariable analysis, and statistical significance was declared at <i>p</i> &lt; 0.05. Model fitness was assessed using the Hosmer–Lemeshow goodness-of-fit test. Findings were presented using text, tables and figures.</p> Result <p>Out of 432 eligible neonatal records, 420 charts were reviewed, yielding a completeness rate of 97.2%. The proportion of poor treatment outcomes among jaundiced neonates was 11.7% (95% Confidence Interval: 8.7%, 14.8%). Significant predictors of poor treatment outcomes included origin of admission (Adjusted Odds Ratio = 2.57; 95% Confidence Interval: 1.06–6.22), rhesus incompatibility (Adjusted Odds Ratio = 2.64; 95% Confidence Interval: 1.05–6.67), neonatal sepsis (Adjusted Odds Ratio = 4.54; 95% Confidence Interval: 1.82–11.3), temperature instability (Adjusted Odds Ratio = 3.38; 95% Confidence Interval: 1.15–9.90) and use of intermittent phototherapy (Adjusted Odds Ratio = 2.90; 95% Confidence Interval : 1.22–6.89).</p> Conclusion and Recommendation <p>The study revealed that moderate proportion of neonates with jaundice experienced poor treatment outcomes in public hospitals of Bahir Dar City. Poor treatment outcomes were significantly associated with referral origin, rhesus incompatibility, neonatal sepsis, temperature instability, and the use of intermittent phototherapy. These findings emphasize the importance of early identification and timely management of high-risk neonates, strengthening referral systems, ensuring effective and continuous phototherapy, and improving the management of comorbid conditions to enhance treatment outcomes of neonatal jaundice.</p>