Individuals treated for drug-resistant tuberculosis (DR-TB) with aminoglycosides (AGs) in resource-limited settings often experience permanent hearing loss, yet there is no practical method to identify those at higher risk. We sought to develop a clinical prediction model of AG-induced hearing loss among patients initiating DR-TB treatment in South Africa.Using nested, prospective data from a cohort of 379 South African adults being treated for confirmed DR-TB with AG-based regimens we developed the prediction model using multiple logistic regression. Predictors were collected from clinical, audiological, and laboratory evaluations conducted at the initiation of DR-TB treatment. The outcome of AG-induced hearing loss was identified from audiometric and clinical evaluation by a worsened hearing threshold compared to baseline during the 6-month intensive phase.63% of participants (n=238) developed any level of hearing loss. The model predicting hearing loss at frequencies from 250 to 8,000Hz included: weekly AG dose, HIV status with CD4 count, age, serum albumin, BMI, and pre-existing hearing loss. This model demonstrated reasonable discrimination (AUC=0.71) and calibration (χ2[8]=6.10, p=.636). Using a cutoff of 80% predicted probability of hearing loss, the positive predictive value of this model was 83% and negative predictive value was 40%. Model discrimination was similar for ultrahigh-frequency hearing loss (frequencies higher than 9,000Hz; AUC=0.81) but weaker for clinically determined hearing loss (AUC=0.60).This model may identify patients with DR-TB who are at the highest risk of developing AG-induced ototoxicity and may help prioritize patients for AG-sparing regimens in clinical settings where access is limited.