Background and aims Chronic pain after traumatic injury and surgery is highly prevalent, and associated with substantial psychosocial co-morbidities and prolonged opioid use. It is currently unclear whether predicting chronic post-injury pain is possible. If so, it is unclear if predicting chronic post-injury pain requires a comprehensive set of variables or can be achieved only with data available from the electronic medical records. In this prospective study, we examined models to predict pain at the site of injury 3-6 months after hospital discharge among adult patients after major traumatic injury requiring surgery. Two models were developed: one with a comprehensive set of predictors and one based only on variables available in the electronic medical records. Methods We examined pre-injury and post-injury clinical variables, and clinical management of pain. Patients were interviewed to assess chronic pain, defined as the presence of pain at the site of injury. Prediction models were developed using forward stepwise regression, using follow-up surveys at 3-6 months. Potential predictors identified a priori were: age; sex; presence of pre-existing chronic pain; intensity of post-operative pain at 6 h; in-hospital opioid consumption; injury severity score (ISS); location of trauma, defined as body region; use of regional analgesia intra- and/or post-operatively; pre-trauma PROMIS Depression, Physical Function, and Anxiety scores; in-hospital Widespread Pain Index and Symptom Severity Score; and number of post-operative non-opioid medications. After the final model was developed, a reduced model, based only on variables available in the electronic medical record was run to understand the "value add" of variables taken from study-specific instruments. Results Of 173 patients who completed the baseline interview, 112 completed the follow-up within 3-6 months. The prevalence of chronic pain was 66%. Opioid use increased from 16% pre-injury to 28% at 3-6 months. The final model included six variables, from an initial set of 24 potential predictors. The apparent area under the ROC curve (AUROC) of 0.78 for predicting pain 3-6 months was optimism-corrected to 0.73. The reduced final model, using only data available from the electronic health records, included post-surgical pain score at 6 h, presence of a head injury, use of regional analgesia, and the number of post-operative non-opioid medications used for pain relief. This reduced model had an apparent AUROC of 0.76, optimism-corrected to 0.72. Conclusions Pain 3-6 months after trauma and surgery is highly prevalent and associated with an increase in opioid use. Chronic pain at the site of injury at 3-6 months after trauma and surgery may be predicted during hospitalization by using routinely collected clinical data. Implications If our model is validated in other populations, it would provide a tool that can be easily implemented by any provider with access to medical records. Patients at risk of developing chronic pain could be selected for studies on preventive strategies, thereby concentrating the interventions to patients who are most likely to transition to chronic pain.