OBJECTIVES: Hospital-acquired pressure ulcers (HAPUs) have a mortality rate of 11.6%, are costly to treat and result in Medicare reimbursement penalties. Medicare flags HAPUs based on inclusion criteria of Agency for Healthcare Research and Quality (AHRQ) Patient-Safety Indicator 3 (PSI-03), but are sometimes inappropriately coded. To use electronic health records to predict pressure ulcers and to identify coding issues leading to penalties. METHODS: This study applied a multilevel logistic regression to a retrospective cohort of all hospitalized patient electronic medical records at an academic medical center between 2011-2014.  Data for this study contained patient-encounter level demographic variables, diagnoses, prescription drugs and provider orders. HAPUs were defined by PSI-03: stages III, IV or unstageable pressure ulcers not present-on-admission as a secondary diagnosis; excluding cases of paralysis. Random forests reduced data dimensionality. Multilevel logistic regression of patient-encounters evaluated associations between covariates and HAPU incidence. RESULTS: The approach produced a sample population of 21,153 patients with 1,549 PSI-03 cases. The greatest odds ratio (OR) of HAPU incidence was among patients diagnosed with spinal cord injury (ICD-9 907.2: OR=14.3; P<0.001), and 71% of spinal cord injuries were not properly coded for paralysis, leading to a PSI-03 flag. Other high ORs included bed confinement (ICD-9 V49.84: OR=3.1, P<0.001), and provider-ordered pre-albumin lab (OR=2.5, P<0.001). CONCLUSIONS: This analysis identifies spinal cord injuries high-risk for HAPUs and often inappropriately coded without paralysis leading to PSI-03 flags. Inappropriate coding of conditions leads to poor hospital performance measures and Medicare reimbursement penalties. AHRQ should exclude spinal cord injury from the PSI-03 flag,a nd CMS might consider making a payment exception for pressure ulcers concominant with spinal cord injury.  The resulting statistical model can be tested to predict HAPUs during hospitalization.