Sub-epidermal moisture is an established biophysical marker of pressure ulcer formation based on biocapacitance changes in affected soft tissues, which has been shown to facilitate early detection of these injuries. Artificial intelligence shows great promise in wound prevention and care, including in automated analyses of quantitative measures of tissue health such as sub-epidermal moisture readings acquired over time for effective, patient-specific, and anatomical-site-specific pressure ulcer prophylaxis. Here, we developed a novel machine learning algorithm for early detection of heel deep tissue injuries, which was trained using a database comprising six consecutive daily sub-epidermal moisture measurements recorded from 173 patients in acute and post-acute care settings. This algorithm was able to achieve strong predictive power in forecasting heel deep tissue injury events the next day, with sensitivity and specificity of 77% and 80%, respectively, revealing the clinical potential of artificial intelligence-powered technology for hospital-acquired pressure ulcer prevention. The current work forms the scientific basis for clinical implementation of machine learning algorithms that provide effective, early, and anatomy-specific preventive interventions to minimise the occurrence of hospital-acquired pressure ulcers based on routine tissue health status measurements.