The effective management of human resources in nursing is fundamental to ensuring high-quality care. The necessary staffing levels can be derived from the nursing-related health status. Our approach is based on the use of artificial intelligence (AI) and machine learning (ML) to recognize key workload-driving predictors from routine data in the first step and derive recommendations for staffing levels in the second step. The precedent analysis was a multi-center study with data provided by three hospitals. The SPI (Self Care Index = sum score of 10 functional/cognitive items of the epaAC (epaAC = nursing assessment tool for AcuteCare (abbreviated from the German-language effiziente Pflege-Analyse AcuteCare))) was identified as a strong predictor of nursing workload. The SPI alone explains the variance in minutes with an adjusted R² of 40% to 66%. With the addition of further predictors such as “fatigue” or “pain intensity”, the adjusted R² can be increased by up to 17%. The resulting model can be used as a foundation for data-based personnel controlling using AI-based prediction models.