Search

Healthcare quality improvement increasingly relies on routinely collected data to identify preventable harm, missed care opportunities, adverse outcomes, and variation in performance. Artificial intelligence predictive models may support earlier detection of quality risks and enable more proactive monitoring than retrospective audits alone. This systematic review examined artificial intelligence predictive models for healthcare quality improvement from 2017 to 2024. The review focused on patient safety events, care gaps, adverse clinical outcomes, and performance monitoring systems. A PRISMA 2020-compliant search was conducted across PubMed, Scopus, Web of Science, and IEEE Xplore for peer-reviewed English-language studies published from 2017 through 2024. Dual screening, structured data extraction, risk-of-bias assessment, and narrative synthesis were used. The evidence base showed growing use of machine learning for pressure injuries, sepsis, readmission, mortality, ICU transfer, and continuous monitoring. However, most studies remained retrospective model-development or validation studies, while fewer described deployment within formal quality improvement workflows. Technical progress in predictive modelling for quality improvement is substantial, but evidence of sustained improvement in care processes, safety outcomes, or organisational performance remains limited. Stronger prospective evaluation and clearer integration with improvement methods are needed.