Ayudando a mitigar riesgos en herramientas de IA generativa para Sistemas de Decisión Clínica (CDS)

Insights on ClinicalKey AI implementation at Azienda Sanitaria Locale di Bari (ASL Bari), Italy

Healthcare systems worldwide are navigating an era of unprecedented complexity. Rising patient volumes, increasingly challenging clinical scenarios and persistent workforce shortages have placed immense pressure on clinicians and institutions.1 These challenges are compounded by clinician burnout, that has the potential to impact both the quality of care and the sustainability of healthcare delivery.2 Moreover, clinicians must contend with an overwhelming and rapidly expanding body of clinical evidence, making it difficult to stay current and reach timely decisions. In order to address these challenges, there is an urgent need for solutions that help clinicians stay current with the latest scientific advancements, while strengthening confidence, streamlining workflows and enhancing patient care. These concerns were especially evident by one of Italy’s largest and most complex healthcare organizations, Azienda Sanitaria Locale di Bari (ASL Bari). To help address these concerns, ASL Bari partnered with Elsevier to implement ClinicalKey AI, an AI-powered clinical decision support tool designed to deliver evidence-based insights at the point of care.3 Clinicians’ ability to access timely, evidence-based information is now more important than ever. By enabling rapid access to evidence-based clinical knowledge, AI has the potential to enhance clinical decision-making, streamline workflows and reduce the cognitive burden on healthcare professionals, ultimately helping clinicians to improve patient outcomes.4 However, the promise of AI must be balanced with responsibility. Unvetted AI tools not suitable for healthcare use may introduce new inefficiencies, erode trust and compromise patient safety. For AI to succeed in healthcare, it must be transparent, ethical and verified. This white paper explores the implementation of Elsevier’s ClinicalKey AI at ASL Bari. It examines why and how ClinicalKey AI was introduced to address local challenges, evaluates its impact on clinical confidence, workflow efficiency and patient care delivery and provides actionable insights for healthcare leaders seeking to adopt responsible AI.

References 1. Kumar, P., Holt, T., Wong, Y., & Kimeu, M. (2025, May 14). Heartbeat of health: Reimagining the healthcare workforce of the future. McKinsey & Company. https://www.mckinsey.com/mhi/our-insights/heartbeat-of-health-reimagining-the-healthcare-workforce-of-the-future 2. Shanafelt, T. D., West, C. P., Dyrbye, L. N., Trockel, M., Tutty, M., Wang, H., ... & Sinsky, C. (2022, December). Changes in burnout and satisfaction with work-life integration in physicians during the first 2 years of the COVID-19 pandemic. In Mayo Clinic Proceedings (Vol. 97, No. 12, pp. 2248-2258). Elsevier. 3. Defilippis, V. (2025, November 10). Enhancing medical decision making with responsible AI: a case study from Italy [Conference presentation]. AI and Medicine The Challenge of Human Dignity International Congress, Rome, Italy. https://www.aimedicine.va/content/dam/aimedicine/documenti/PROGRAM.pdf 4. Khosravi, M., Zare, Z., Mojtabaeian, S. M., & Izadi, R. (2024). Artificial Intelligence and Decision-Making in Healthcare: A Thematic Analysis of a Systematic Review of Reviews. Health services research and managerial epidemiology, 11, 23333928241234863. https://doi.org/10.1177/23333928241234863