Abstract
Hospital length of stay (HLOS) is a critical healthcare metric influencing patient outcomes, resource utilization, and healthcare costs. While reducing HLOS can improve hospital efficiency and patient throughput, it also poses risks such as premature discharge, increased readmission rates, and potential compromise of patient safety. This literature review synthesizes current evidence on the determinants of HLOS, including patient-specific factors such as demographics, comorbidities, and socioeconomic status, as well as hospital-related factors like admission route, resource allocation, and institutional policies. We also examine the relationship between HLOS and key clinical outcomes, including mortality, readmission rates, and healthcare-associated infections. Additionally, we evaluate predictive modeling approaches, including artificial intelligence and machine learning, for forecasting HLOS and guiding early intervention strategies. While interventions such as enhanced recovery after surgery (ERAS) protocols, multidisciplinary care teams, and structured discharge planning have demonstrated efficacy in reducing HLOS, their success varies based on healthcare setting, patient complexity, and resource availability. Predictive analytics, incorporating clinical and non-clinical variables, offer promising avenues for improving hospital efficiency, yet may carry risks related to data quality and model bias. Given the impact of HLOS on clinical and economic outcomes, targeted interventions and predictive models should be applied cautiously, with future research focusing on refining personalized discharge strategies and addressing disparities across diverse patient populations.