Downloads: 1 | Views: 54 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1
Research Paper | Information Technology | United States of America | Volume 13 Issue 7, July 2024 | Rating: 5.2 / 10
Enhancing Healthcare Operations with Predictive Length of Stay Models
Umamaheswara Reddy Kudumula [7]
Abstract: Healthcare costs are a significant concern in the United States, posing a substantial burden on American families and leading many to bankruptcy. Hospitalization stands out as a major contributor to these costs. According to the American Hospital Association, there were over 36 million hospital admissions in 2018, with an average length of stay (LOS) of approximately 5.5 days-an increase of over 19% from previous years. The average daily hospitalization cost is estimated at $2,883, resulting in nearly $13,000 per stay. If hospitalization involves surgery, costs can range from $5,000 to $150,000, with potential for exceedingly high out-of-pocket expenses. Consequently, healthcare costs are a primary reason for bankruptcy filings. The correlation between healthcare costs and the length of hospital stays is clear: longer stays result in higher costs. Excessive hospital days contribute to operational inefficiencies and negatively impact patient outcomes. Therefore, reducing LOS is crucial for benefiting both patients and healthcare providers. This white paper examines the use of predictive data analytics to forecast average length of stay (ALOS). By leveraging these predictions, healthcare systems can develop strategies to enhance management efficiency, optimizing the use of healthcare workers and resources like beds. Ultimately, this approach aims to improve the quality of care, reduce LOS, and lower associated healthcare costs.
Keywords: Healthcare, Length of Stay, American Hospital Association (AHA), Data Analytics, Average Length of stay (ALOS), Patient Care, Bankruptcy, Hospitalization, Providers, Medicare Severity Diagnosis-Related Group (MS DRG)
Edition: Volume 13 Issue 7, July 2024,
Pages: 792 - 796