Scholarlink

Given their delicacy and complexity, the clinical activities carried out in the nephrology department are closely related to the variation of the length of stay (LOS) parameter. The LOS in a nephrology department can be influenced by several factors, including the severity of the kidney disease, the response to treatment, the presence of complications, and other individual factors. LOS is an important measure for evaluating the effectiveness of clinical management, the department efficiency, and the economic impact on the healthcare system. The purpose of this work is to carry out a study on the LOS within the nephrology department of about 3000 patients who had access in the last 3 years within the University Hospital of Study of Naples “Federico II”. To carry out the processing, both machine learning methodologies were used using KNIME sw and linear regression methods were applied. The results showed how LOS is influenced by the previously named variables.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Regression Model and Machine Learning Algorithm to Predict LOS in a Nephrology Department of University Hospital of Study of Naples “Federico II”

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Marta Rosaria Marino,
  • Giuseppe Longo,
  • Maria Triassi,
  • Giovanni Improta

摘要

Given their delicacy and complexity, the clinical activities carried out in the nephrology department are closely related to the variation of the length of stay (LOS) parameter. The LOS in a nephrology department can be influenced by several factors, including the severity of the kidney disease, the response to treatment, the presence of complications, and other individual factors. LOS is an important measure for evaluating the effectiveness of clinical management, the department efficiency, and the economic impact on the healthcare system. The purpose of this work is to carry out a study on the LOS within the nephrology department of about 3000 patients who had access in the last 3 years within the University Hospital of Study of Naples “Federico II”. To carry out the processing, both machine learning methodologies were used using KNIME sw and linear regression methods were applied. The results showed how LOS is influenced by the previously named variables.