نيلوفر ثمري

This research addresses the critical need to identify influential factors in the survival status of patients in the intensive care unit using associative rules. With the highest mortality rates in hospitals, the aim of this study is to uncover significant relationships and patterns in the intensive care dataset. The objectives include analyzing these rules, creating insights for informed decision-making, and eva‎luating the performance of associative rule algorithms. This research highlights the importance of real-world data in this field and the potential for reducing hospital costs in the intensive care unit. Advancements in medical equipment and healthcare services have generated a substantial volume of valuable medical information and data. Collecting and analyzing this data to extract vital insights that potentially save lives is of paramount importance. Currently, predicting the survival status of patients in intensive care units and identifying patterns and correlations between patient characteristics and mortality is highly significant. In this research, the a priori algorithm of associative rules was employed to identify the antecedents leading to patient mortality. Factors such as patient age, high levels of creatinine in the blood, and the use of ventilators were found to be antecedents that can lead to patient death in the intensive care unit. Additionally, a high level of consciousness is considered an influential factor in patient survival in this unit.

داده كاوي , قوانين انجمني , بخش مراقبت‌هاي ويژه , الگوريتم اپريوري

data mining , Association Rules Mining , intensive care unit , Apriori algorithm

Niloofar Samari

Dr. Mohammad reza Mohammad Aliha