Abstract:
Diabetes ICU patients have a higher risk of complications and in-hospital death. Due to many factors, estimating death risk is difficult and time-consuming. Healthcare providers want to identify high-risk ICU patients to reduce risk factors. Severity scoring methods are based on a patient’s health during the ICU stay, not their medical history. This paper proposes incorporating diabetes patients’ medical histories into severity scoring methods using process mining/deep learning. First, hospital records are converted to event logs for process mining. Event logs are used to create a process model of patients’ hospital visits. An adaptation of Decay Replay Mining is proposed to predict diabetes ICU patient in-hospital mortality using medical and demographic data and severity scores. The Medical Information Mart for Intensive Care III dataset shows significant performance improvements over risk severity scoring and machine learning methods.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
