Enhanced Detection of Dementia in the Emergency Department Through Advanced Machine Learning Techniques
Poster Number: P56
Presentation Time: 05:00 PM - 06:30 PM
Abstract Keywords: Machine Learning, Chronic Care Management, Clinical Decision Support, Bioinformatics, Healthcare Quality
Primary Track: Applications
Programmatic Theme: Clinical Informatics
We apply three machine learning methods (traditional, positive unlabeled learning, and active learning) using three types of models (Random Forest, XGBoost, and LASSO) to predict dementia among patients 65+ in the emergency department (ED). Our findings indicate that while traditional models show robust performance, incorporating novel learning strategies hold potential for improved identification of dementia cases in the ED, which is crucial for timely intervention.
Speaker(s):
Inessa Cohen, MPH
Yale University
Poster Number: P56
Presentation Time: 05:00 PM - 06:30 PM
Abstract Keywords: Machine Learning, Chronic Care Management, Clinical Decision Support, Bioinformatics, Healthcare Quality
Primary Track: Applications
Programmatic Theme: Clinical Informatics
We apply three machine learning methods (traditional, positive unlabeled learning, and active learning) using three types of models (Random Forest, XGBoost, and LASSO) to predict dementia among patients 65+ in the emergency department (ED). Our findings indicate that while traditional models show robust performance, incorporating novel learning strategies hold potential for improved identification of dementia cases in the ED, which is crucial for timely intervention.
Speaker(s):
Inessa Cohen, MPH
Yale University
Enhanced Detection of Dementia in the Emergency Department Through Advanced Machine Learning Techniques
Category
Poster - Student
Description
Date: Tuesday (11/12)
Time: 05:00 PM to 06:30 PM
Room: Grand Ballroom (Posters)
Time: 05:00 PM to 06:30 PM
Room: Grand Ballroom (Posters)