Conference proceeding
Visualizing Model Behaviors for Clinic Users: Explaining A Clinical Prediction Model for 30-day Readmission after Inpatient Alcohol Dependence Treatment
2024 IEEE 12th International Conference on Healthcare Informatics (ICHI), pp 718-724
03 Jun 2024
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Machine learning models for predicting alcohol use relapse lack adequate explanations. This study aims to utilize visualization techniques to (1) highlight a machine learning model's predictive reasoning and biases; and (2) to identify the risk factors associated with readmission following inpatient treatment for alcohol use disorder. Our visualizations show that first, the model was reliable in its negative predictions but had difficulty in correctly identifying positive instances with missing variable values; second, a history of multiple treatments may distinguish otherwise similar instances; and third, highly impactful risk factors for 30-day readmission included a history of multiple treatments and lower participation in treatment. The visualizations when considered together could help clinical users understand model biases.
Metrics
11 Record Views
Details
- Title
- Visualizing Model Behaviors for Clinic Users: Explaining A Clinical Prediction Model for 30-day Readmission after Inpatient Alcohol Dependence Treatment
- Creators
- Ou Stella Liang - Drexel UniversityChristopher C. Yang - Drexel UniversityKate Gliske - Ford FoundationJacqueline Braughton - Hazelden Betty Ford Graduate School of Addiction StudiesQuyen Ngo - Hazelden Betty Ford Graduate School of Addiction Studies
- Publication Details
- 2024 IEEE 12th International Conference on Healthcare Informatics (ICHI), pp 718-724
- Publisher
- IEEE; LOS ALAMITOS
- Number of pages
- 7
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Information Science (Informatics)
- Web of Science ID
- WOS:001304501700107
- Scopus ID
- 2-s2.0-85203717206
- Other Identifier
- 991021901302704721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Information Systems
- Medical Informatics