A Decision Support System for Mental Healthcare Workers

Daniel Ojeda and Dr. Daehan Kwak School of Computer Science and Technology, Kean University, Union, NJ 07083

Mental health is vital at every stage of life, affects the way a person thinks, feels, and behaves. Furthermore, it helps determine how people relate to others, make decisions, and handle stress. In the United States, mental health remains a persistent problem. Indeed, at the time of the most recent national survey, approximately one in five U.S. adults live with a mental illness (46.6 million). Despite the support of community resources and care services, people with mental illness have a difficult time navigating through such resources and services. Furthermore, the general scarcity of care managers, experts who work to coordinate all of the physical and mental healthcare needs of a mentally ill patient, means that only 41% of those with any mental illness had received mental health services in the past year. On top of that, most care managers that deliver care management services are with minimal training and experience.
Thus, the goal of this research is to support the efficiency of care managers and provide solutions for easy access to community resources and services to individuals living with Severe Mental Illness and Substance Use Disorders. We address this issue by developing a system with decision trees options: in Transportation, Safety, Housing Instability, Food Insecurity, Employment, Financial, Social Isolation, and Supports, to help care managers to track the outcomes they go through with each patient, increase their capacity to create holistic views of patients, personalize treatments, and enhance health outcomes. A database is created where healthcare workers at CPC Behavioral Healthcare will utilize the system. Also, a representation of data via maps and graphs to make better decisions that are essential to fill the gap between the need and availability of mental health services is implemented.

Additional Abstract Information

Presenter: Daniel Ojeda

Institution: Kean University

Type: Poster

Subject: Computer Science

Status: Approved

Time and Location

Session: Poster 5
Date/Time: Tue 12:30pm-1:30pm
Session Number: 4026