Design
Research
Resources
Contact
This website is organized as follows. The side navigation serves a static menu to navigate across pages on this website. We provide you with a template of what we want to see from your project pages, the contents can be edited on a per project basis.
The Personalized Depression Treatment Ontology aims to enhance the personalization of treatment plans for individuals diagnosed with depression by integrating diverse data sources, including genetic profiles, demographic information, and clinical outcomes. This ontology serves as a decision-support tool for clinicians, enabling them to access patient-specific recommendations that improve the efficiency and effectiveness of mental health care. By mapping relationships between patient demographics, genetic markers, and therapeutic options, the ontology will hopefully reduce the traditional trial-and-error approach, providing evidence-based treatment paths that account for individual variability in treatment response. Key features include the integration of clinical trial data, genetic studies, and real-world patient-reported outcomes to continuously refine recommendations. This ontology addresses critical needs in the mental health field, providing stakeholders such as clinicians, researchers, and genetic counselors with a robust framework for delivering tailored treatment strategies that enhance patient outcomes and reduce treatment resistance.
List resources you think a reader would benefit from to use your project. We list some examples you could make available below.
| Resources | Links |
|---|---|
| 1. Ontology | (a) PDT Ontology |
| 2. Term List | (a) Mapped Vocabularies |
| 2. Competency Questions | (a) SPARQL Queries |
| 3. Presentations: | (a) Project presentations during class |
This work is undertaken as a part of the Health Empowerement by Analytics, Learning and Semantics (HEALS) project , and is partially supported by IBM Research AI through the AI Horizons Network. We thank our colleagues from IBM Research, Dan Gruen, Morgan Foreman and Ching-Hua Chen, and from RPI, John Erickson, Alexander New, Neha Keshan and Rebecca Cowan, who provided insight and expertise that greatly assisted the research.