| NSF Org: |
TI Translational Impacts |
| Recipient: |
|
| Initial Amendment Date: | November 13, 2013 |
| Latest Amendment Date: | November 13, 2013 |
| Award Number: | 1345452 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Glenn H. Larsen
TI Translational Impacts TIP Directorate for Technology, Innovation, and Partnerships |
| Start Date: | January 1, 2014 |
| End Date: | June 30, 2014 (Estimated) |
| Total Intended Award Amount: | $149,974.00 |
| Total Awarded Amount to Date: | $149,974.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
901 WATERFALL WAY RICHARDSON TX US 75080-6700 (972)680-0800 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
TX US 75080-3597 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | SBIR Phase I |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.084 |
ABSTRACT
This SBIR Phase I project proposes to address the challenges medical professionals face since the signing of The Patient Protection and Affordable Care Act. Today's mental health therapist must prepare for an increased patient load as the pool of insured Americans grows, while simultaneously reducing the overall cost of healthcare. The healthcare delivery process must be streamlined by eliminating unnecessary tests, procedures, and repeat patient care. This project will provide therapists tools to: (1) speed up and improve patient diagnosis, (2) prepare a course of treatment that is likely to yield a fast and positive patient outcome, and (3) keep informed about scientific findings that directly impacting their daily work. Deep research issues need to be solved to parse the technical jargon of medical literature and reconcile that with the free form narrative typical in therapist session notes. The project will produce novel methods to transform patient records and medical resources like the Diagnostic and Statistical Manual of Mental Disorders (DSM) into a medically tuned semantic graph that is merged with a rich mental health ontology. Moreover, the project will research advanced text similarity algorithms to align patient data with DSM disorders, quality treatment plan options, and relevant research findings.
Broader Impacts/ Commercial Potential: The broader/commercial impact of this project is to deliver an automated medical assistant to mental health professionals that will give them time to focus on patient interactions and make healthcare more personal. Government agencies and insurance companies will benefit as increased efficiency and quality of care from therapists will lead to lower healthcare costs, especially because mental health disorders often manifest themselves as general medical conditions. The World Health Organization reports that mental disorders account for nearly 12% of the global burden of disease, and that by 2020 these disorders will account for nearly 15% of disability-adjusted life-years lost to illness. Further because the burden of mental disorders is maximal in young adults, the most productive section of the population, improvements to mental health diagnosis and treatment will significantly impact the American society as a whole. The patient population will also benefit from lowered personal costs as well as a lessened societal burden that comes with taking care of the mentally ill.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
The World Health Organization reports that mental disorders account for nearly 12% of the global burden of disease, and that by 2020 these disorders will account for nearly 15% of disability-adjusted life-years lost to illness. Further because the burden of mental disorders is maximal in young adults, the most productive section of the population, improvements to mental health diagnosis and treatment significantly impact American society as a whole. Lymba’s Automated Health Care Assistant for Mental Health (AHCA-MH) project is a revolutionary clinical decision support system that provides critical insights to mental health professionals directly at the point of care. With the passage of the Affordable Care Act, the modern mental health clinician must prepare for an increased patient load as the pool of insured Americans drastically increases, while simultaneously reducing the overall cost of healthcare. This requires streamlining the healthcare delivery process by eliminating unnecessary tests, procedures, and repeat patient care.
The outcome of the Phase 1 project is a clinical decision support system prototype to help therapists/clinicians: (1) speed up and improve patient diagnosis, (2) quickly prepare a course of treatment that is likely to yield a fast and positive patient outcome, and (3) keep informed about scientific findings that directly impact their daily work. Specifically Lymba’s AHCA-MH project researched and developed innovative tools and algorithms to:
- Semantically match patient records to a list of disorders from the Diagnostic and Statistical Manual of Mental Disorders
- Proactively retrieve research literature related to the therapist’s current patient case load
- Suggest treatment for a new patient by mining historic patient data for similar cases
Lymba’s research efforts for the 6-month performance period of the Phase I project resulted in algorithms for: a rich knowledge driven representation of patient information, clinical notes, and reference materials and innovative matching capabilities to align these resources to affect coordination of care in an electronic health record system. As a scientific impact, the AHCA-MH prototype demonstrates that fusion of patient information with research resources and diagnostic references is feasible, works well, and improves the quality of information available to doctors at the point of care. The broader societal impact of AHCA-MH is two-fold: (1) government agencies and insurance companies will benefit as increased efficiency and quality of care from therapists will lead to lower healthcare costs, especially because mental health disorders often manifest themselves as general medical conditions, and (2) the patient population as a whole will also benefit from lowered personal costs as well as a lessened societal burden that comes with taking care of the mentally ill.
This effort demonstrates the feasibility of automatic diagnostic and treatment assistance based on clinical notes and reports stored in an EHR. In Phase 2, the project will be extended to operate in a domestic commercial environment serving the medical EHR/EMR markets for mental health and other medical fields that rely on narrative notes/reports from clinicians.
Keywords: Semantic Technology, Text Understanding, Healthcare, Medical
Topic and subtopic: IC/IC1B
Last Modified: 09/10/2014
Modified by: Mithun Balakrishna
Please report errors in award information by writing to: awardsearch@nsf.gov.
