| NSF Org: |
TI Translational Impacts |
| Recipient: |
|
| Initial Amendment Date: | February 24, 2021 |
| Latest Amendment Date: | May 21, 2021 |
| Award Number: | 2120858 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Ruth Shuman
rshuman@nsf.gov (703)292-2160 TI Translational Impacts TIP Directorate for Technology, Innovation, and Partnerships |
| Start Date: | February 15, 2021 |
| End Date: | July 31, 2022 (Estimated) |
| Total Intended Award Amount: | $50,000.00 |
| Total Awarded Amount to Date: | $50,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1850 RESEARCH PARK DR STE 300 DAVIS CA US 95618-6153 (530)754-7700 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
OR/Sponsored Programs Davis CA US 95618-6134 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | I-Corps |
| 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
The broader impact/commercial potential of this I-Corps project is the development of digital interventions to detect and deliver early treatment recommendations for advanced cardiac disease. Through the use of artificial intelligence, it is possible address one of the most pressing healthcare burdens in the United States by detecting trajectories of chronic heart disease early. As a result, this technology would enable multiple applications including, but not limited to, reductions in healthcare-related costs, chronic disease burden, specialist care gaps, and time to treatment. This proposed technology may deliver a new era of software as a digital therapeutic, an area traditionally reserved for non-chronic conditions.
This I-Corps project is based on the development of a software platform using neural network models that leverage the use of biomarkers coupled with clinical vitals. Combining molecular and clinical data applied through natural experimentation, has made it is possible to understand the state changes of heart disease. Through the use of deep neural network learning, the proposed project goal is to make algorithms think and understand as humans by replicating the human brain connection and focusing on learning state changes rather than task-specific algorithms. Previous work on molecular profiling paired with clinical data within the realm of heart transplantation has yielded promising results in creating new sub-diagnosis as well as new artificial intelligence-guided therapy optimization protocols.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
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.
This award was used to complete discovery interviews with various healthcare stakeholders across the country (hospitals, providers, insurance groups, and patients) to identify the need for our product.
There was significant interest from provider and payor groups in our discovery that a need for more streamlined methods to detect heart disease and create treatment plans for it. The use of AI to predict the severity level of a inidividuals heart disease is very complex from our interviews. Predicting risk and medication tolerance are some of the biggest takeaways from our conversations with providers and hospitals. Payors continue to look at hospital readmissions as a source to reduce and finding ways to use AI to improve care management pathways.
We learned that this product would sqaurely sit at the providers office as well as in pharmacy centers/care management groups. Our previous hypothesis that a patient would be our end user was false but instead we learned our end user is any provider doing upstream engagement with the patient around disease and medication management.
Medication management is a big part of disease management; as such there is significant interest from pharma companies to find ways to develop better drugs for patients with advanced heart disease. There were findings around using AI to develop contra-indications with other drugs and predict outcomes.
Last Modified: 09/27/2022
Modified by: Martin Cadeiras
Please report errors in award information by writing to: awardsearch@nsf.gov.
