Improving predictions for severe health conditions using electronic health records
Enhanced Metadata Design, Architecture, and Learning (MeDAL) for Development of Generalizable Deep Learning-based Predictive Analytics from Electronic Health Records
This study is working on new technology that helps doctors predict serious health issues like sepsis and kidney problems before they happen, using data from hospital records, so they can take action sooner and improve patient care.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California, San Diego NIH-funded |
| Lab location | 1 site (La Jolla, United States) |
| Project ID | NIH-11019703 on NIH RePORTER |
What this research studies
This research focuses on developing advanced predictive analytics using deep learning techniques applied to electronic health records. By analyzing vast amounts of data from acute care settings, particularly intensive care units, the project aims to enhance the ability of clinicians to anticipate and prevent critical conditions such as sepsis and acute kidney injury. The methodology involves creating algorithms that can predict these events several hours in advance, potentially improving patient outcomes significantly. The research also seeks to address the limitations of current predictive models, making them more generalizable across different healthcare institutions.
Who could benefit from this research
Good fit: Ideal candidates for this research include adults over 21 years old who are admitted to emergency departments or intensive care units with conditions like sepsis or acute kidney injury.
Not a fit: Patients with chronic conditions that do not require acute care or those who are not admitted to emergency settings may not benefit from this research.
Why it matters
Potential benefit: If successful, this research could lead to earlier interventions for patients at risk of severe health complications, ultimately reducing mortality and improving recovery rates.
How similar studies have performed: Previous research has shown promising results with similar deep learning approaches in predicting acute health events, indicating a strong potential for success in this project.
Where this research is happening
La Jolla, United States
- University of California, San Diego — La Jolla, United States (Active)
Researchers
- Principal investigator: Nemati, Shamim — University of California, San Diego
- Study coordinator: Nemati, Shamim
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.