A model to predict respiratory failure in COVID-19 patients
Official title: VentNet: A Real-Time Multimodal Data Integration Model for Prediction of Respiratory Failure in Patients with COVID-19
Funded at University of California, San Diego · NIH-11046630 · Data updated 2026-11-12
This study is creating a smart tool that uses health data to help doctors predict if COVID-19 patients might need breathing support within the next day, so they can act quickly and improve 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 start | February 15, 2022 |
| Project end | January 31, 2026 |
| Funding year | 2025 |
| Award (this year) | $651,706 |
| NIH project number | 5R01HL157985-04 |
| Project ID | NIH-11046630 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are COVID-19 patients at risk of developing acute hypoxemic respiratory failure.
✕Less likely to help
Patients who are not infected with COVID-19 or those who do not exhibit risk factors for respiratory failure may not benefit from this research.
What this research studies
This research develops a predictive model using machine learning algorithms to analyze data from electronic health records (EHR) to forecast respiratory failure in COVID-19 patients 24 hours in advance. By integrating various clinical parameters, the model aims to improve decision-making for healthcare providers, helping them identify patients who may require mechanical ventilation sooner. This approach addresses the challenges faced during the pandemic, where timely intervention was critical for patient outcomes. The model has shown promising accuracy in preliminary tests, indicating its potential effectiveness in clinical settings.
Why it matters
Potential benefit: If successful, this research could significantly enhance the ability to predict respiratory failure, leading to timely interventions and improved patient outcomes.
How similar studies have gone: Other studies have successfully utilized machine learning for predictive modeling in healthcare, indicating a promising avenue for this approach.
Where this research is happening
-
University of California, San Diego
La Jolla, United States Active
Researchers
- Principal investigator: Nemati, Shamim — University of California, San Diego
- Study coordinator: Nemati, Shamim
Related research
Other NIH-funded projects on the same topics.
-
How alcohol misuse affects cognitive and respiratory health in COVID-19 patients
This study is looking at how drinking too much alcohol might affect people with severe COVID-19 breathing problems, especially those on breathing machines, to see if it makes their thinking and breathing worse, and to find ways to help them recover better.
-
Structural factors linking minimum wage, COVID-19, and community violence
A long-term study will explore whether higher minimum wages and pandemic-related economic factors are connected to changes in violence in US communities.
-
COVID-19 healthcare disruptions and heart health inequities in NYC adults with multiple conditions
This project looks at how COVID-19-related gaps in care affected heart health in adults with several chronic conditions in New York City.
-
Modifying body fat to aid COVID-19 recovery through behavioral strategies
A study in veterans explores whether changing weight through lifestyle habits can improve recovery after COVID-19–related health problems.
-
Post-COVID Neuro-Cognitive Changes in Older African Americans
A study explores how COVID-19 affects thinking, memory, and daily life in older African American adults and what might be driving these changes.
-
How COVID school closures affected kids with or at risk for developmental differences
This NIH grant follows children aged 4 to 15 and their families to see how pandemic school closures impacted emotional well-being and parenting over three years.
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.