Early prediction of lung scarring after COVID using explainable AI
Official title: Predicting Post-Covid Pulmonary Fibrosis with Explainable Deep Learning and Optimal Biomarker Discovery
Funded at Northwestern University · NIH-11178702 · Data updated 2026-11-12
This project uses explainable AI on CT scans and medical records to find people at risk of lung scarring after COVID-19.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Northwestern University NIH-funded |
| Lab location | 1 site (Chicago, United States) |
| Project start | September 1, 2024 |
| Project end | May 31, 2028 |
| Funding year | 2025 |
| Award (this year) | $617,578 |
| NIH project number | 5R01HL171376-02 |
| Project ID | NIH-11178702 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates are people who had COVID-19—especially those hospitalized or with persistent breathing problems—who have recent chest CT scans and accessible medical records.
✕Less likely to help
People without prior COVID-19, without chest imaging or medical records, or whose lung disease is from a different cause may not benefit from this project.
What this research studies
If I join, researchers will combine my chest CT images and electronic health-record data and apply explainable deep learning to spot early signs of post-COVID lung fibrosis. They will use patient data pooled from multiple hospitals, including Northwestern and Columbia, to train and validate the models. The team will search for imaging and clinical biomarkers and show which features the AI models rely on. The goal is a transparent tool that can identify at-risk patients earlier so doctors can consider timely treatments.
Why it matters
Potential benefit: If successful, this work could help doctors identify people at high risk for post-COVID lung fibrosis earlier so treatments might be started sooner to limit scarring.
How similar studies have gone: Previous studies have used machine learning to find fibrosis patterns on CT, but combining explainable deep learning with multimodal EHR across multiple centers is relatively new.
Where this research is happening
-
Northwestern University
Chicago, United States Active
Researchers
- Principal investigator: Bagci, Ulas — Northwestern University
- Study coordinator: Bagci, Ulas
Related research
Other NIH-funded projects on the same topics.
-
Predicting Post-Covid Lung Scarring with Easy-to-Understand Deep Learning and Key Biomarkers
Aims to use explainable artificial intelligence and biomarker data from multiple hospitals to predict which patients will develop long-term lung scarring after COVID-19.
-
Molecular clues to progressive lung scarring
Researchers are studying how lung tissue becomes progressively scarred, focusing on cell signals and receptors that may drive fibrosis in people with lung disease.
-
Alveolar Cell Dysfunction in Pulmonary Fibrosis: Using SFTPC Mutations to Find New Targets
This grant explores how rare SFTPC mutations in alveolar cells may drive IPF and seeks new molecular targets to improve treatment.
-
Iron and scar-forming cells in the lungs (IPF)
Researchers are exploring how iron in the lungs may drive the scarring seen in idiopathic pulmonary fibrosis and whether this could lead to new therapies.
-
Repurposing Pyrvinium as an Inhaled Therapy for Idiopathic Pulmonary Fibrosis
A patient-friendly look at a project trying to use an existing drug, pyrvinium, as an inhaled treatment option for idiopathic pulmonary fibrosis (IPF).
-
Screening new compounds to reverse gene signatures in IPF lungs
A researcher hopes to find compounds that reverse harmful gene changes in the lungs of people with idiopathic pulmonary fibrosis (IPF).
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.