Combining chest X-rays and arterial blood gas results to predict ventilator need in critically ill adults
Combining Chest X-Ray Findings With Arterial Blood Gas Analysis for Generation of Machine Learning Model Assessing the Need for Mechanical Ventilation in Critically Ill Patients
This project will test whether a computer model that uses chest X-rays and arterial blood gas results can predict which critically ill adults will need mechanical ventilation.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 2160 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Zagazig University Government |
| Locations | 1 site (Zagazig, Al Sharqia) |
| Trial ID | NCT07001696 on ClinicalTrials.gov |
What this trial studies
This prospective cross-sectional study at Zagazig University Hospitals will develop a machine learning model that integrates chest X-ray radiographic features with arterial blood gas (ABG) parameters to predict the need for mechanical ventilation in critically ill adults. About 2,160 patients will be enrolled over six months and data collected will include demographics, clinical status, ABG values (pH, PaO2, PaCO2, HCO3) and radiologic findings (infiltrates, effusions, consolidation). The model will be trained on 70% of the dataset and validated on the remaining 30%, and performance will be compared to standard clinical assessments using metrics such as accuracy and RMSE. The protocol has institutional IRB approval and aims to provide an objective decision-support tool to aid ventilator decision-making.
Who should consider this trial
Good fit: Critically ill adults (age ≥18) at Zagazig University Hospitals who have both a chest X-ray and an arterial blood gas performed at the time of evaluation are the intended participants.
Not a fit: Patients with chronic unrelated lung diseases, pregnant females, or those with missing chest X-ray or ABG data are excluded and may not benefit from this approach.
Why it matters
Potential benefit: If successful, the model could help clinicians make faster, more objective decisions about starting mechanical ventilation and potentially improve patient outcomes.
How similar studies have performed: Machine learning has been applied to imaging or ABG data separately in prior work, but combining both modalities to predict ventilator need is relatively novel and not yet widely validated.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: Critically ill adult patients aged 18 years or older. Patients assessed to require mechanical ventilation. Control group: Age- and sex-matched critically ill patients not requiring mechanical ventilation. Availability of both chest X-ray and arterial blood gas (ABG) analysis at the time of evaluation. Exclusion Criteria: Patients with missing or incomplete data (e.g., absent chest X-ray or ABG results). Patients with chronic lung diseases unrelated to the current admission (e.g., COPD, pulmonary fibrosis). Pregnant females.
Where this trial is running
Zagazig, Al Sharqia
- Faculty of medicine, zagazig university — Zagazig, Al Sharqia, Egypt (Recruiting)
Study contacts
- Study coordinator: Omaima Ibrahim Prof
- Email: OIAbdelhamid@medicine.zu.edu.eg
- Phone: +201001664310
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.