ML-based ABPA recurrence predictor in adults with ABPA
Official title: Machine Learning-Based Prediction of Recurrence Risk in Allergic Bronchopulmonary Aspergillosis and Its Clinical Decision-Making Value: A Multicenter Study With External Validation
Run by Qianfoshan Hospital · NCT07714863 · Data updated 2026-11-12
A machine-learning model is being tested to see if it can predict the chance of an ABPA flare within a year in adults with ABPA during a stable phase.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 200 (estimated) |
| Sponsor | Qianfoshan Hospital Academic / other |
| Locations | 1 site (Jinan, Shandong) |
| Status | Recruiting |
| Started | January 1, 2021 |
| Main results expected | December 31, 2028 |
| Study ends | December 31, 2028 |
| Registry record updated | July 20, 2026 |
| Trial ID | NCT07714863 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults aged 18–80 with ABPA per ISHAM 2024 criteria who are in the stable phase and have achieved meaningful improvement after initial therapy.
✕Probably not a fit
Patients outside the stable-phase ABPA criteria or with significant comorbidities or immunocompromised status may not benefit from the model.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This multicenter observational study develops and externally validates multiple machine-learning models to predict acute exacerbation within 12 months in stable ABPA patients, using a bidirectional cohort design. Patients meeting ISHAM 2024 criteria are classified by whether they experience an acute exacerbation within a year, and data are split into training and internal validation sets. A comprehensive feature selection process uses univariate analysis, collinearity checks, nine ML algorithms for feature importance, and expert input to construct 12 independent models. The study aims to evaluate the practical value of the models for risk stratification and clinical decision-making, though specific model performance metrics are not yet provided.
Why it matters
Potential benefit: If successful, patients and clinicians could use the model to identify those at higher risk of ABPA recurrence and tailor monitoring or treatment decisions accordingly.
How similar studies have gone: Previous work in ABPA and other airway diseases has shown promise for ML-based risk prediction, but external validation in ABPA remains limited.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Aged between 18 and 80 years old. 2. Consistent with the diagnostic consensus criteria for ABPA proposed by the ISHAM-ABPA Working Group. 3. Patients in stable phase of ABPA: newly diagnosed treatment-naive patients or those with prior ABPA exacerbation who achieved at least 50% improvement in symptoms assessed by Likert scale or visual analogue scale (VAS) following initial therapy, accompanied by marked radiological improvement (≥50% reduction in pulmonary opacities) or a minimum 20% decline in serum total IgE level. Exclusion Criteria: 1. Concurrent malignant tumors or severe organ dysfunction involving the heart, brain, kidney and other vital organs. 2. Complicated with severe underlying diseases, including active pulmonary tuberculosis, lung cancer, chronic heart failure (NYHA class Ⅳ), chronic kidney disease stage 5 (CKD 5), decompensated liver cirrhosis, etc. 3. Immunocompromised status, such as human immunodeficiency virus (HIV) infection, long-term oral administration of glucocorticoids or immunosuppressive agents. 4. Pregnant or breastfeeding women. 5. Patients with missing core clinical data or incomplete medical records.
Where it's running
-
Department of Respiratory, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, #16766, Jingshi Road, Jinan City, Shandong Province, China
Jinan, Shandong, China Recruiting
Study contacts
- Study coordinator: Qian Qi
- Email: qiqianqlh@163.com
- Phone: +86 13706380314
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Fungal status and prognosis in ABPA: looking at who improves based on fungal tests
This study checks if ABPA patients with positive or negative fungal tests in sputum or BALF have different outcomes over a year.
-
Biologic treatment for adults with ABPA and severe asthma
This project will test whether biologic medicines help adults with ABPA who have severe asthma and elevated eosinophils.
-
Bronchoscopic airway clearance with amphotericin B spraying for ABPA
This study will try bronchoscopic airway clearance plus amphotericin B spraying to see if it helps adults with allergic bronchopulmonary aspergillosis (ABPA) who have mucus plugs.
-
Benralizumab treatment for adults with ABPA and severe asthma
This will test whether benralizumab helps adults (18–75) who have severe asthma with allergic bronchopulmonary aspergillosis (ABPA).
-
Can a multi-omics and AI model predict ABPA relapse within 1 year in adults?
This study tests a machine learning model that uses multi-omics and clinical data to predict the 1-year relapse risk for adults with ABPA who are in a stable state.
-
Immune status and disease control in airway inflammatory diseases
This project will test whether specific blood immune cell patterns relate to disease control in adults with asthma, COPD, bronchiectasis, or obstructive sleep apnea by comparing them with healthy volunteers.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.