PH-DyPred: Multimodal dynamic risk prediction in pulmonary hypertension

Research on Dynamic Risk Prediction for Patients With Pulmonary Hypertension Based on Multimodal Data Fusion: A Prospective Observational Study

First Affiliated Hospital of Fujian Medical University · NCT07131241

This project will try to build a prediction model using scans, ECGs, blood tests, and clinical data to see which adults with pulmonary hypertension are at higher risk of hospitalization, worsening symptoms, or death.

Quick facts

Study typeObservational
Enrollment1000 (estimated)
Ages18 Years and up
SexAll
SponsorFirst Affiliated Hospital of Fujian Medical University (other)
Locations1 site (Fuzhou, Fujian)
Trial IDNCT07131241 on ClinicalTrials.gov

What this trial studies

This prospective observational cohort will enroll adults with pulmonary hypertension and collect serial multimodal data including echocardiography, cardiac MRI, PET-MR, ECG, blood biomarkers, and clinical information. Biospecimens (whole blood, serum, plasma, urine, stool) will be banked for multi-omics analyses and linked with imaging and outcomes using de-identified codes. Machine learning and data-fusion methods will be used to derive and internally and externally validate a dynamic prognostic model predicting hospitalization, functional decline, and mortality. The aim is to identify key predictive markers and enable individualized early-warning and management strategies.

Who should consider this trial

Good fit: Adults aged 18 or older with pulmonary artery systolic pressure ≥35 mmHg on echocardiography who can provide informed consent and attend baseline and follow-up visits are ideal candidates.

Not a fit: Patients with active cancer treatment, severe hepatic or renal failure, uncontrolled infection or autoimmune disease, recent major surgery, pregnancy, or those unable to complete follow-up may not receive benefit from the study findings.

Why it matters

Potential benefit: If successful, the model could provide earlier warnings and help clinicians tailor monitoring and treatment to reduce hospitalizations and slow disease progression.

How similar studies have performed: Previous work combining imaging, biomarkers, and machine learning has shown promising signals for risk stratification in pulmonary hypertension, but fully integrated multimodal models including PET-MR and multi-omics remain largely novel and unproven.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Adults aged 18 years or older
* Pulmonary artery systolic pressure (PASP) ≥35 mmHg as estimated by echocardiography
* Provided written informed consent

Exclusion Criteria:

* Severe hepatic or renal insufficiency
* Malignancy under active treatment
* Severe infection
* Active autoimmune disease
* Major surgery within the past 3 months
* Pregnant or breastfeeding women
* Severe psychiatric disorder impairing ability to comply with the study protocol

Where this trial is running

Fuzhou, Fujian

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.

View on ClinicalTrials.gov →

Conditions: Pulmonary Hypertension, Dynamic Risk Prediction, Multimodal Data Fusion, Echocardiography, Right Heart Function, Cardiac Magnetic Resonance

Last reviewed 2026-05-15 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.