Artificial Intelligence-assisted Evaluation of Pulmonary HYpertension

NCT05566002 | Recruiting

• 1 other identifier: AIPHY Project
• Study Type: observational
• Target: 2,000
• Locations: 1 country
• Sites: 1

Brief Summary

Pulmonary hypertension represents a challenging and heterogeneous condition that is associated with high mortality and morbidity if left untreated. Artificial intelligence is used to study and develop theories and methods that simulate and extend human intelligence, which is being applied in fields related to cardiovascular diseases. The study intends to combine multimodal clinical data of patients who undergo right heart catheterization at Fuwai Hospital with artificial intelligence techniques to create programs that can screen and diagnose pulmonary hypertension.

Conditions

Pulmonary Hypertension; Pulmonary Arterial Hypertension

Keywords

pulmonary hypertension; pulmonary vascular disease; right heart catheterization; echocardiography; electrocardiography; chest X-ray; artificial intelligence; machine learning; deep learning; screening; diagnosis

Outcome Measures

Primary Outcomes (1)

• Accuracy of diagnosis by artificial intelligence-assisted algorithm

  The investigators will calculate the area under the receiver operating characteristic curve of diagnosis by artificial intelligence-assisted algorithm and compare this index between artificial intelligence-assisted algorithm and RHC.

  Baseline

Secondary Outcomes (2)

• Sensitivity of diagnosis by artificial intelligence algorithm

  Baseline

• Specificity of diagnosis by artificial intelligence algorithm

  Baseline

Study Arms (2)

Patients with pulmonary hypertension

A series of routine examinations, including chest X-ray, electrocardiography, echocardiography, etc, would be performed on consecutive patients at Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. An RHC with an mPAP of \>20 mmHg would confirm the diagnosis of PH. All these data will be collected as a source for machine learning or other artificial intelligence-assisted programs.

Diagnostic Test: Right heart catheterization

Patients without pulmonary hypertension

A series of routine examinations, including chest X-ray, electrocardiography, echocardiography, etc, would be performed on consecutive patients at Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. An RHC with an mPAP of ≤20 mmHg would confirm the absence of PH. All these data will be collected as a source for machine learning or other artificial intelligence-assisted programs.

Diagnostic Test: Right heart catheterization

Interventions

Right heart catheterization DIAGNOSTIC_TEST

RHC is commonly used essential test to make gold-standard diagnosis of PH with mPAP \>20 mmHg. All multimodal data from patients eligible for inclusion would be randomly assigned to development datasets (70% of the study population) to train the artificial intelligence models for the detection of PH, which would be validated and tested by other datasets (30% of the study population).

Patients with pulmonary hypertension; Patients without pulmonary hypertension

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adult patients previously received chest X-rays, electrocardiography, echocardiography, other routine examinations, and RHC at the Fuwai Hospital, CAMS \& PUMC, Beijing, China.

You may qualify if:

• Age ≥18 years old
• Patients previously received chest X-ray, electrocardiography, echocardiography, other routine examinations, and RHC at the Fuwai Hospital, CAMS \& PUMC, Beijing, China

You may not qualify if:

• Patients without RHC
• The quality of routine examinations and RHC cannot meet the requirement for further analysis
• Severe loss of results of routine examinations (chest X-ray, electrocardiography, echocardiography, etc.)

Sponsors & Collaborators

• Chinese Pulmonary Vascular Disease Research Group: lead

Study Sites (1)

Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College

Beijing, Beijing Municipality, 100037, China

RECRUITING

Related Publications (2)

• Huang Z, Diao X, Huo Y, Zhao Z, Geng J, Zhao Q, Liu J, Xi Q, Xia Y, Xu O, Li X, Duan A, Zhang S, Gao L, Wang Y, Li S, Luo Q, Liu Z, Zhao W. Deep Learning-Enhanced Noninvasive Detection of Pulmonary Hypertension and Subtypes via Chest Radiographs, Validated by Catheterization. Chest. 2025 Nov;168(5):1215-1230. doi: 10.1016/j.chest.2025.06.008. Epub 2025 Jun 18.

  PMID: 40541737 DERIVED

• Zhao W, Huang Z, Diao X, Yang Z, Zhao Z, Xia Y, Zhao Q, Sun Z, Xi Q, Huo Y, Xu O, Geng J, Li X, Duan A, Zhang S, Gao L, Wang Y, Li S, Luo Q, Liu Z. Development and validation of multimodal deep learning algorithms for detecting pulmonary hypertension. NPJ Digit Med. 2025 Apr 10;8(1):198. doi: 10.1038/s41746-025-01593-3.

  PMID: 40205021 DERIVED

MeSH Terms

Conditions

Hypertension, Pulmonary; Pulmonary Arterial Hypertension; Disease

Condition Hierarchy (Ancestors)

Lung Diseases; Respiratory Tract Diseases; Hypertension; Vascular Diseases; Cardiovascular Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Zhihong Liu, MD, PhD

  Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Zhihong Liu, MD, PhD

CONTACT

13269276067; zhihongliufuwai@163.com

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 30, 2022
• First Posted: October 4, 2022
• Study Start: June 1, 2022
• Primary Completion: December 31, 2025
• Study Completion: December 31, 2025
• Last Updated: April 8, 2025

Record last verified: 2025-04

Locations

CN (1)