Artificial Intelligence-assisted Evaluation of Pulmonary HYpertension (AIPHY)

Artificial Intelligence-Assisted Evaluation of Pulmonary Hypertension

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.

Study Overview

• Status: Recruiting
• Conditions: Pulmonary Arterial Hypertension; Pulmonary Hypertension
• Intervention / Treatment: Diagnostic test: Right heart catheterization

Detailed Description

Patients with pulmonary hypertension (PH) represent a challenging and heterogeneous cohort with high morbidity and mortality if left untreated. To make a definitive diagnosis of PH, one needs to conduct an invasive right heart catheterization (RHC) in order to assess the mean pulmonary artery pressure (mPAP). As PH occurs sporadically in various medical conditions, including connective tissue disease, and congenital heart disease, and presenting symptoms are non-specific, there is a need to raise the suspicion of PH early in the community. For this reason, noninvasive tools that are widely available for upfront screening would be ideal to enable timely diagnosis of PH. Transthoracic echocardiography has emerged as the mainstay for screening of PH, yet the sensitivity and specificity of this approach remain limited even in experienced hands. As high-throughput technologies advance and access to PH big data improve, it will be critical to prudently select artificial intelligence approaches for data analysis, visualization, and interpretation. By combining the multimodal clinical data (such as indicators from chest X-ray, electrocardiography, and echocardiography), this study aims to develop artificial intelligence-assisted programs to assist the screening and diagnosis of PH, and to evaluate its diagnostic accuracy for PH as compared with RHC, and to estimate whether this approach outperforms the conventional echocardiographic method.

• Study Type: Observational
• Enrollment (Estimated): 2000

Contacts and Locations

• Study Contact: Name: Zhihong Liu, MD, PhD; Phone Number: 13269276067; Email: zhihongliufuwai@163.com

Study Locations

• China
  • Beijing
    • Beijing, Beijing, China, 100037
      • Recruiting
      • Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College
      • Contact: Zhihong Liu, MD, PhD; Phone Number: 13269276067; Email: zhihongliufuwai@163.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes

• 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.

Description

Inclusion Criteria:

• 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

Exclusion Criteria:

• 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.)

Study Plan

How is the study designed?

Design Details

• Observational Models: Case-Only
• Time Perspectives: Retrospective

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
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; 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 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; 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).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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 Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity of diagnosis by artificial intelligence algorithm	The investigators will calculate the sensitivity of diagnosis by artificial intelligence-assisted algorithm and compare this index between artificial intelligence-assisted algorithm and RHC.	Baseline
Specificity of diagnosis by artificial intelligence algorithm	The investigators will calculate the sensitivity of diagnosis by artificial intelligence-assisted algorithm and compare this index between artificial intelligence-assisted algorithm and RHC.	Baseline

Collaborators and Investigators

• Sponsor: Chinese Pulmonary Vascular Disease Research Group
• Investigators: Principal Investigator: Zhihong Liu, MD, PhD, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College

Study record dates

Study Major Dates

• Study Start (Actual): June 1, 2022
• Primary Completion (Estimated): December 31, 2025
• Study Completion (Estimated): December 31, 2025

Study Registration Dates

• First Submitted: September 30, 2022
• First Submitted That Met QC Criteria: September 30, 2022
• First Posted (Actual): October 4, 2022

Study Record Updates

• Last Update Posted (Actual): April 8, 2025
• Last Update Submitted That Met QC Criteria: April 6, 2025
• Last Verified: April 1, 2025

More Information

Terms related to this study

• Keywords: machine learning; echocardiography; artificial intelligence; diagnosis; screening; pulmonary hypertension; deep learning; pulmonary vascular disease; electrocardiography; right heart catheterization; chest X-ray
• Additional Relevant MeSH Terms: Vascular Diseases; Cardiovascular Diseases; Respiratory Tract Diseases; Lung Diseases; Pulmonary Arterial Hypertension; Hypertension; Hypertension, Pulmonary
• Other Study ID Numbers: AIPHY Project

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No