Algorithm can accurately diagnose pulmonary hypertension: Study

Corvista System offers noninvasive, point-of-care option for detecting PH

Andrea Lobo avatar

by Andrea Lobo |

Share this article:

Share article via email
A heart-shaped image is superimposed over the human heart in this illustration of the heart and lungs.

Corvista Health’s machine-learned algorithm can accurately diagnose pulmonary hypertension (PH) in a noninvasive way by assessing the elevation of mean pulmonary arterial pressure (mPAP), a study showed.

The point-of-care system is based on a procedure that can be conducted during medical appointments in under five minutes, with patients receiving the results at the same visit. It uses algorithms to detect signs of specific conditions, allowing for the diagnosis of both coronary artery disease — which affects the blood vessels that supply the heart — and PH.

“The CorVista System can transform our approach to PH diagnosis as a frontline diagnostic tool. Now that highly effective new treatment options exist for most patients with PH, earlier detection has become critically important,” Charles R. Bridges, MD, executive vice president and chief scientific officer at Corvista Health, said in a company press release.

The results were described in the study “Clinical validation of a machine-learned, point-of-care system to IDENTIFY pulmonary hypertension,” published in European Respiratory Journal (ERJ) Open Research.

Recommended Reading
An illustration of people looking at information shown on a tablet's screen.

EchoRight Pro app aims to speed pulmonary hypertension diagnosis

Noninvasive system aims to make PH diagnosis easier

PH is characterized by high blood pressure in the pulmonary arteries, the blood vessels that supply the lungs. As a result, the heart’s right ventricle needs to work harder to pump blood, which may lead to right heart failure.

Currently, PH is mainly diagnosed using right heart catheterization, an invasive procedure that measures blood pressure in the pulmonary arteries and the heart’s ability to pump blood. Transthoracic echocardiography, a noninvasive imaging technique, may also be used to estimate pulmonary arterial pressure and assess right heart function, but it has significant limitations in diagnosing PH, the researchers noted.

“Pulmonary hypertension remains vastly underdiagnosed, with patients waiting an average of two and a half years from symptom onset to accurate diagnosis — often after disease progression has already compromised outcomes,” Bridges said.

The now-published study assessed the Corvista System’s accuracy at detecting PH in 462 participants from the IDENTIFY-PH study (NCT04031989) and the IDENTIFY study (NCT03864081).

Because this dataset was independent of the one used to develop the algorithm, the results support the system’s “real-world applicability and generalizability,” according to the company.

Recommended Reading
A speaker points to data on a white board while leading a meeting at a conference.

Corvista point-of-care device good at detecting heart failure: Study

Corvista System at least 93% accurate at detecting PH

The test’s sensitivity, or its ability to detect PH, was assessed in 315 patients with an mPAP of 21 mmHg or higher (how PH is defined, according to current guidelines). Of those, 239 had an mPAP of 25mmHg or higher (how the disease was defined under previous guidelines).

The algorithm’s specificity, or its ability to correctly identify people without PH, was assessed in 147 patients who were considered to have a very low risk for PH through echocardiography.

Among those with an mPAP of 25 mmHg or higher, the algorithm had a specificity of 92% and a sensitivity of 82%. Moreover, it had a specificity of 92% and a sensitivity of 78% in those whose mPAP was at least 21 mmHg.

The accuracy was also high, reaching 95% at the 25 mmHg threshold and 93% at the 21 mmHg threshold.

This system fulfills the need for a non-stress, non-invasive, front-line test for PH, offering substantial benefits to the patient, physician, and the broader healthcare system.

The algorithm had a similar performance at detecting PH in people with pre-capillary PH or pulmonary arterial hypertension, caused by the narrowing of the pulmonary arteries, and those with post-capillary PH, when the condition is caused by left heart disease. It was also able to correctly identify patients with a combination of both pre- and post-capillary PH.

There were no significant differences in the algorithm’s accuracy across sex, age, body mass index (a measure of body fat), and certain coexistent conditions, including hypertension, or high blood pressure, and chronic obstructive pulmonary disease, an inflammatory lung disease.

The Corvista System’s PH indication was approved last year by the U.S. Food and Drug Administration (FDA). In 2022, the device was awarded an FDA breakthrough device designation, aimed at speeding the system’s development and potential approval to help diagnose PH.

“This system fulfills the need for a non-stress, non-invasive, front-line test for PH, offering substantial benefits to the patient, physician, and the broader healthcare system,” the researchers wrote.