Anumana unveils promising AI algorithm for early detection of pulmonary hypertension
Anumana, an AI-driven health technology leader and a portfolio company of nference, has announced significant advancements in pulmonary hypertension (PH) diagnosis through its latest study, revealing promising results for its investigational PH algorithm. The study, titled “An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension,” was published in the European Respiratory Journal, showcasing the algorithm’s ability to detect PH using routine 12-lead electrocardiogram (ECG) data.
Pulmonary hypertension is a severe, progressive illness where delays in diagnosis significantly increase the risk of morbidity and mortality. Typically, diagnostic delays span over two years from symptom onset, primarily due to the disease’s non-specific early symptoms. Addressing this critical challenge, Anumana, in collaboration with Mayo Clinic, Vanderbilt University Medical Center (VUMC), and Janssen Research & Development, LLC—a Johnson & Johnson company—has pioneered an AI algorithm designed for early PH detection using routinely collected ECG data.
The AI algorithm was trained and validated using retrospective ECG data alongside right heart catheterization or echocardiogram data from a pool of 39,823 PH-likely patients and 219,404 control patients at Mayo Clinic. It underwent further validation on an additional 6,045 PH-likely patients and 24,256 control patients from VUMC. Impressively, the algorithm achieved an area under the receiver operating characteristic curve (AUC) of 0.92 at Mayo Clinic and 0.88 at VUMC, indicating high efficacy in PH identification.
Recognized for its potential, the PH algorithm received the FDA’s Breakthrough Device designation in 2022. Anumana is actively pursuing FDA clearance and CE marking to bring this innovative solution to clinical practice. The technology aims to shift the paradigm in cardiac care by enabling earlier and more accurate detection of PH, thereby improving patient outcomes and reducing the diagnostic journey for those affected.
“The promising data from our study suggest that an AI algorithm has the potential to non-invasively detect PH at an early stage using standard ECGs,” said Dr. Hilary DuBrock, a Mayo Clinic pulmonologist and the study’s lead author. Maulik Nanavaty, CEO of Anumana, added, “These new data underscore the potential of AI algorithms to empower clinicians to uncover diseases earlier, improve patient outcomes, and bring us one step closer to our mission to transform cardiac care.”
This development in AI-driven diagnostics by Anumana could significantly reduce the burden on healthcare systems by facilitating the early detection of pulmonary hypertension. The use of non-invasive, easily accessible ECG data to predict such a complex condition demonstrates the transformative potential of AI in healthcare.