The U.S. Food & Drug Administration (FDA) recently granted Breakthrough Device Designation to an AI algorithm designed to aid in the early detection of pulmonary hypertension (PH). This type of high blood pressure often goes undetected until it has reached an advanced stage. The algorithm was developed by the health technology company Anumana in collaboration with researchers at the Mayo Clinic and at the pharmaceutical company Janssen Research & Development, LLC. It works with data from 12-lead ECGs, which are usually found in emergency rooms, urgent care settings, and primary care facilities. In time, we expect it to be available on wearables and other mobile devices.

Personal ECGs have seen significant advancements of late. AliveCor stepped up from a single-lead ECG device to its popular 6-lead KardiaMobile 6L in 2019, which the company touted it as the world’s first 6-lead personal device. Today’s medical-grade ECG devices, such as the Eko DUO ECG, are increasingly coming down both in size and in price, making them more amenable to personal use. With the growing increase in the number of leads in more widely available ECG devices, there’s naturally a growing need for advanced algorithms to process the increased data that’s collected.

The new algorithm is used to mine massive amounts of information from the nference platform, which collects unstructured real-world biomedical data from electronic medical records (EMRs). This includes over 6 million patient records (which are de-identified) and more than 8 million ECGs. If the algorithm is approved for use, Anumana plans to offer it as software that physicians can download onto devices they use with 12-lead ECGs. Then, within seconds, the algorithm will be able to analyze the nference data and predict the likelihood of PH in the patient.

The Mayo Clinic’s Dr. Paul Friedman says “The addition of AI to a standard ECG — a painless, inexpensive, widely used test that is routinely performed — transforms the ECG into a screening tool for PH, with the opportunity to improve outcomes via early detection by guiding appropriate testing. [And] early diagnosis of pulmonary hypertension is paramount due to its progression and potential severity.” Dr. Najat Khan, of Janssen Research & Development, LLC., adds, “While therapeutic options for patients with pulmonary hypertension have evolved in recent years, we have not seen significant advancement in reducing the time from symptom onset to diagnosis…[the algorithm] could help change this.”