Sudden cardiac arrest (SCA) kills millions of people worldwide each year, triggered by an electrical malfunction in the heart that causes it to unexpectedly stop beating, often without warning. Health care startup Transformative AI Ltd. wants to reduce those deaths. To that end, the company has secured $1.7 million in seed funding for artificial intelligence (AI)-driven software that predicts a patient’s risk of suffering SCA based on subtle physiological changes.
Tera Ventures led the round, which also included the Wellcome Trust and preseed investor Inhealth Ventures. The Wellcome Trust’s investment was via a Healthcare Innovator Award.
In conjunction with the financing, investors Andrus Oks, founding partner of Estonia-based Tera Ventures, and Nick Slater, partner at London-based AI Seed Fund, are joining Transformative’s board.
The company plans to use the new funding to gain U.S. FDA clearance of its first product for SCA and to begin the building out of technologies that predict other life-threatening conditions.
Early intervention is key
Each year, an estimated 292,000 adults and 7,000 children suffer cardiac arrest in U.S. hospitals, according to the American Heart Association (AHA). Of those, only 25% survive. Globally, SCA claims 6 million lives. Early intervention is a focal point of the AHA’s guidelines on improving cardiac arrest outcomes.
“On each shift, I experience the tragedy of delayed care and the marvel of early, preventive interventions,” said Josh Oppenheimer, Transformative’s co-founder and CEO and a practicing emergency medicine physician. “AI-augmented patient monitoring detects subtle changes preceding patient deterioration that are invisible to physicians, allowing us to be in the right place at the right time and save more lives.”
Transformative’s patented technology analyzes data from patient monitoring tools routinely used in hospitals to identify individuals who are at imminent risk of SCA, enabling doctors and nurses to intervene before an event occurs.
The life-saving tool employs cutting-edge AI and analysis techniques developed at the European Organization for Nuclear Research (CERN) and Cambridge University to anticipate SCA up to an hour in advance based on subtle physiological changes.
“We have compiled the largest electrocardiographic dataset of its kind, comprising tens of thousands of patients’ data and have used this to train our algorithm,” Oppenheimer told BioWorld. “Our product has been technically validated using data collected at our partner hospitals. We are currently negotiating with leading device manufacturers, planning clinical studies and preparing for FDA and CE [mark] applications.”
The predictive software is compatible with patient monitoring devices that are standard in hospitals around the world.
Oppenheimer said the company’s “second wave of products” will build on the SCA work by improving care for related cardiac conditions and predicting noncardiac events.
Co-founders saw disruptive potential of AI
Founded in December 2016 through the Entrepreneur First startup program, Transformative is the brainchild of co-founders Oppenheimer, Marek Sirendi and Marek Rei. The trio met at Cambridge University where Oppenheimer was earning his MBA and Sirendi and Rei were conducting machine learning research.
Their belief in the power of AI to transform health care is grounded in their respective experiences as data scientists and as a physician, Oppenheimer said.
While Oppenheimer has witnessed the impact of early intervention in life-threatening conditions, Sirendi and Rei have seen the potential of machine learning to solve challenging problems. Before Transformative, Sirendi conducted particle physics research at CERN’s Large Hadron Collider, while Rei developed the models powering the Swiftkey predictive keyboard, which was acquired by Microsoft.
The company is headquartered in Cambridge, U.K., with offices in London, Washington and Tallinn, Estonia.
Jack Lewin, chairman of the National Coalition on Health Care, former CEO of the American College of Cardiology and an advisor to Transformative, said the technology could save thousands of lives a year and prevent serious cognitive impairments in survivors when care is delayed. “While this is disheartening, there is new hope. Transformative has developed amazing and disruptive technology capable of predicting sudden cardiac arrest minutes to hours in advance, and with 94% accuracy.”
Expanding field of players
Other companies are leveraging AI in the cardiac space. Last year, Eko Devices Inc. snagged an FDA breakthrough device designation for its electrocardiogram-based algorithm, which could be used to screen for heart failure during routine medical exams. The agency recently permitted its use in detecting patients with heart failure during the COVID-19 pandemic under an emergency use authorization.
Meanwhile, Paris-based Cardiologs Technologies SAS raised $15 million in series A funding earlier this year to advance an AI-based platform to quickly diagnose cardiac arrhythmias. That company also is leveraging its product in the coronavirus outbreak, with a clinical study to remotely monitor cardiac safety in COVID-19 patients treated with the malaria drug hydroxychloroquine. The study, which uses ECG data collected from smartwatches, could help to detect and prevent serious complications linked to the drug, including QT prolongation, an electrical disturbance that can lead to severe heart arrhythmias and death.
Ultromics Ltd. also is vying in the space. The U.K.-based company has partnered with the Mayo Clinic to use its AI software, Echogo Core, to analyze ECGs of COVID-19 patients for signs of how the virus affects the cardiovascular system. The goal is to map cardiac features associated with the virus and improve patient triage and treatment.