Thalamus has been awarded a UK Government grant to develop an artificial intelligence system to assist doctors during diagnostic heart surgery. When launched, the algorithm will save approximately 7,000 lives per year, and improve the outcomes of a further 140,000.
The algorithm is designed to work during Fractional Flow Reserve (FFR) - a leading technique for diagnosing narrowings in the coronary arteries, a problem that leads to an impeded oxygen supply to the heart muscle causing severe chest pain, which can lead to heart attack and death. Last year there were 500,000 FFR procedures. Of these, studies suggest that due to measurement errors, up to 30% were performed incorrectly, leading to unnecessary treatments and increased mortality and morbidity rates. These errors occur due to the subtlety of the readings and even experienced FFR experts can make mistakes or miss key information.
The software will observe how the procedure is progressing and alert the doctor to measurement errors it detects, enabling the physician to quickly correct the cause of the error and correcting the potentially incorrect diagnosis.
Thalamus' CEO, Jeremy Walker, says:
"Artificial intelligence is heralding a wealth of new opportunities to dramatically improve healthcare and reduce costs. In a time where heart disease is on the rise and health system worldwide are struggling under increasing costs, this sorts of innovation makes a huge difference."
"Once successfully developed, we hope to build on our success and work towards a fully AI system that can provide fully automated diagnoses and eliminate all human-error, dramatically reducing procedure time and waiting lists, and freeing up doctors."
Thalamus is an applied artificial intelligence company who develop innovative systems across a variety of sectors. They apply the latest artificial intelligence research and techniques to real-world problems. This project is a joint venture with Dr Justin Davies, a senior cardiologist consultant.
If you'd like to discuss Thalamus' work, we'd love to hear from firstname.lastname@example.org