E-HEALTH - E-SANTE - PHARMAGEEK

Doctors will be helped by AI

The world needs high-quality healthcare just as it’s running out of doctors, warned Ada Health co-founder Claire Novorol – but AI can help. “In India and China, doctors have two minutes per patient,” she told delegates. “In Bangladesh it’s 43 seconds.” Her solution is Ada – a diagnostic AI built with GPs. It’s human plus machine, she explained. “Doctors are better at patient relationships, but AI has less bias and a better memory.”

Francis Crick Institute researcher Andrew Steele argued that AI’s lack of bias means it’s ideal to answer the dreaded question – how long have I got, doctor? Steele analysed the electronic health records of more than 100,000 patients, checking for diagnosis, prescription and results to arrive at strong prediction models. “Doctors can just press a button, the AI looks at the patient’s health record then spits out immediately – a ten per cent chance of dying in next five years, for instance,” he explained. The next step? Letting AI help prescribe treatment.

The Use of Artificial Intelligence in Cardiology:  As the type and breadth of data available to cardiologists and the cardiovascular care team continues to grow more sophisticated, physicians are increasingly being asked to provide more rapid and personalized interpretations of data to their patients. One solution to providing this level of personalized medicine efficiently is artificial intelligence, also known as machine learning. researchers analyze select applications of artificial intelligence in cardiology and identify how the specialty could incorporate more artificial intelligence in the future to enhance the capabilities and experiences of clinicians and patients.  “(Artificial intelligence) has clear potential to enhance every stage of patient care — from research and discovery, to diagnosis, to selection of therapy,” said Joel Dudley, Ph.D., senior author of the review and director of the Next Generation Healthcare Institute at Mount Sinai. “A key next step to incorporating artificial intelligence into cardiology is to align available data and technologies with clinical and business use. This way, we can prioritize short-term opportunities and understand gaps in available data or algorithms that are holding back applications of artificial intelligence in areas of high clinical need.”  According to the review, artificial intelligence is currently only performed by those with specialized training, but in the future, these methods will be increasingly easy and widely available. It may eventually be incorporated into day-to-day practice by interacting with electronic health records and billing.