This archive report was first published on 25 September 2019.
Published on September 25, 2019, a study by University Hospitals Birmingham NHS Foundation Trust has shown that artificial intelligence can identify illnesses ranging from cancer to eye diseases as accurately as trained doctors.
Using a technique known as deep learning, computers can examine thousands of medical images to identify patterns of disease. This has enormous potential for improving the precision and speed of diagnosis, according to scientists.
The study, published in The Lancet Digital Health, pooled data from 14 trials and showed that deep learning correctly detected disease in 87 per cent of cases - compared to 86 per cent achieved by doctors. The ability to accurately rule out patients who did not have disease was similar - 93% for the machine algorithms compared to 91 per cent for doctors.
Lead author Professor Alastair Denniston noted that while AI can detect diseases as accurately as health professionals, it did not substantially out-perform human diagnosis.
More than 30 AI algorithms for healthcare have already been approved by the US Food and Drug Administration, and there have been strong market forces driving their development. However, the study notes that only a few studies were of sufficient quality to be included in the analysis, and the true power of AI remains uncertain.
Prof Denniston and colleagues called for higher standards of research and reporting to improve future evaluations, and for evidence on how AI algorithms will change patient outcomes to come from comparisons with alternative diagnostic tests in randomised controlled trials.
