AI that mimics mindset of a doctor could transform medical practice

Over the years, experts have applied artificial intelligence (AI) to diagnose medical conditions in specific fields and can build on the knowledge of particular disciplines to hone in on details such as the shape of a tumour that suggests breast cancer or abnormal cells that indicate cervical cancer.

But while AI is very good when trained on years of human data in specific domains, it has yet to deal with the huge number of diagnostic tests (about 5,000) and disorders (about 14,000) of modern clinical practice.

To tackle this issue, the new algorithm, developed by engineers at the USC Viterbi School of Engineering in California, is said to think and learn just like a doctor but with essentially infinite experience.

The research derives from the lab of Gerald Loeb, a professor of biomedical engineering, pharmacy, and neurology at USC Viterbi, and a trained physician. Loeb spent years applying AI algorithms to haptics and building robots to sense and identify materials and objects.

While the state of AI for haptics was to identify about 10 objects with about 80 per cent accuracy, Loeb and his graduate student, Jeremy Fishel, could identify 117 objects with 95 per cent accuracy. When they extended it to 500 objects and 15 different possible tests, their algorithm got even faster and more accurate. That, Loeb says, is when he started thinking about adapting it for medical diagnosis.

Loeb’s new form of AI suggests the best diagnostic strategies by mining electronic healthcare records in databases. This could lead to faster, better, and more efficient diagnoses and treatments.

“The algorithm works just like a doctor – thinking about what to do next at each stage of the medical workup,” Loeb explained. “The difference is that it has the benefit of all the experiences in the collective healthcare records.”

Conventional AI has long used a specific algorithm to suggest to physicians the most likely diagnoses given a set of observations. Called Bayesian Inference, it uses whatever information is currently available to suggest which diagnoses are the most likely.

Loeb’s algorithm, which he named ‘Bayesian Exploration’, reverses this process and instead seeks those tests that would most likely identify the correct illness or condition, no matter how obscure. The algorithm can also consider the costs and delays associated with various diagnostic tests, he added.

According to Loeb, this new algorithm could help doctors make better diagnostic and testing decisions by suggesting several good options, including some a practitioner might not have otherwise considered. The diagnostic software would also automatically update and improve, as myriad physicians input additional data into electronic medical records.

In addition, Loeb believes doctors would more easily generate complete and accurate medical records. Instead of having to hunt for codes or work their way through many drop-down menus, they could simply select a particular illness or diagnostic procedure suggested by the AI, which would automatically input the correct information into the electronic records.

Loeb also emphasised that physicians could override the AI and go with their own judgment. “The algorithm isn’t meant to make decisions for doctors or replace them. It’s meant to complement and support them,” he added.