Thursday, September 1, 2016

This AI software can tell if you're at risk from cancer before symptoms appear


Breast cancer is the most common cancer in the UK, with one in eight women receiving the terrifying diagnosis in their lifetime.
But researchers have now developed artificial intelligence software that can accurately predict breast cancer risk, which would enable doctors to closely monitor those most at risk of developing the potentially life-threatening disease.
The AI program reliably interprets mammograms and translates patient data into diagnostic information 30 times faster than a human doctor, with 99 per cent accuracy.
It was developed by researchers at Houston Methodist Research Institute in Texas.
“This software intelligently reviews millions of records in a short amount of time, enabling us to determine breast cancer risk more efficiently using a patient's mammogram,” said Stephen T Wong, chair of the Department of Systems Medicine and Bioengineering at the institute. “This has the potential to decrease unnecessary biopsies," he added.

The team used the AI software to evaluate mammograms and pathology reports of 500 breast cancer patients.
The software scanned patient charts, collected diagnostic features and correlated mammogram findings with breast cancer subtype. Clinicians used results, such the expression of tumour proteins, to accurately predict each patient's probability of breast cancer diagnosis.
In the US, 12.1 million mammograms are performed annually, but half yield false results, according to the American Cancer Society, resulting in one in two healthy women being told they have cancer.
Patients who are told they are at particular risk of breast cancer are often recommended for biopsies – a necessary but invasive procedure that removes tissue or fluid from a suspicious area so cells can be analysed. However, 20 per cent are performed unnecessarily.
The researchers hope their software will help physicians better choose which patients need the procedure and decrease unnecessary breast biopsies.
Manual review of 50 charts took two clinicians 50 to 70 hours, whereas the AI software reviewed 500 charts in a few hours, saving the human doctors 500 hours of their time.
"Accurate review of this many charts would be practically impossible without AI," Dr Wong said.

No comments:

Post a Comment

AddToAny