Predictive Analytics Detects Breast Cancer Spread with 90% Accuracy

A predictive analytics method was able to detect with 90 percent accuracy which stage 0 breast cancers are likely to spread and recur, according to a study published in the American Journal of Physiology-Cell Physiology.

Approximately one in five new breast cancers are caught at their earliest stages, the researchers noted, but physicians aren’t able to confidently predict which of these stage 0 breast cancers are likely to recur and spread after surgery, or which forms surgery is likely to cure.

Understanding which aggressive a stage 0 cancer is likely to be will help doctors and their patients decide on the best course of treatment, which consists of removal of the tumor and a small amount of tissue followed by radiation, or removal of the entire breast.

To help providers better forecast the aggressiveness of these cancers, researchers developed a predictive analytics tool using samples from 70 patients who had stage 0 breast cancer. These patients had all undergone a mastectomy, and each had at least ten additional years of medical records available. Twenty of the 70 patients experienced a recurrence of their cancer, while 50 did not.

The team stained these tissue samples so that the proteins of interest would fluoresce under the microscope. Then, using a computer vision application, researchers created a library of microscope images associated with either aggressive or non-aggressive ductal carcinoma in situ (DCIS) based on what had happened to that patient.

Researchers then showed the program roughly 100 micrographs it hadn’t seen before, known as holdout images, to see how well it could accurately predict whether that patient’s cancer was likely to recur.

“The computer is looking for patterns in the images that humans can’t readily discern, from the level of individual pixels up to an entire image of a million pixels,” said Howard Petty, PhD, a professor of ophthalmology and visual sciences, and of microbiology and immunology at Michigan Medicine, the University of Michigan’s academic medical center.

The program is now able to correctly identify aggressive and non-aggressive disease 96 percent of the time, the researchers noted.

“That’s pretty impressive when you consider that a human looking at these images would get the answer right about 70 percent of the time,” Petty said. “And we’ve continued to work on reducing the level of false negatives.”

The tool also reported false positives in four percent of cases, meaning it identified aggressive disease in patients who did not experience recurrence.

“We believe many of these examples speak to the skill of the patient’s surgeon, who effectively cured them of more aggressive disease in the operating room,” Petty said.

Researchers plan to continue to refine the approach using additional samples, and the team expects that with further validation the tool could be approved for clinical use by the FDA within the next few years. The approach could also help providers predict the aggressiveness of similar types of cancer.

“We started with a hypothesis about the biochemical mechanisms that drive cancer recurrence, tested the role of the movement of key proteins to the cell membrane in cancer recurrence and then confirmed our understanding of the underlying biology by assessing how well our explanation predicted what we actually see in patients,” Petty said.

“This improved understanding of the biology of cancer recurrence could also inform the development of new anti-cancer drugs.”

By determining that the location of key proteins can predict a cancer’s aggressiveness, researchers could enhance treatment of stage 0 breast cancers.

“Scientists don’t really understand what leads to cancer recurrence at the molecular level and that has made it impossible to accurately predict which patients will experience a recurrence and which won’t,” said Petty.

“What we found is that certain key enzymes collect near the cell membrane in these early breast cancers that end up being aggressive, but they don’t in the cancers that are non-aggressive.”