Computers are now better at treating cancer than doctors

Thursday, May 02, 2013 by: Ethan A. Huff, staff writer
Tags: cancer treatment, computer modeling, oncology

(NaturalNews) Researchers from the Netherlands claim to have found a better way to develop and monitor the effects of treatment protocols for cancer patients, but it involves taking doctors out of the picture. As reported by the U.K.'s Independent, a team of scientists from Maastricht University Medical Hospital has developed a computer model they say is able to more accurately predict how cancer patients will respond to various treatment options compared to experienced oncologists doing the same work by hand.

According to reports, the team that developed the program tested it on 121 lung cancer patients undergoing conventional treatments involving both radiotherapy and chemotherapy. The patients' personal medical details, as well as data on their treatment histories, was input into the computer model and used to make an assessment of how each patient would respond to the treatments over the course of a two-year period.

Specifically, the research team, led by Dr. Cary Oberije, looked at how many of the 121 lung cancer patients would likely still be alive after two years, as well as how many of them would suffer side effects such as breathing problems and difficulty swallowing. Upon analysis, the researchers determined that in each of these three categories, the computer model more accurately predicted patient outcomes and appropriate treatment intervals compared to doctors making such decisions on their own accord.

"If models based on a patient, tumor and treatment characteristics already outperform the doctors, then it is unethical to make treatment decisions based solely on the doctors' opinion," says Dr. Oberije, as quoted by the Independent. "We believe models should be implemented in clinical practice to guide decisions."

Is mathematical modeling the future of healthcare?

The findings may strike a blow to the collective ego of the cancer industry, which is generally quite hostile to treatment modalities that fall outside the conventional paradigm. But they just go to show that doctors are not omniscient, and they do not always know, or take the time to learn, how to best treat patients individually rather than generically.

"We have shown that current models already outperform doctors," adds Dr. Oberije. "We know that there are many factors that play a role in the prognoses of patients and prediction models can combine them all. They are not perfect, but neither are humans and models are better than humans ... Our study shows that it is very unlikely that a doctor can outperform a model."

In similar but unrelated work, researchers from Stanford University are in the process of developing biological computational mechanisms that they claim can be placed directly inside living cells to perform mathematical functions. According to the Massachusetts Institute of Technology (MIT)'s Technology Review, scientists at the school are developing a genetic "transcriptor," of sorts, that may eventually help in disease detection and chemical production, among other tasks.

Sources for this article include:

http://www.dailymail.co.uk

http://www.independent.co.uk

http://www.technologyreview.com