[ad_1]
The researchers created a new machine learning software that can predict survival rates and response to treatments for ovarian cancer patients.
The artificial intelligence software, created by researchers from Imperial College London and the University of Melbourne, was able to predict the prognosis of patients with cancer-related cancer. Ovary more precisely than current methods. He can also predict which treatment would be most effective for patients after diagnosis.
The lawsuit, published in Nature Comunications was held at Hammersmith Hospital, part of the Imperial College Healthcare NHS Trust.
The researchers say the new technology could help clinicians deliver the best treatments to patients faster and pave the way for more personalized medicine. They hope that the technology can be used to stratify patients with ovarian cancer into groups based on the subtle differences in their cancer's texture on CT scanners rather than a classification based on their cancer type or condition d & # 39; advance.
Professor Eric Aboagye, lead author and professor of cancer pharmacology and molecular imaging at Imperial College London, said:
"The long-term survival rates of patients with advanced ovarian cancer are poor despite advances in the treatment of cancer. It is urgent to find new ways to treat the disease. Our technology is able to provide clinicians with more detailed and accurate information about the likely response of patients to different treatments, which may enable them to make better and more targeted treatment decisions.
Artificial intelligence has the potential to transform the way health care is delivered and improve outcomes for patients. Professor Andrea Rockall Honorary Consultant Radiologist, Imperial College Healthcare NHS Trust
Professor Andrea Rockall, co-author and honorary consultant radiologist at the Imperial College Healthcare NHS Trust, added:
"Artificial intelligence has the potential to transform the way health care is delivered and improve outcomes for patients. Our software is one example and we hope it can be used as a tool to help clinicians better manage and treat ovarian cancer patients. "
Ovarian cancer is the sixth most common cancer in women and usually affects women after menopause or those with a family history of the disease. There are 6,000 new cases of ovarian cancer a year in the UK, but the long-term survival rate is only 35 to 40% because the disease is often diagnosed much more late when symptoms, such as bloating, are noticeable. Early detection of the disease could improve survival rates.
Doctors diagnose ovarian cancer in several ways, including a blood test to look for a substance called CA125 – an indication of cancer – followed by a scanner using X-rays and a computer to create detailed images of the ovarian tumor. This helps clinicians know how far the disease has spread and determines the type of treatment that patients receive, such as surgery and chemotherapy.
However, the analyzes can not give clinicians detailed information about the likely overall results of the patients or the likely effects of a therapeutic intervention.
Researchers used mathematical software called TEXLab to identify the aggressiveness of tumors in CT scans and tissue samples from 364 women with ovarian cancer between 2004 and 2015.
The software examined four biological features of tumors that significantly influence overall survival – structure, shape, size, and genetic makeup – to assess the patient's prognosis. The patients then received a score called radiological prognosis vector (RPV) indicating the severity of the disease, ranging from mild to severe.
The researchers compared the results with blood tests and the current prognostic scores used by doctors to estimate survival. They discovered that the software was up to four times more accurate in predicting ovarian cancer mortality than standard methods.
The team also found that 5% of patients with a high VPA score had a survival rate of less than two years. High VPR was also associated with resistance to chemotherapy and poor surgical results, suggesting that RPV can be used as a potential biomarker to predict how patients would respond to treatment.
Professor Aboagye suggests that this technology can be used to identify patients unlikely to respond to standard treatments and offer them alternative treatments.
Researchers will conduct a larger study to determine the extent to which the software can predict the outcome of surgery and / or pharmacotherapy for individual patients.
The study was funded by the Imperial Biomedical Research Center, the Imperial College Experimental Cancer Research Center, and the Imperial College Health Tissue Bank.
This research is an example of the work done by the University College of Health Sciences at Imperial College, a joint initiative of Imperial College London and three hospital trusts of the NHS. Its goal is to transform healthcare by transforming scientific discoveries into medical advances for the benefit of local, national and global populations as soon as possible.
For more information on the software, please contact Professor Andrea Rockall at the address [email protected]
[ad_2]
Source link