[ad_1]
A new software tool has been shown to be four times more reliable than current methods for predicting prognosis in patients with ovarian cancer. The tool was also able to predict the most effective treatment for patients once they had been diagnosed.
Fantasy Studio | Shutterstock
Ovarian cancer is the sixth common cancer in women and affects mainly menopausal women or those with a family history of the disease.
The long-term survival rate is only 35 to 40%, because cancer is often diagnosed only at an advanced stage, once the symptoms have already begun to manifest themselves. The ability to detect ovarian cancer at an early stage of the disease is urgent and could improve patient survival rates.
Currently, the diagnosis of ovarian cancer involves a blood test for a substance called CA125 (a cancer indicator) and a CT scan that generates detailed images of ovarian tumors. These tests can help doctors determine the extent of cancer spread and whether a patient can benefit from surgery or chemotherapy, for example. However, these tests do not reliably indicate the effectiveness of this treatment or the chances of survival.
As reported in the newspaper Nature Communications, researchers at Imperial College London and the University of Melbourne used mathematical software to badess tumor aggressiveness using CT scans and tissue samples from 364 patients with bad cancer. the ovary between 2004 and 2015.
The software evaluated four characteristics of the tumor (structure, size, shape, and genetic constitution) known to affect patient survival. This generated a score called the Radiologic Prognostic Vector (RPV) which serves as an indicator of the severity of the disease.
By comparing the PVR score to the blood test results and prognostic scores currently used by physicians, the team found that it was up to four times more reliable in predicting the patient's death. He was also able to reliably identify the 5% of patients who would generally survive only two years.
Early identification of these patients allowed the team to better determine the most effective treatment and improve the prognosis.
According to researchers, this technology could help clinicians optimize treatment earlier and create a more personalized therapeutic approach:
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. "
Professor Andrea Rockall, co-author
Source:
Lu, H. et al. A mathematical descriptor of the mesoscopic structure of the tumor from computerized tomography images annotates the prognostic and molecular phenotypes of epithelial ovarian cancer. Nature Communications. February 15, 2019.
[ad_2]
Source link
