The AI ​​is FOUR TIMES more effective in predicting the risk of death of a patient with ovarian cancer



The AI ​​is FOUR TIMES more effective at predicting the risk of death of an ovarian cancer patient than existing CT scans.

  • Evaluates the size, structure and DNA of a tumor to predict the patient's prognosis
  • Could even help doctors choose the best treatment for the individual
  • Analyzes how similar growths have responded to chemotherapy or surgery in the past

Research suggests that AI is four times more effective in predicting the risk of death of a patient with ovarian cancer than existing scanners.

One study found that an artificial intelligence model assessing the structure of a tumor and its genetic makeup better predicts the patient's prognosis than the methods currently used by physicians.

The technology could even help doctors choose the best treatment for a patient by analyzing how similar growths have responded to chemotherapy or surgery in the past.

The researchers say that AI has "the potential to transform the way health care is delivered and improve outcomes for patients."

The AI ​​is four times more effective in predicting the risk of death of an ovarian cancer patient than the existing CT scans used by doctors, according to a study (stock)

The AI ​​is four times more effective in predicting the risk of death of an ovarian cancer patient than the existing CT scans used by doctors, according to a study (stock)

The research was conducted by Imperial College London and directed by Professor Eric Aboagye, of the Faculty of Medicine of the Department of Surgery and Cancer.

"The long-term survival rates of patients with advanced ovarian cancer are poor despite advances in the treatment of cancer," said Professor Aboagye.

"There is an urgent need 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."

Ovarian cancer affects about 7,300 new women each year in the UK, according to ovarian cancer statistics.

And in the United States, 22,530 women are diagnosed each year with the disease, according to the American Cancer Society.

Although 90% of sufferers live at least five years old if cancer is diagnosed at an early stage, vague symptoms – bloating, loss of appetite, and abdominal pain – mean that it often goes unnoticed.

To check if AI could help with ovarian cancer management, the researchers entered CT and tissue sample data into a mathematical software program called TEXLab.

This information was collected from 354 patients who fought the disease between 2004 and 2015.

Ovarian cancer is currently diagnosed via a blood test that looks for a substance called CA125, followed by a scan showing the details of the tumor.

This helps doctors to know how far the disease has spread and determines the type of treatment that patients should receive.

However, the analysis does not give a detailed overview of the likely results of a patient or the most effective treatment.

TEXLab examined the structure, shape, size, and DNA of tumors – four features that significantly influence patient survival and give an indication of their prognosis.

The patients then received a score, known as the Radiologic Prognostic Vector (RPV), which indicates the severity of the disease.

The results – published in the journal Nature Communications – were compared with existing blood tests and prognostic scores used by physicians.

The software was not only four times more accurate in assessing patient survival, but the team also found that only 5% of patients with a high PVR score had a survival rate of less than two years.

High VPR was also associated with poor response to chemotherapy and surgery.

This suggests that PRV could be used to predict how patients will respond to treatment.

Professor Andrea Rockall, co-author of the Chair of Clinical Radiology, added, "Artificial intelligence has the potential to transform the way health care is delivered and improve outcomes for patients.

"Our software is an example of this and we hope it can be used as a tool to help clinicians better manage and treat ovarian cancer patients."

More important studies need to be conducted to determine how accurately TEXLab can predict the outcome of surgery and drug treatments in each patient.

Why ovarian cancer is called a "silent killer"

About 80% of ovarian cancer cases are diagnosed at advanced stages of the disease.

At the time of diagnosis, 60% of ovarian cancers have already spread to other parts of the body, bringing the five-year survival rate from 90% to 30% at the early stage.

The diagnosis is so late because it is in the pelvis, according to Dr. Ronny Drapkin, an associate professor at the University of Pennsylvania, who has been studying the disease for more than two decades.

"The pelvis is like a bowl, so a tumor can become quite big before it becomes noticeable," Dr. Drapkin told Daily Mail Online.

The first symptoms of ovarian cancer are gastrointestinal because tumors can start to pressurize.

When a patient complains of gastrointestinal discomfort, doctors are more likely to focus on diet changes and on other causes than to suggest ovarian cancer screening.

Dr. Drapkin said that it is usually only after a patient has suffered persistent gastrointestinal symptoms that he undergoes screening revealing cancer.

"It is often said that ovarian cancer is a silent killer because it has no early symptoms, whereas in fact, it has symptoms, they are simply very and could be caused by other factors, "he said.

"One of the things I tell women is that no one knows your body as well as you do. If you feel that something is wrong, something is probably not right. & # 39;


Source link