For the nearly 20,000 women in the US who receive diagnosis of ovarian cancer Every year, artificial intelligence emerges as a potentially life-saving tool.
In a new study led by researchers from the Karolinska Institute in Sweden, AI models did a better job of detecting ovarian cancer than human doctors.
The research, which was published in the journal Nature Medicine, tested the AI model’s ability to distinguish between benign and malignant ovarian lesions, according to a press release.
WHAT IS ARTIFICIAL INTELLIGENCE?
The AI model was trained on more than 17,000 ultrasound images from 3,652 patients at 20 hospitals in eight countries, according to the statement.
“High-quality diagnostics may become more accessible, particularly in regions with limited access to experienced examiners,” said the study’s author. (iStock)
The AI model achieved an accuracy rate of 86% for detection of ovarian cancercompared to 82% for human experts and 77% for those with less expertise.
“I was surprised that the AI models outperformed all 33 experts,” study author Elisabeth Epstein, a professor in the Department of Clinical Science and Education at the Karolinska Institute, told Fox News Digital.
RESEARCHERS FIND PARENTS TRUST AI MORE THAN DOCTORS FOR MEDICAL ADVICE
Ovarian tumors are common and “often discovered incidentally,” according to Epstein.
“Our study shows that Diagnostic support guided by artificial intelligence can significantly improve the diagnosis of ovarian cancer by increasing the efficiency of triage, reducing diagnostic errors and addressing the problem of shortage of specialists,” she said in a statement to Fox News Digital.
The AI model achieved an 86% accuracy rate for detecting ovarian cancer, compared to 82% for human experts and 77% for those with less expertise. (iStock)
“High-quality diagnostics may become more accessible, particularly in regions with limited access to experienced examiners,” Epstein continued.
“This will help reduce waiting times, avoid unnecessary interventions and facilitate earlier detection of cancer, ultimately improving patient outcomes and ensuring more accurate diagnoses.”
AI could also reduce the need for referrals, as well as the chances of misdiagnosis, the researchers noted.
“I was surprised that the AI models outperformed all 33 expert testers.”
dr. Brian Slomovitz, director of gynecologic oncology and co-chair of the Cancer Research Committee at Mount Sinai Medical Center in Florida, noted that screening and early detection of ovarian cancer is the “holy grail” of reducing deaths from the disease.
“This large retrospective trial clearly shows that there may be a role for incorporating artificial intelligence-driven support to better interpret ultrasound findings in patients with a pelvic mass,” Slomovitz, who was not involved in this study, told Fox News Digital.
“This, in itself, increases the accuracy of radiology findings by reducing the rate of false positives (leading to unnecessary surgeries) and by reducing the rate of false negatives (missing cancer cases).”
Screening and early detection of ovarian cancer is the “holy grail” of reducing deaths from the disease, one oncologist has noted. (iStock)
There are other ways of assessment ovarian cancer patients outside of radiological examinations, the doctor noted.
“Menopausal status, presence or absence of symptoms, and blood test results are some of the other factors used to determine which patients may or may not need surgery,” Slomovitz said. “It would be great if these factors could be incorporated into artificial intelligence modeling.”
SIGNS, SYMPTOMS, DIAGNOSIS AND TREATMENT OPTIONS OF OVARIAN CANCER
In addition to demonstrating improved accuracy of ultrasound analysis, AI technology will need to demonstrate a survival benefit to gain widespread use, he added.
“I am optimistic that artificial intelligence will be part of the armamentarium used to improve the care we offer our patients.”
“I am optimistic that artificial intelligence will be part of the armamentarium used to improve the care we offer our patients,” said the oncologist. (iStock)
dr. Harvey Castro, a Based in Dallas, Texas a board-certified emergency medicine physician and national speaker on artificial intelligence in healthcare, agreed that the technology has the potential to improve cancer diagnostics, but cautioned that limitations remain.
CLICK HERE TO SUBSCRIBE FOR OUR HEALTH NEWSLETTER
“AI relies on diverse, high-quality data, and bias could limit effectiveness,” he told Fox News Digital.
“It is also not fully validated for routine clinical use, and issues of transparency and regulation remain unresolved.”
Castro repeated it additional research is needed to determine how well AI adapts to real-world settings, the long-term effect on healthcare costs and outcomes, and whether the technology will be able to cope with different populations and different clinical settings.
For more health articles visit www.foxnews.com/health
The researchers also acknowledged potential limitations of the study.
“It’s not a prospective study, so more data is needed to know how it would work in a real clinical setting,” Epstein told Fox News Digital.
OVARIAN CANCER COULD BE DETECTED EARLY WITH A NEW BLOOD TEST, STUDY SHOWS
The team plans to start clinical studies soon at Stockholm South Hospital in Sweden, she added.
“It is still the doctor who remains responsible for the diagnosis and treatment of the patient.”
Epstein noted that artificial intelligence should only be used as diagnostic support, not as a replacement for human doctors.
“It is still the doctor who remains responsible for the patient diagnosis and treatment“, she said.
CLICK HERE TO DOWNLOAD THE FOX NEWS APP
Karolinska Institutet’s research team collaborated with KTH Royal Institute of Technology. Funding was provided by the Swedish Research Council, Swedish Cancer Society, Stockholm Regional Council, Cancer Research Funds Radiumhemmet and Wallenberg AI, Autonomous Systems and Software Program (WASP), according to a statement.
