Artificial Intelligence is better at diagnosing breast cancer than human doctors. That’s the conclusion of a new study published in the journal Nature. For the research, an international team, including representatives from Google Health and Imperial College London, used anonymous X-ray images of 29,000 women to train a computer model so that it could spot breast cancer. When put to the test against six radiologists in reading mammograms, the algorithm came out on top. In fact, it was even proven to be as good as two doctors working together – the current system for assessing mammograms. And unlike the human experts who had access to the patients’ medical history, the AI had just the X-rays to go on. Specifically, the AI resulted in a reduction of 1.2% in false positives - when a mammogram is incorrectly diagnosed as abnormal – and a 2.7% reduction in false negatives, where a cancer is missed. While we’re not likely to see AI being used to diagnose or clear breast cancer patients any time soon, the technology could be used to assist radiologists and speed up diagnoses going forward. Speaking about the findings of the research, Dominic King, from Google Health, said: “Our team is really proud of these research findings, which suggest that we are on our way to developing a tool that can help clinicians spot breast cancer with greater accuracy.”
New research suggests cancer patients are at higher risk of dying from cardiovascular disease than the general population. According to the study, the results of which are published in the European Heart Journal, more than one in 10 cancer survivors die from heart and blood vessel problems, rather than their initial illness. Among the 3,234,256 cancer patients studied for the research, 38% died from cancer, while 11% died from cardiovascular diseases. Among the deaths from cardiovascular diseases, 76% were due to heart disease. The risk of dying from cardiovascular disease was also highest in the first year after a patient’s cancer diagnosis and among patients younger than 35. Among those cancer patients diagnosed before the age of 55 and who went on to survive their illness, the risk of dying from cardiovascular disease was more than 10 times higher than that for the general population. Meanwhile, patients with breast, prostate or bladder cancer were most likely to die from heart disease – but this is simply because these are the most common types of cancer. It is still unclear as to why cancer patients have a seemingly higher risk of heart disease, but their treatment itself or lifestyle factors, such as being overweight, drinking too much and not exercising, could be to blame, experts say.
Hundreds of men in the UK are trialling a new prostate cancer screening scan to see if it could eventually be offered on the NHS. Right now, there is no routine prostate cancer screening performed in the UK. Blood tests and biopsies are the most reliable ways to determine if a man has prostate cancer. The new test involves a non-invasive MRI scan that checks the inside of the body for any abnormal growths. It will be a few years yet before we know if the new scan is better than the current blood tests, scientists say, but NHS England is, nevertheless, hailing the breakthrough as a “potentially exciting development”. In the UK alone, prostate cancer claims the lives of around 11,800 men every year. It usually develops slowly, so there are often no associated signs or symptoms for many years. Prostate cancer treatment depends on its development. Doctors may suggest to monitor the situation first, while surgery and radiotherapy will be advised for others. Speaking about the new test, Karen Stalbow, from Prostate Cancer UK, said: “This trial could provide an exciting step towards our ambition for a national screening programme that enables men to get the early prostate cancer diagnosis that can save more lives.”
A US study suggests that Artificial Intelligence (AI) is better than specialist doctors at identifying lung cancer. It’s a finding that could revolutionize cancer screening in the future, potentially allowing tumors to be found at an earlier stage and improving treatment outcomes. According to the study - which was conducted by researchers from Northwestern University in Illinois and the Google Health Research Group – Artificial Intelligence was able to outperform six specialist cancer doctors when it came to identifying cancer from a single CT scan. When multiple CT scans were used, the AI and the doctors were equally effective. Prior to the tests, the AI was trained with 42,290 CT lung scans from nearly 15,000 patients. It was not told what to look for in a CT scan, merely which patients went on to develop cancer and which didn’t. The results of the study, published in Nature Medicine, show that AI can not only boost cancer detection by 5%, but can also reduce false-positives by 11%. Speaking about the findings of the research, Dr Mozziyar Etemadi, from Northwestern University, said: “Not only can we better diagnose someone with cancer, we can also say if someone doesn't have cancer, potentially saving them from an invasive, costly, and risky lung biopsy.”
Ovarian cancer treatment is much more effective if it’s administered during the early stages of the disease. In fact, when ovarian cancer is diagnosed early, approximately 94% of patients have a good prognosis post-treatment. However, the reality is that relatively few cases (about 20%) of ovarian cancer are diagnosed early, which makes treatment less effective. But a newly developed blood test could change this. Beyong a full pelvic exam, medical professionals, at present, have two options when it comes to testing for ovarian cancer: a transvaginal ultrasound and a cancer antigen 125 (CA 125) blood test. Unfortunately, both have significant limitations. For example, while the ultrasound can detect growths, it cannot determine whether they are cancerous. The CA 125 test looks for a specific ovarian cancer marker, but people with unrelated conditions also have high levels of this particular antigen. These limitations of the existing tests are one of the driving forces behind the development of the new blood test. The new test, developed by a team from Griffith University and the University of Adelaide (both in Australia), looks for telltale sugars associated with ovarian cancer cells. According to the findings of the team’s study, the new blood test detected large levels of the sugars in 90% of people with stage 1 ovarian cancer and 100% of people with later stage ovarian cancer. Moreover, the test detected none of the telltale sugars in healthy participants. Prof. James Paton, one of the study authors, said the test is a huge step toward diagnosing ovarian cancer in its early stages. “Ovarian cancer is notoriously difficult to detect in its early stages, when there are more options for treatment and survival rates are better. Our new test is therefore a potential game-changer,” he said.
NHS England is in the process of introducing ‘one-stop cancer shops’ across the country, the aim of which is to afford quicker diagnoses for patients. At present, patients often face delays as they are sent for several tests to check for different forms of the illness. Despite cancer survival rates having increased over recent decades, patients who do not display obvious signs of cancer often face treatment delays. For example, individuals who have experienced unexplained weight loss, reduced appetite or abdominal pain can be referred several times for different tests, which delays valuable opportunities to begin treatment. The approach NHS England is now adopting was first introduced in Denmark and allows patients to undergo all the necessary tests under one roof. Cally Palmer, national director for cancer at NHS England, said: "Early diagnosis is crucial to saving lives and providing peace of mind for patients, which is why we are driving forward plans to revolutionise our approach to cancer in this country. "These new one-stop shops represent a real step change in the way people with unclear symptoms are identified, diagnosed and treated." The bottom line is that the rapid diagnosis and subsequent fast treatment of cancer is vital for saving lives. Initially, there will be 10 such centres spread across England at the following locations: Royal Free Hospital, London North Middlesex Hospital, London, University College Hospitals London Southend University Hospital Queens Hospital, Romford St James University Hospital, Leeds Airedale General Hospital, West Yorkshire University Hospital, South Manchester Royal Oldham Hospital, Greater Manchester Churchill Hospital, Oxford More centres will be added if the project is a success.