Google’s AI system can beat doctors at detecting breast cancer
One of the major trends of the 2020s is artificial intelligence increasingly being utilized in healthcare and early patient diagnosis.
Subscribe to the Last Futurist, to read more articles like this.
If in 2019 AI became a political, human rights and trade issue, over the course of the last decade big tech (GAFMA) companies have largely gotten away with data harvesting that have infringed on our privacy rights and made Google seems almost unrecognizable.
Now in 2020, those same companies are going after our healthcare data in the race to become $2 Trillion dollar companies. Alphabet could become one of the dominant global corporations at the intersection of AI and healthcare.
Artificial intelligence tool could reduce the number of false positives in Early Diagnosis
An artificially intelligent Google system could be better at spotting breast cancer than expert radiologists, a new study suggests.
The gist of it is that AI system outperforms experts in spotting breast cancer according to a program developed by Google Health tested on mammograms of UK and US women.
While Google’s own workers said the company’s culture has turned into the opposite of what the founders said they had hoped for, Google’s ambitions in healthcare are immense. Fuelled by some of the foremost deep learning specialists at DeepMind (now with Google Health), Google has an ability to bring predictive analytics into the patient and hospital management experience.
If the program proves its worth in clinical trials, the software, developed by Google Health, could make breast screening more effective and ease the burden on health services such as the NHS where radiologists are in short supply.
This is also an example of AI impacting white-collar jobs, since these systems outperform radiologists, doctors and so forth with greater accuracy and finding clues in the data that could speed up early diagnosis, improve accuracy and lower costs of healthcare.
About one in eight women are diagnosed with breast cancer in their lifetime.
Google’s AI program analyses mammograms in three different ways before combing the results to produce an overall risk score. The scientists trained the program on mammograms from more than 76,000 women in the UK and 15,000 women in the US. To see how well it worked, they then asked it to assess nearly 30,000 new mammograms from UK and US women who either had biopsy-confirmed cancer, or no signs of cancer during follow-up at least a year later.
The early evidence is very promising for AI regarding breast cancer detection. In the US, women who go for breast cancer screening tend to be seen every one or two years and their mammograms are examined by a single radiologist. When compared with the US system, the AI produced 5.7% fewer false positives and 9.4% fewer false negatives.
- The algorithm outperformed six radiologists in reading mammograms. (Link: Nature)
Replacing the Second Radiologist
Why is this a big deal? It can basically replace the second radiologist, which would greatly lower costs while improving accuracy. The results suggest the AI could boost the quality of breast cancer screening in the US and maintain the same level in the UK, with the AI assisting or replacing the second radiologist.
DeepMind has built a team to tackle some of healthcare’s most complex problems—developing AI research and mobile tools that are already having a positive impact on patients and care teams. In the Fall of 2019, they moved to Google Health officially.
- The AI is actually superior at spotting cancer than a single doctor.
- It takes over a decade of training as a doctor and specialist to become a radiologist, capable of interpreting mammograms. It would seem that the demand for such skills could be greatly reduced if this sort of AI becomes better and trained to detect a variety of common cancers and conditions.
Google is showing evidence that its AI will be able to broadly transform the healthcare industry with its superior accuracy that replaces some of the tasks of human doctors and specialists.
However we must be cautious, this was a research study, and as yet the AI system has not been let loose in the clinic. It’s showing Google is pioneering the impact of deep learning on early diagnosis as this breast cancer study was not an isolated case.
Healthcare is a $3 Trillion dollar industry and the impact could be real from Alphabet. This can also save lives.
Radiologists miss about 20 per cent of breast cancers in mammograms, the American Cancer Society says, and half of all women who get the screenings over a 10-year period have a false positive result.
The clear-cut solution of all of this is that AI could largely do away with the need for dual reading of mammograms by two doctors, easing pressure on their workload, say researchers. In recent years there’s been increasing evidence of the impact of machine intelligence on white-collar skills, and the medical, law and finance fields are also open to disruption as are the retail, transportation and logistics industries, just by different smart technologies.
As Google Health matures we’ll be able to say more on Google’s own impact on the future of healthcare, but along with Apple and Amazon, it appears to be significant especially in the 2025 to 2035 period. It’s still obviously very early days.
Professor Ara Darzi, one of the authors of the paper and the director of the Cancer Research UK Imperial Centre, said he had not expected to see such an impressive result from the AI system.
“This went far beyond my expectations. It will have a significant impact on improving the quality of reporting, and also free up radiologists to do even more important things.”
What do you think of the impact of AI on healthcare, can it reduce workloads of hospital staff, doctors and nurses and reduce the costs of healthcare globally? And which professionals could be impacted? Share your view in a comment below.