Google has announced a new medical partnership with British doctors related to machine-learning technologies.
Recently it was announced that Google’s DeepMind subsidiary will partner with doctors at the Moorfields Eye Hospital in London, with staff researching whether machine-learning technology could assist in making the diagnosis of eye conditions faster. In a new announcement from DeepMind it has been revealed that the partnership will be extended to the National Health Service (NHS).
DeepMind announces partnership NHS trust
The Google subsidiary will enter into a partnership with the University College London Hospitals (UCLH) NHS Foundation Trust, with the aim of planning treatments for oral cancer. When radiotherapy is used to treat cancer, it has to be carefully designed.
Gates Capital Management's ECF Value Funds have a fantastic track record. The funds (full-name Excess Cash Flow Value Funds), which invest in an event-driven equity and credit strategy, have produced a 12.6% annualised return over the past 26 years. The funds added 7.7% overall in the second half of 2022, outperforming the 3.4% return for Read More
This is particularly true when treatment involves the head and neck. Radiotherapy is used to kill cancerous cells, but surrounding cells can also be affected. In the head and neck it is especially important not to damage the nerves and organs around cancerous cells.
The partnership between UCLH and DeepMind will research whether machine learning technology can assist in cutting the amount of time needed to plan such treatments. More specifically the teams are hoping to reduce the time needed to carry out a process known as “segmentation,” in which doctors make a detailed map of areas that require treatment.
Technology could cut planning time
Machine learning technology is one way of defining the process of training computers to learn certain things from data which is fed to them. This will eventually allow them to draw their own conclusions from information without the help of a human being.
The technology is already in use in areas like image-tag suggestions on Facebook and Gmail spam filters. In this instance the technology will involve DeepMind systems working with anonymized oral cancer scans from up to 700 former UCLH patients.
“Clinicians will remain responsible for deciding radiotherapy treatment plans but it is hoped that the segmentation process could be reduced from up to four hours to around an hour,” DeepMind said in a statement.
If clinicians are able to provide more precise radiotherapy, it can reduce side effects. This is one aim of the project.
“Using computers to help plan radiotherapy could help deliver better treatment for patients by speeding up the process and improving accuracy,” said Dr Justine Alford, senior science information officer at Cancer Research UK. “But we won’t know until results from this innovative new project are produced.”
The use of anonymized scans should come as no surprise in these two latest projects. In April it was revealed that DeepMind had been granted access to non-anonymized healthcare data from around 1.6 million people who received treatment from the Royal Free NHS Trust in London. The data was handed over without public knowledge.
That particular deal was supposed to help in building an app called Streams, which would improve the monitoring of kidney disease patients. However after the story broke the app was taken out of use by the hospitals in the trust. The app had not been cleared by the Medicines & Healthcare Products Regulatory Agency (MHRA) for use as a medical device.
The deal between DeepMind and the Royal Free is now under investigation by the Information Commissioner’s Office, which is the U.K.’s national data protection authority, and the National Data Guardian, which works with health and social care.
In the United States the Google cloud is also used by cancer researchers.