AI Improves Heart Disease Diagnosis

Researchers from the University of Oxford are using artificial intelligence (AI) to improve diagnostic accuracy for heart disease. The team hope to roll out the system across the NHS later this year, helping to improve patient outcomes and saving millions is misdiagnoses. The research, led by Prof Paul Leeson and RDM DPhil student Ross Upton (Cardiovascular Clinical Research Facility), took place in the Oxford University Hospitals Foundation Trust and is the basis of spin-out company Ultromics.

CLICK ON THE IMAGE TO ENJOY THE VIDEO

Thousands of people every year have an echocardiogram – a type of heart scan – after visiting hospital suffering with chest pain. Clinicians currently assess these scans by eye, taking into account many features that could indicate whether someone has heart disease and if they are likely to go on to have a heart attack. But even the most well trained cardiologist can misdiagnose patients. Currently, 1 in 5 scans are misdiagnosed each year – the equivalent to 12,000 patients. This means that people are either not being treated to prevent a heart attack, or they are undergoing unnecessary operations to stave off a heart attack they won’t have.

The new system uses machine learning – a form of artificial intelligence – to tap into the rich information provided in an echocardiogram. Using the new system, AI can detect 80,000 subtle changes inviable to the naked eye, improving the accuracy of diagnosis to 90%. The machine learning system was trained using scans from previous patients, alongside data about whether they went on to have a heart attack. The team hope that the improved diagnostic accuracy will not only improve patient care and outcomes, but save the NHS £300million a year in avoidable operations and treatment.  So far the system has been trialled in six cardiology units in the UK. Further implementation of the technology is now being led by Ultromics – a spin-out company co-founded by Ross Upton and Paul Leeson (Cardiovascular Clinical Research Facility). The software will be made available for free throughout the NHS later this year.

Source: https://www.rdm.ox.ac.uk/

Solar Cell: How To Boost Perovskites Performance

One of the fastest-growing areas of solar energy research is with materials called perovskites. These promising light harvesters could revolutionize the solar and electronics industries because they show potential to convert sunlight into electricity more efficiently and less expensively than today’s silicon-based semiconductors. These superefficient crystal structures have taken the scientific community by storm in the past few years because they can be processed very inexpensively and can be used in applications ranging from solar cells to light-emitting diodes (LEDs) found in phones and computer monitors.
A new study published online in the journal Science by University of Washington (UW) and University of Oxford researchers demonstrates that perovskite materials, generally believed to be uniform in composition, actually contain flaws that can be engineered to improve solar devices even further.
peroskite solar cell
Perovskites are the fastest-growing class of photovoltaic material over the past four years,” said lead author Dane deQuilettes, a UW doctoral student working with David Ginger, professor of chemistry and associate director of the UW Clean Energy Institute.

In that short amount of time, the ability of these materials to convert sunlight directly into electricity is approaching that of today’s silicon-based solar cells, rivaling technology that took 50 years to develop,” deQuilettes said. “But we also suspect there is room for improvement.”

Perovskite solar cells have so far have achieved efficiencies of roughly 20 percent, compared to about 25 percent for silicon-based solar cells. The team found “dark” or poorly performing regions of the perovskite material at intersections of the crystals. In addition, they discovered that they could “turn on” some of the dark areas by using a simple chemical treatment.
Source: http://www.washington.edu/