Researchers at the University of Adelaide, Australia, have developed an Artificial Intelligence software which can predict how long a patient will live much accurately after analyzing photos of the person’s organs.
This artificial intelligence was used to analyze the medical imaging of 48 patients’ chests. This AI examination was able to predict which patients would die within five years, with 69% precision – comparable to ‘manual’ predictions by clinicians.
The most confident predictions were made for patients with critical chronic diseases such as congestive heart failure and emphysema.
How does this technology work?
The technology uses deep learning principles to search CT scans for signs of disease. Deep learning programs can represent results based on large repositories of data previously filled into them. And this deep learning system was prepared to examine over 16,000 image characteristics that could show indications of disease in the organs.
This is the first study of its kind using medical images and artificial intelligence
“Instead of focusing on diagnosing diseases, the automated systems can predict medical outcomes in a way that doctors are not trained to do, by incorporating large volumes of data and detecting subtle patterns,” a radiologist and Ph.D. student with the University of Adelaide’s School of Public Health.
The study has strong implications for personalizing treatment. It could help in predicting how a disease will progress as well as estimating struggles to stop progression.
“Predicting the future of a patient is useful because it may enable doctors to tailor treatments to the individual,” Oakden-Rayner said.
The researchers expect to use the same methods to predict other significant medical conditions, Like the start of heart attacks.
The next step of their study includes examining 20,000 to 100,000 of patient images.