Big data will predict your death
- Autore:Ella Cai
- Rilasciare il:2017-06-02
Artificial intelligence has analysed CT scans of the organs in the chests of 48 patients, and predicted who would die within five years with 69% accuracy – comparable to predictions by clinicians, according to the University of Adelaide which led the research.
The most confident predictions were made for patients with severe chronic diseases such as emphysema and congestive heart failure
“Although for this study only a small sample of patients was used, our research suggests that the computer has learnt to recognise the complex imaging appearances of diseases, something that requires extensive training for human experts,” said Dr Luke Oakden-Rayner.
A ‘deep learning’ technique was used, and the researchers have not identified exactly what the computer system was seeing in the images to make its predictions. “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,” said Oakden-Rayner.
The next stage of their research involves analysing tens of thousands of patient images, and the team hopes to apply the same techniques to predict other medical conditions, such as the onset of heart attacks.
“Predicting the future of a patient is useful because it may enable doctors to tailor treatments to the individual,” said Oakden-Rayner,
The most confident predictions were made for patients with severe chronic diseases such as emphysema and congestive heart failure
“Although for this study only a small sample of patients was used, our research suggests that the computer has learnt to recognise the complex imaging appearances of diseases, something that requires extensive training for human experts,” said Dr Luke Oakden-Rayner.
A ‘deep learning’ technique was used, and the researchers have not identified exactly what the computer system was seeing in the images to make its predictions. “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,” said Oakden-Rayner.
The next stage of their research involves analysing tens of thousands of patient images, and the team hopes to apply the same techniques to predict other medical conditions, such as the onset of heart attacks.
“Predicting the future of a patient is useful because it may enable doctors to tailor treatments to the individual,” said Oakden-Rayner,
