Share:
Lifetimes Can an AI predict the death of patients?
From the very beginning of humanity, the question arises whether there is a way to predict our life expectancy. Researchers developed an artificial intelligence capable of evaluating images of organs and thereby predicting the approximate time of death.
Researchers at the University of Adelaide found in their study that newly developed artificial intelligence is able to predict our remaining life expectancy. The experts published a press release on the results of their study.
Most diseases of the organs are extremely difficult for doctors to recognize. An artificial intelligence is now able to analyze images of organs and thereby detect serious diseases early on. In addition, this artificial intelligence can also predict the remaining life span of the patient. (Image: sakkmesterke / fotolia.com) Prediction accuracy of 69 percent
Computer-based analysis was able to predict with 69 percent accuracy which patients would die within the next five years, compared to predictions from experts, according to the University of Adelaide.
Prediction may have an impact on the early detection of serious illness
By computer-aided evaluation of scans of the organs, it was possible to calculate the remaining life of the patient relatively accurately, say the authors. This is another step in the direction of artificial intelligence that can predict the exact time of death of humans. Such a prediction could have an impact on the early detection of serious illnesses and the subsequent treatment in the future, explain the physicians. However, the question remains whether it is really desirable to know his own time of death.
Biological age and longevity usually difficult to estimate
Predicting the future of a patient is useful because it allows physicians to optimize personalized treatment for individuals, the researchers explain. The exact assessment of the biological age and the prediction of the longevity of a patient remain so far limited, since there are limited opportunities to look into the human body and to measure the health of the organs, the experts add.
Computer learns to recognize the complex imaging phenomena of diseases
The current study used a technique that allows artificial intelligence to learn exactly how to analyze and evaluate images. Luke Oakden-Rayner of the University of Adelaide's School of Public Health. Although only a small sample of patients has been studied for this study, the computer has learned to recognize the complex imaging pathologies of diseases, the researchers say. This actually requires extensive training from human experts.
Artificial intelligence is not just focused on diagnosing disease
What exactly the computer system in the images must analyze for its predictions, is still unclear, explain the researchers. Most predictions have been made for patients with severe chronic diseases, such as emphysema and congestive heart failure. Instead of focusing on diagnosing disease, however, the automated systems can also predict medical outcomes in ways that normal physicians are not trained to do, explain the experts. To do this, the computers involve a very large amount of data and capture subtle patterns, according to author Dr. med. Oakden-Rayner continues.
Breakthrough in the detection of serious diseases?
Our research opens new avenues for the application of artificial intelligence technology in medical image analysis, says the expert. This could make a breakthrough in the detection of serious illnesses and enable treatment through specific medical interventions, hope the scientists. The same technique may also be used in the future to predict other important medical events, such as heart attacks. (As)