The latest trends in artificial intelligence highlight how algorithms can predict patient mortality almost 69% of the time. The use of artificial intelligence in predicting mortality might enable doctors to tailor treatment for an individual based on his/her lifespan.
So you think that robots are best suited for menial jobs? You couldn’t be far from wrong. The research in artificial intelligence (AI) has moved to an all-new level with scientists at the University of Adelaide in Australia announcing that robots can predict mortality. By analysing CT scans from 48 patients, the deep learning algorithms could predict whether they would die within five years with 69% accuracy, which is broadly similar to the scores from human diagnosticians, the paper says. It will open up new avenues for the application of AI in medical image analysis, offering hope for early detection of serious illness that requires specific medical interventions.
AI in healthcare involves using algorithms and software for the analysis of complex medical data. With the current shortage of seven million physicians, nurses and other health workers worldwide, AI comes as a blessing. The primary aim of AI applications in healthcare is to analyse the complex relationships between prevention and treatment techniques. In the traditional set-up, a patient, when unwell, visits a physician who checks his/her vitals, asks questions and prescribes medicines. A large chunk of clinical and outpatient services can now be handed over to AI assistants.
The use of AI in predicting mortality may enable doctors to tailor treatments for an individual based on their lifespan. When AI comes into the picture, medical outcomes will be predicted in a way that doctors are not trained to do. The automated systems will incorporate large volumes of data to detect subtle patterns.
The algorithms become even more accurate as a person’s suicide attempt gets closer. For example, the accuracy climbs to 92% one week before a suicide attempt when AI focuses on general hospital patients. The traditional risk factors identified over the past half-century to predict suicidal behaviour—such as depression, stress or substance abuse—could muster an accuracy rate not much better than random guessing.