A new artificial intelligence-powered system created by Google is able to predict, with amazing accuracy, if a patient will die within 24 hours from the time of admission into a hospital.
Google is one of the world's pioneers in AI research, with its DeepMind subsidiary recently able to create a computer that can generate 3D models by looking at 2D images. The latest artificial intelligence project by Google, however, is focused on the technology's applications on healthcare.
Google AI Predicts Death At 95 Percent Accuracy
The research that was published by Google in May included an anecdote of a woman suffering from late-stage breast cancer who went to a hospital with her lungs flooded by fluids. After seeing two doctors and undergoing a radiology scan, the hospital's computers estimated a 9.3 percent chance that she would die during her stay.
A new Google artificial intelligence algorithm, meanwhile, took a look at nearly 176,000 data points of the woman, and released an assessment of a 19.9 percent risk of death. The woman died in a matter of days.
The research, highlighted the potential of artificial intelligence in healthcare, particularly neural networks which are adept at automatically learning and improving from data. Google used this form of AI to create a tool that forecasts the outcomes for patients, including how long they might stay confined in a hospital, the chances of readmission, and their death risk.
The accuracy of the Google AI in predicting whether a patient will die within 24 hours after admission is as high as 95 percent, which is 10 percent more accurate than models that the healthcare industry is currently using.
The AI is able to analyze previously out of reach data, such as notes scribbled on charts or buried in PDFs. The neural network had no trouble digesting all the information to make the best predictions possible, which came faster and more accurate compared to traditional methods.
AI In Healthcare
Artificial intelligence technology has seen its fair share of applications in the healthcare industry. For example, the United Kingdom's National Health Service is considering the use of AI-powered robot medics, named carebots, which can be deployed to both private homes and hospitals.
Stigma still surrounds artificial intelligence, due to the technology's portrayal in science fiction movies and recent developments such as the creation of the world's first psychopath AI. However, artificial intelligence has a lot to offer to the healthcare industry, with the potential to save thousands of lives in the future.