Being a search engine used by around 1.17 billion users, Google perhaps has every information under the sun and beyond.
Now, it might also know when you will die. Google's Medical Brain team claims that feeding electronic health record data to a deep learning model could substantially improve the accuracy of projected outcomes.
The team is said to be training an artificial intelligence (AI) computer system that is 95 per cent accurate in predicting whether hospital patients will die 24 hours after admission. If the reports are to be believed, the AI system is around 10 per cent more accurate than traditional models or a hospital's own warning system. The tool can also predict a host of patient outcomes - such as how long they will stay in hospitals, their odds of re-admission and the death risk probabilities.
The neural network described in the study uses an immense amount of data, such as a patient's vitals and medical history, to make its predictions. An algorithm creates a timeline based on patient's previous records and uses it to predict the future outcomes, including the death. According to the journal Digital medicine, where the findings of the study were published, "This was significantly more accurate than the traditional predictive model.
These models outperformed traditional, clinically-used predictive models in all cases. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios."
The obvious question that arises in mind is that there is nothing one can do rather than getting stressed about inevitable. However, the productive side of AI system is that hospitals could find new ways to prioritise patient care, adjust treatment plans, and catch medical emergencies before they even occur