Artificial intelligence can predict the time of death
Researchers have now developed a method to calculate the exact time of death of patients. Artificial intelligence is able to analyze important medical records and electronic patient files and thus enable an accurate prediction of the remaining life expectancy.
Scientists at Stanford University have developed an artificial intelligence that can predict the time of death of patients with cancer and other incurable diseases. The so-called deep learning system could lead to groundbreaking developments in palliative medicine in the future. The experts published the results of their study on the document server for preprints "Arxiv".
New developments could improve palliative health care in the future
Standford University researchers have tested a new artificial intelligence algorithm designed to help hospitals improve palliative health care for cancer patients and people with incurable diseases.
The algorithm, which is based on a learning machine from the so-called Deep Neural Network, can analyze important medical records or electronic health records of terminally ill patients. It can then be calculated whether the patients are more likely to benefit from so-called end-of-life care or palliative care.
Predictions are accurate to three to twelve months
The algorithm can predict patient mortality with an accuracy of three to twelve months, and based on this prediction, affected patients can be referred to palliative care.
The predictions could allow clinicians and nurses in palliative care in hospitals to proactively respond to such patients, rather than relying on physician recommendations or performing time-consuming exams.
The wishes of terminally ill people are rarely addressed
Previous studies have shown that around 80 percent of Americans want to spend their last days at home. However, only 20 percent of those affected are able to do this and many die in hospitals. Indeed, terminally ill patients often receive aggressive medical care in their last days, rather than having to address their end-of-life wishes, the experts explain.
These problems are common in palliative care hospitals
The ability of hospitals to provide palliative care has improved in recent years. However, only seven to eight percent of patients receive such care, say the doctors. The lack of palliative care professionals who analyze all patient data and the frequent over-optimism among doctors when it comes to predicting the course of the disease are points that contribute to this problem. This is where the so-called deep learning AI algorithm comes into play.
Mortality prediction model is based on the evaluation of large amounts of data
Based on the amount of data available, we were able to create a predictive model of all-cause mortality, the researchers explain. The learning technique known as deep learning algorithm uses neural networks to filter and analyze a large amount of data.
The prediction of mortality is independent of the type of disease, the age of the patient and other factors. The algorithm used last year's patient data from first contact to determine their mortality within twelve months.
The data sets of two million people were analyzed for the study
For the study, the researchers analyzed two million data sets of adults and children who were admitted to Standford Hospital and Lucile Packard Children's Hospital. The doctors identified a possible 200,000 patients for their study. The participants' electronic patient records were then analyzed by the system to predict their mortality.
The algorithm should then predict the mortality rate of 160,000 patients within 12 months from a specific date. The system was able to improve and learn. The algorithm was then able to predict patient mortality over the next three to twelve months.
Mortality information was accurate in nine out of ten cases
The algorithm then evaluated the data from the remaining 40,000 patients. He was able to accurately predict mortality in three to twelve months in nine out of ten cases. It should be ensured that the most seriously ill patients are given an opportunity to discuss with their families how and where they want to spend their last days before they become so seriously ill that they need to be hospitalized in an intensive care unit, the authors say. (as)