Developments in the field of artificial intelligence (AI) are happening at a staggering rate. Earlier, we saw how a ‘robot scientist’ helped scientists in discovering a key compound that could be used in developing a malarial drug which is resistant to the drugs available in the market. And now, researchers are using an advanced artificially intelligent system to predict the “death” of terminally ill patients.
A team of researchers from the Stanford University has tested a new AI algorithm that can help hospitals in predicting the mortality of patients from three to 12 months and use this prediction to refer patients for end-of-life care or palliative care.
How does the ‘death calculator’ work?
Stanford’s AI algorithm relies on ‘deep learning’, a machine learning technique that uses neural networks to learn from large amounts of data, to calculate patient mortality.
The deep learning algorithm– Deep Neural Network– is trained on the Electronic Health Record data of nearly 2 million adults and children admitted to either the Stanford Hospital or Lucile Packard Children’s hospital to predict their mortality in next three to 12 months. The good news is that it can do so with a precision of 90 percent.
ALSO READ: WTF is Artificial Intelligence!
How will it improve the quality of palliative care?
Previous studies have shown that nearly 80 percent of the American would like to spend their final days at home. Despite the availability of best health-care facilities, only 20 percent people get to do so. Also, only seven to eight percent people who need palliative care treatment get it.
The reason for this, as the Stanford researchers point out are several which include over-optimism of the physician, time pressure, treatment inertia, and the shortage of palliative care professionals.
“We demonstrate that routinely collected EHR data can be used to create a system that prioritizes patients for follow up for palliative care. In our preliminary analysis we find that it is possible to create a model for all-cause mortality prediction and use that outcome as a proxy for the need of a palliative care consultation,” the study indicated.
“Our predictions enable the Palliative Care team to take a proactive approach in reaching out to such patients, rather than relying on referrals from treating physicians, or conduct time-consuming chart reviews of all patients,” the study added.
While the resulting model is currently being piloted for daily and proactive outreach to newly admitted patients in the United States, a similar model, wherein AI is used to access and prioritize the need for end-of-life care and palliative care options for patients, can be used in India and other countries as well.