Researchers are now using the power of artificial intelligence to predicts if a patient will live longer or is soon to knock on death’s door. They are hopeful that this could help them in many ways such as a way to slash number of unexpected death in the US and offer better end-of-life care, amongst others.
In two separate developments, Stanford University and Excel Medical have developed AI that helps in predicting death.
In one of the developments by Stanford University, they are developing AI to help physicians screen for newly admitted patients who could benefit from talking about palliative care choices. According to a research paper cited by the Stanford group titled “Improving Palliative Care with Deep Learning” published on the arXiv preprint server, up to 60 percent of Americans end up dying in an acute care hospital while receiving aggressive medical treatments.
The AI algorithm by Stanford relies on deep learning, that uses neural networks to filter and learn from huge amounts of data. The deep learning algorithm has been trained with about 2 million adult and child patients admitted to either the Stanford Hospital or Lucile Packard Children’s hospital to predict the mortality of a given patient within the next three to 12 months.
Over 100,000 people subscribe to our newsletter.
See stories of Analytics and AI in your inbox.
“We could build a predictive model using routinely collected operational data in the healthcare setting, as opposed to a carefully designed experimental study,” says Anand Avati, a PhD candidate in computer science at the AI Lab of Stanford University. “The scale of data available allowed us to build an all-cause mortality prediction model, instead of being disease or demographic specific.”
The institute says that they want to make sure that the sickest patients and their families should get a chance to talk about what they want to happen before they become critically ill and they end up in the ICU, this AI is aimed towards achieving that.
Stanford University had earlier also developed an AI that identifies skin cancer from images, as accurate as doctors.
In another development, Excel Medical, a medical tech company tech company in Florida, has created an algorithm that can accurately predict if medical patients could be at risk of a sudden, unexpected death.
The company explains that it consists of integrated system of hospital workstations and digital medical records that includes real time data on their physiology, past medical history, family history, age, medications etc. AI can automatically calculate the risk of patient deterioration up to six hours in advance, based on these parameters. It can inform doctors if it detects anything suspicious, through a smartphone app.
This AI platform by the company has become the first of its kind to be approved by the FDA. The decision was based on a series of studies at the University of Pittsburgh Medical Center that showed the AI platform could prevent unexpected deaths in hospitals.
Lance Burton, General Manager of Excel Medical said in a statement that everything they do as an organisation aligns toward and supports the goal of eradicating unexpected deaths in hospitals. “People may say zero unexpected deaths is unattainable. We say anything other than zero is unconscionable”, he said.
The company, that eventually aims to make AI wearable devices usable for people at home, plans to implement this technology in hospitals as of now.