The daily email that arrived in physician Samantha Wang's inbox at 8 a.m., just before morning rounds, contained a list of names and a warning: These patients are at high risk of dying within the next year. One name that turned up again and again belonged to a man in his 40s, who had been admitted to Stanford University's hospital the previous month with a serious viral respiratory infection. He was still much too ill to go home, but Wang was a bit surprised that the email had flagged him among her patients least likely to be alive in a year's time. This list of names was generated by a machine, an algorithm that had reached its conclusions by scanning the patients' medical records. The email was meant as something of a nudge, to encourage Wang to broach a delicate conversation with her patient about his goals, values, and wishes for his care should his condition worsen.

Earlier this month the University of Nottingham published a study in PloSOne about a new artificial intelligence model that uses machine learning to predict the risk of premature death, using banked health data (on age and lifestyle factors) from Brits aged 40 to 69. This study comes months after a joint study between UC San Francisco, Stanford, and Google, which reported results of machine-learning-based data mining of electronic health records to assess the likelihood that a patient would die in hospital. One goal of both studies was to assess how this information might help clinicians decide which patients might most benefit from intervention. Amitha Kalaichandran, M.H.S., M.D., is a resident physician based in Ottawa, Canada. Follow her on Twitter at @DrAmithaMD.

I don't know how self-driving car technology ranks on a difficulty scale. Perhaps it's not as difficult as rocket science, but it still must be very hard. Add to that the challenge of programming a self-driving car to make moral decisions. Take for example the MIT Media Lab experiment called "The Moral Machine," which was "designed to test how we view…moral problems in light of the emergence of self-driving cars." If a self-driving car were in a'moral bind' in which it would have to hit either an elderly person, a child or a pet to avoid the others, what should it do?

The means to predict mortality using artificial intelligence could be a transformative factor in the future of palliative health care. While this topic may seem a bit morbid, AI has the potential to help medical care providers and doctors significantly improve the delivery of patient care in hospice situations. Getting the right kind of treatment at the end-of-life stage is more important than many assume. Not enough treatment -- or even inaccurate treatment -- can provide a painful experience for patients, and overcare may result in hundreds of thousands of dollars in unnecessary medical bills, even if the patient is covered by insurance. While it's crucial to select the proper medical coverage that includes hospice care regardless of the situation -- especially for people over 65 or older, because there are specific plans for specific purposes to help with these medical costs -- AI advances may help patients and physicians determine illness sooner to prepare for end-of-life costs and treatments before it's too late.

In this work, we characterize the doctor-patient relationship using a machine learning-derived trust score. We show that this score has statistically significant racial associations, and that by modeling trust directly we find stronger disparities in care than by stratifying on race. We further demonstrate that mistrust is indicative of worse outcomes, but is only weakly associated with physiologically-created severity scores. Finally, we describe sentiment analysis experiments indicating patients with higher levels of mistrust have worse experiences and interactions with their caregivers. This work is a step towards measuring fairer machine learning in the healthcare domain.

When patients receive a terminal cancer diagnosis, they are often given a frustratingly vague sense of how much time they have left. "You've got x months/years to live," they're typically told, a sentiment aimed at allowing patients to get their lives in order, maybe even live their last days with aplomb. But physicians are human, and forecasting like this is wrought with not only errors but also the pain of planning for a death that may or may not happen in the given time frame. In many cases--partially because the awkwardness of having to communicate that the end of a patient's life looms near, and partially because humans are not good at predicting--the end-of-life time frame is off, forecasted to be way more in the future than it actually is. That leaves some patients scrambling to stitch together end-of-life care, and makes what was supposed to be as comfortable and peaceful a process as possible actually more stressful and wretched.

Humans today live a lot longer than they used to. That's great news, but as modern medical advances are giving patients second chances at living normal lives, end-of-life care continues to be a difficult thing to plan. Forecasting when someone will die is an extremely challenging and often uncomfortable thing, but Stanford researchers have trained an AI to be able to predict death with incredible accuracy, and it could revolutionize end-of-life care for patients who are reaching their ends. The goal is to better match patient (and family) wishes with an accurate timeline of an individuals final months, weeks, and days, while affording them the opportunity to plan ahead for the inevitable. The work is titled Improving Palliative Care with Deep Learning, and it's currently available online.

By using an artificially intelligent algorithm to predict patient mortality, a research team from Stanford University is hoping to improve the timing of end-of-life care for critically ill patients. In tests, the system proved eerily accurate, correctly predicting mortality outcomes in 90 percent of cases. But while the system is able to predict when a patient might die, it still cannot tell doctors how it came to its conclusion. Doctors must consider an array of complex factors, ranging from a patient's age and family history to their response to drugs and the nature of the affliction itself. To complicate matters, doctors have to contend with their own egos, biases, or an unconscious reluctance to assess a patient's prospects for what they are.

End of life care might be improved with Deep Learning. An AI program in a successful pilot study predicted how long people will live. George Dvorsky in Gizmodo and others reported on their work. The Stanford University team is using an algorithm to predict mortality, and their goal is to improve timing of end-of-life care for critically ill patients. While 80 percent of Americans prefer to spend their final days in their home, only 20 percent do just that.

A Stanford University research team applied machine learning technology to health records, in order to help hospitals and hospices give better end-of-life care to the terminally ill. Researchers examined Electronic Health Record (EHR) data from Stanford Hospital and Lucile Packard Children's hospital. The data, which covered health history for around two million child and adult patients, was used to train a "neural network" that is now able to predict the mortality of people with serious or terminal illnesses. The idea is that by telling hospitals and hospices when patients are likely to die, end-of-life care can be prioritised in a more intelligent way. "We demonstrate that routinely collected EHR [electronic health record] data can be used to create a system that prioritises patients for follow up for palliative care," the Stanford researchers explain.