The Death Predictor: A Helpful New Tool or an Ethical Morass?
Whenever Eric Karl Oermann has to tell a patient about a terrible prognosis, their first question is always: "how long do I have?" Oermann would like to offer a precise answer, to provide some certainty and help guide treatment. But although he's one of the country's foremost experts in medical artificial intelligence, Oermann is still dependent on a computer algorithm that's often wrong.
Doctors are notoriously terrible at guessing how long their patients will live.
Artificial intelligence, now often called deep learning or neural networks, has radically transformed language and image processing. It's allowed computers to play chess better than the world's grand masters and outwit the best Jeopardy players. But it still can't precisely tell a doctor how long a patient has left – or how to help that person live longer.
Someday, researchers predict, computers will be able to watch a video of a patient to determine their health status. Doctors will no longer have to spend hours inputting data into medical records. And computers will do a better job than specialists at identifying tiny tumors, impending crises, and, yes, figuring out how long the patient has to live. Oermann, a neurosurgeon at Mount Sinai, says all that technology will allow doctors to spend more time doing what they do best: talking with their patients. "I want to see more deep learning and computers in a clinical setting," he says, "so there can be more human interaction." But those days are still at least three to five years off, Oermann and other researchers say.
Doctors are notoriously terrible at guessing how long their patients will live, says Nigam Shah, an associate professor at Stanford University and assistant director of the school's Center for Biomedical Informatics Research. Doctors don't want to believe that their patient – whom they've come to like – will die. "Doctors over-estimate survival many-fold," Shah says. "How do you go into work, in say, oncology, and not be delusionally optimistic? You have to be."
But patients near the end of life will get better treatment – and even live longer – if they are overseen by hospice or palliative care, research shows. So, instead of relying on human bias to select those whose lives are nearing their end, Shah and his colleagues showed that they could use a deep learning algorithm based on medical records to flag incoming patients with a life expectancy of three months to a year. They use that data to indicate who might need palliative care. Then, the palliative care team can reach out to treating physicians proactively, instead of relying on their referrals or taking the time to read extensive medical charts.
But, although the system works well, Shah isn't yet sure if such indicators actually get the appropriate patients into palliative care. He's recently partnered with a palliative care doctor to run a gold-standard clinical trial to test whether patients who are flagged by this algorithm are indeed a better match for palliative care.
"What is effective from a health system perspective might not be effective from a treating physician's perspective and might not be effective from the patient's perspective," Shah notes. "I don't have a good way to guess everybody's reaction without actually studying it." Whether palliative care is appropriate, for instance, depends on more than just the patient's health status. "If the patient's not ready, the family's not ready and the doctor's not ready, then you're just banging your head against the wall," Shah says. "Given limited capacity, it's a waste of resources" to put that person in palliative care.
The algorithm isn't perfect, but "on balance, it leads to better decisions more often."
Alexander Smith and Sei Lee, both palliative care doctors, work together at the University of California, San Francisco, to develop predictions for patients who come to the hospital with a complicated prognosis or a history of decline. Their algorithm, they say, helps decide if this patient's problems – which might include diabetes, heart disease, a slow-growing cancer, and memory issues – make them eligible for hospice. The algorithm isn't perfect, they both agree, but "on balance, it leads to better decisions more often," Smith says.
Bethany Percha, an assistant professor at Mount Sinai, says that an algorithm may tell doctors that their patient is trending downward, but it doesn't do anything to change that trajectory. "Even if you can predict something, what can you do about it?" Algorithms may be able to offer treatment suggestions – but not what specific actions will alter a patient's future, says Percha, also the chief technology officer of Precise Health Enterprise, a product development group within Mount Sinai. And the algorithms remain challenging to develop. Electronic medical records may be great at her hospital, but if the patient dies at a different one, her system won't know. If she wants to be certain a patient has died, she has to merge social security records of death with her system's medical records – a time-consuming and cumbersome process.
An algorithm that learns from biased data will be biased, Shah says. Patients who are poor or African American historically have had worse health outcomes. If researchers train an algorithm on data that includes those biases, they get baked into the algorithms, which can then lead to a self-fulfilling prophesy. Smith and Lee say they've taken race out of their algorithms to avoid this bias.
Age is even trickier. There's no question that someone's risk of illness and death goes up with age. But an 85-year-old who breaks a hip running a marathon should probably be treated very differently than an 85-year-old who breaks a hip trying to get out of a chair in a dementia care unit. That's why the doctor can never be taken out of the equation, Shah says. Human judgment will always be required in medical care and an algorithm should never be followed blindly, he says.
Experts say that the flaws in artificial intelligence algorithms shouldn't prevent people from using them – carefully.
Researchers are also concerned that their algorithms will be used to ration care, or that insurance companies will use their data to justify a rate increase. If an algorithm predicts a patient is going to end up back in the hospital soon, "who's benefitting from knowing a patient is going to be readmitted? Probably the insurance company," Percha says.
Still, Percha and others say, the flaws in artificial intelligence algorithms shouldn't prevent people from using them – carefully. "These are new and exciting tools that have a lot of potential uses. We need to be conscious about how to use them going forward, but it doesn't mean we shouldn't go down this road," she says. "I think the potential benefits outweigh the risks, especially because we've barely scratched the surface of what big data can do right now."
Stronger psychedelics that rewire the brain, with Doug Drysdale
A promising development in science in recent years has been the use technology to optimize something natural. One-upping nature's wisdom isn't easy. In many cases, we haven't - and maybe we can't - figure it out. But today's episode features a fascinating example: using tech to optimize psychedelic mushrooms.
Listen on Apple | Listen on Spotify | Listen on Stitcher | Listen on Amazon | Listen on Google
These mushrooms have been used for religious, spiritual and medicinal purposes for thousands of years, but only in the past several decades have scientists brought psychedelics into the lab to enhance them and maximize their therapeutic value.
Today’s podcast guest, Doug Drysdale, is doing important work to lead this effort. Drysdale is the CEO of a company called Cybin that has figured out how to make psilocybin more potent, so it can be administered in smaller doses without side effects.
The natural form of psilocybin has been studied increasingly in the realm of mental health. Taking doses of these mushrooms appears to help people with anxiety and depression by spurring the development of connections in the brain, an example of neuroplasticity. The process basically shifts the adult brain from being fairly rigid like dried clay into a malleable substance like warm wax - the state of change that's constantly underway in the developing brains of children.
Neuroplasticity in adults seems to unlock some of our default ways of of thinking, the habitual thought patterns that’ve been associated with various mental health problems. Some promising research suggests that psilocybin causes a reset of sorts. It makes way for new, healthier thought patterns.
So what is Drysdale’s secret weapon to bring even more therapeutic value to psilocybin? It’s a process called deuteration. It focuses on the hydrogen atoms in psilocybin. These atoms are very light and don’t stick very well to carbon, which is another atom in psilocybin. As a result, our bodies can easily breaks down the bonds between the hydrogen and carbon atoms. For many people, that means psilocybin gets cleared from the body too quickly, before it can have a therapeutic benefit.
In deuteration, scientists do something simple but ingenious: they replace the hydrogen atoms with a molecule called deuterium. It’s twice as heavy as hydrogen and forms tighter bonds with the carbon. Because these pairs are so rock-steady, they slow down the rate at which psilocybin is metabolized, so it has more sustained effects on our brains.
Cybin isn’t Drysdale’s first go around at this - far from it. He has over 30 years of experience in the healthcare sector. During this time he’s raised around $4 billion of both public and private capital, and has been named Ernst and Young Entrepreneur of the Year. Before Cybin, he was the founding CEO of a pharmaceutical company called Alvogen, leading it from inception to around $500 million in revenues, across 35 countries. Drysdale has also been the head of mergers and acquisitions at Actavis Group, leading 15 corporate acquisitions across three continents.
In this episode, Drysdale walks us through the promising research of his current company, Cybin, and the different therapies he’s developing for anxiety and depression based not just on psilocybin but another psychedelic compound found in plants called DMT. He explains how they seem to have such powerful effects on the brain, as well as the potential for psychedelics to eventually support other use cases, including helping us strive toward higher levels of well-being. He goes on to discuss his views on mindfulness and lifestyle factors - such as optimal nutrition - that could help bring out hte best in psychedelics.
Show links:
Doug Drysdale full bio
Doug Drysdale twitter
Cybin website
Cybin development pipeline
Cybin's promising phase 2 research on depression
Johns Hopkins psychedelics research and psilocybin research
Mets owner Steve Cohen invests in psychedelic therapies
Doug Drysdale, CEO of Cybin
How the body's immune resilience affects our health and lifespan
Story by Big Think
It is a mystery why humans manifest vast differences in lifespan, health, and susceptibility to infectious diseases. However, a team of international scientists has revealed that the capacity to resist or recover from infections and inflammation (a trait they call “immune resilience”) is one of the major contributors to these differences.
Immune resilience involves controlling inflammation and preserving or rapidly restoring immune activity at any age, explained Weijing He, a study co-author. He and his colleagues discovered that people with the highest level of immune resilience were more likely to live longer, resist infection and recurrence of skin cancer, and survive COVID and sepsis.
Measuring immune resilience
The researchers measured immune resilience in two ways. The first is based on the relative quantities of two types of immune cells, CD4+ T cells and CD8+ T cells. CD4+ T cells coordinate the immune system’s response to pathogens and are often used to measure immune health (with higher levels typically suggesting a stronger immune system). However, in 2021, the researchers found that a low level of CD8+ T cells (which are responsible for killing damaged or infected cells) is also an important indicator of immune health. In fact, patients with high levels of CD4+ T cells and low levels of CD8+ T cells during SARS-CoV-2 and HIV infection were the least likely to develop severe COVID and AIDS.
Individuals with optimal levels of immune resilience were more likely to live longer.
In the same 2021 study, the researchers identified a second measure of immune resilience that involves two gene expression signatures correlated with an infected person’s risk of death. One of the signatures was linked to a higher risk of death; it includes genes related to inflammation — an essential process for jumpstarting the immune system but one that can cause considerable damage if left unbridled. The other signature was linked to a greater chance of survival; it includes genes related to keeping inflammation in check. These genes help the immune system mount a balanced immune response during infection and taper down the response after the threat is gone. The researchers found that participants who expressed the optimal combination of genes lived longer.
Immune resilience and longevity
The researchers assessed levels of immune resilience in nearly 50,000 participants of different ages and with various types of challenges to their immune systems, including acute infections, chronic diseases, and cancers. Their evaluation demonstrated that individuals with optimal levels of immune resilience were more likely to live longer, resist HIV and influenza infections, resist recurrence of skin cancer after kidney transplant, survive COVID infection, and survive sepsis.
However, a person’s immune resilience fluctuates all the time. Study participants who had optimal immune resilience before common symptomatic viral infections like a cold or the flu experienced a shift in their gene expression to poor immune resilience within 48 hours of symptom onset. As these people recovered from their infection, many gradually returned to the more favorable gene expression levels they had before. However, nearly 30% who once had optimal immune resilience did not fully regain that survival-associated profile by the end of the cold and flu season, even though they had recovered from their illness.
Intriguingly, some people who are 90+ years old still have optimal immune resilience, suggesting that these individuals’ immune systems have an exceptional capacity to control inflammation and rapidly restore proper immune balance.
This could suggest that the recovery phase varies among people and diseases. For example, young female sex workers who had many clients and did not use condoms — and thus were repeatedly exposed to sexually transmitted pathogens — had very low immune resilience. However, most of the sex workers who began reducing their exposure to sexually transmitted pathogens by using condoms and decreasing their number of sex partners experienced an improvement in immune resilience over the next 10 years.
Immune resilience and aging
The researchers found that the proportion of people with optimal immune resilience tended to be highest among the young and lowest among the elderly. The researchers suggest that, as people age, they are exposed to increasingly more health conditions (acute infections, chronic diseases, cancers, etc.) which challenge their immune systems to undergo a “respond-and-recover” cycle. During the response phase, CD8+ T cells and inflammatory gene expression increase, and during the recovery phase, they go back down.
However, over a lifetime of repeated challenges, the immune system is slower to recover, altering a person’s immune resilience. Intriguingly, some people who are 90+ years old still have optimal immune resilience, suggesting that these individuals’ immune systems have an exceptional capacity to control inflammation and rapidly restore proper immune balance despite the many respond-and-recover cycles that their immune systems have faced.
Public health ramifications could be significant. Immune cell and gene expression profile assessments are relatively simple to conduct, and being able to determine a person’s immune resilience can help identify whether someone is at greater risk for developing diseases, how they will respond to treatment, and whether, as well as to what extent, they will recover.