The Promise of Pills That Know When You Swallow Them
Dr. Sara Browne, an associate professor of clinical medicine at the University of California, San Diego, is a specialist in infectious diseases and, less formally, "a global health person." She often travels to southern Africa to meet with colleagues working on the twin epidemics of HIV and tuberculosis.
"This technology, in my opinion, is an absolute slam dunk for tuberculosis."
Lately she has asked them to name the most pressing things she can help with as a researcher based in a wealthier country. "Over and over and over again," she says, "the only thing they wanted to know is whether their patients are taking the drugs."
Tuberculosis is one of world's deadliest diseases; every year there are 10 million new infections and more than a million deaths. When a patient with tuberculosis is prescribed medicine to combat the disease, adherence to the regimen is important not just for the individual's health, but also for the health of the community. Poor adherence can lead to lengthier and more costly treatment and, perhaps more importantly, to drug-resistant strains of the disease -- an increasing global threat.
Browne is testing a new method to help healthcare workers track their patients' adherence with greater precision—close to exact precision even. They're called digital pills, and they involve a patient swallowing medicine as they normally would, only the capsule contains a sensor that—when it contacts stomach acid—transmits a signal to a small device worn on or near the body. That device in turn sends a signal to the patient's phone or tablet and into a cloud-based database. The fact that the pill has been swallowed has therefore been recorded almost in real time, and notice is available to whoever has access to the database.
"This technology, in my opinion, is an absolute slam dunk for tuberculosis," Browne says. TB is much more prevalent in poorer regions of the world—in Sub-Saharan Africa, for example—than in richer places like the U.S., where Browne's studies thus far have taken place. But when someone is diagnosed in the U.S., because of the risk to others if it spreads, they will likely have to deal with "directly observed therapy" to ensure that they take their medicines correctly.
DOT, as it's called, requires the patient to meet with a healthcare worker several days a week, or every day, so that the medicine intake can be observed in person -- an expensive and time-consuming process. Still, the Centers for Disease Control and Prevention website says (emphasis theirs), "DOT should be used for ALL patients with TB disease, including children and adolescents. There is no way to accurately predict whether a patient will adhere to treatment without this assistance."
Digital pills can help with both the cost and time involved, and potentially improve adherence in places where DOT is impossibly expensive. With the sensors, you can monitor a patient's adherence without a healthcare worker physically being in the room. Patients can live their normal lives and if they miss a pill, they can receive a reminder by text or a phone call from the clinic or hospital. "They can get on with their lives," said Browne. "They don't need the healthcare system to interrupt them."
A 56-year-old patient who participated in one of Browne's studies when he was undergoing TB treatment says that before he started taking the digital pills, he would go to the clinic at least once every day, except weekends. Once he switched to digital pills, he could go to work and spend time with his wife and children instead of fighting traffic every day to get to the clinic. He just had to wear a small patch on his abdomen, which would send the signal to a tablet provided by Browne's team. When he returned from work, he could see the results—that he'd taken the pill—in a database accessed via the tablet. (He could also see his heart rate and respiratory rate.) "I could do my daily activities without interference," he said.
Dr. Peter Chai, a medical toxicologist and emergency medicine physician at Brigham and Women's Hospital in Boston, is studying digital pills in a slightly different context, to help fight the country's opioid overdose crisis. Doctors like Chai prescribe pain medicine, he says, but then immediately put the onus on the patient to decide when to take it. This lack of guidance can lead to abuse and addiction. Patients are often told to take the meds "as needed." Chai and his colleagues wondered, "What does that mean to patients? And are people taking more than they actually need? Because pain is such a subjective experience."
The patients "liked the fact that somebody was watching them."
They wanted to see what "take as needed" actually led to, so they designed a study with patients who had broken a bone and come to the hospital's emergency department to get it fixed. Those who were prescribed oxycodone—a pharmaceutical opioid for pain relief—got enough digital pills to last one week. They were supposed to take the pills as needed, or as many as three pills per day. When the pills were ingested, the sensor sent a signal to a card worn on a lanyard around the neck.
Chai and his colleagues were able to see exactly when the patients took the pills and how many, and to detect patterns of ingestion more precisely than ever before. They talked to the patients after the seven days were up, and Chai said most were happy to be taking digital pills. The patients saw it as a layer of protection from afar. "They liked the fact that somebody was watching them," Chai said.
Both doctors, Browne and Chai, are in early stages of studies with patients taking pre-exposure prophylaxis, medicines that can protect people with a high-risk of contracting HIV, such as injectable drug users. Without good adherence, patients leave themselves open to getting the virus. If a patient is supposed to take a pill at 2 p.m. but the digital pill sensor isn't triggered, the healthcare provider can have an automatic message sent as a reminder. Or a reminder to one of the patient's friends or loved ones.
"Like Swallowing Your Phone"?
Deven Desai, an associate professor of law and ethics at Georgia Tech, says that digital pills sound like a great idea for helping with patient adherence, a big issue that self-reporting doesn't fully solve. He likes the idea of a physician you trust having better information about whether you're taking your medication on time. "On the surface that's just cool," he says. "That's a good thing." But Desai, who formerly worked as academic research counsel at Google, said that some of the same questions that have come up in recent years with social media and the Internet in general also apply to digital pills.
"Think of it like your phone, but you swallowed it," he says. "At first it could be great, simple, very much about the user—in this case, the patient—and the data is going between you and your doctor and the medical people it ought to be going to. Wonderful. But over time, phones change. They become 'smarter.'" And when phones and other technologies become smarter, he says, the companies behind them tend to expand the type of data they collect, because they can. Desai says it will be crucial that prescribers be completely transparent about who is getting the patients' data and for what purpose.
"We're putting stuff in our body in good faith with our medical providers, and what if it turned out later that all of a sudden someone was data mining or putting in location trackers and we never knew about that?" Desai asks. "What science has to realize is if they don't start thinking about this, what could be a wonderful technology will get killed."
Leigh Turner, an associate professor at the University of Minnesota's Center for Bioethics, agrees with Desai that digital pills have great promise, and also that there are clear reasons to be concerned about their use. Turner compared the pills to credit cards and social media, in that the data from them can potentially be stolen or leaked. One question he would want answered before the pills were normalized: "What kind of protective measures are in place to make sure that personal information isn't spilling out and being acquired by others or used by others in unexpected and unwanted ways?"
If digital pills catch on, some experts worry that they may one day not be a voluntary technology.
Turner also wonders who will have access to the pills themselves. Only those who can afford both the medicine plus the smartphones that are currently required for their use? Or will people from all economic classes have access? If digital pills catch on, he also worries they may one day not be a voluntary technology.
"When it comes to digital pills, it's not something that's really being foisted on individuals. It's more something that people can be informed of and can choose to take or not to take," he says. "But down the road, I can imagine a scenario where we move away from purely voluntary agreements to it becoming more of an expectation."
He says it's easy to picture a scenario in which insurance companies demand that patient medicinal intake data be tracked and collected or else. Refuse to have your adherence tracked and you risk higher rates or even overall coverage. Maybe patients who don't take the digital pills suffer dire consequences financially or medically. "Maybe it becomes beneficial as much to health insurers and payers as it is to individual patients," Turner says.
In November 2017, the FDA approved the first-ever digital pill that includes a sensor, a drug called Abilify MyCite, made by Otsuka Pharmaceutical Company. The drug, which is yet to be released, is used to treat schizophrenia, bipolar disorder, and depression. With a built-in sensor developed by Proteus Digital Health, patients can give their doctors permission to see when exactly they are taking, or not taking, their meds. For patients with mental illness, the ability to help them stick to their prescribed regime can be life-saving.
But Turner wonders if Abilify is the best drug to be a forerunner for digital pills. Some people with schizophrenia might be suffering from paranoia, and perhaps giving them a pill developed by a large corporation that sends data from their body to be tracked by other people might not be the best idea. It could in fact exacerbate their sense of paranoia.
The Bottom Line: Protect the Data
We all have relatives who have pillboxes with separate compartments for each day of the week, or who carry pillboxes that beep when it's time to take the meds. But that's not always good enough for people with dementia, mental illness, drug addiction, or other life situations that make it difficult to remember to take their pills. Digital pills can play an important role in helping these people.
"The absolute principle here is that the data has to belong to the patient."
The one time the patient from Browne's study forgot to take his pills, he got a beeping reminder from his tablet that he'd missed a dose. "Taking a medication on a daily basis, sometimes we just forget, right?" he admits. "With our very accelerated lives nowadays, it helps us to remember that we have to take the medications. So patients are able to be on top of their own treatment."
Browne is convinced that digital pills can help people in developing countries with high rates of TB and HIV, though like Turner and Desai she cautions that patients' data must be protected. "I think it can be a tremendous technology for patient empowerment and I also think if properly used it can help the medical system to support patients that need it," she said. "But the absolute principle here is that the data has to belong to the patient."
One day in recent past, scientists at Columbia University’s Creative Machines Lab set up a robotic arm inside a circle of five streaming video cameras and let the robot watch itself move, turn and twist. For about three hours the robot did exactly that—it looked at itself this way and that, like toddlers exploring themselves in a room full of mirrors. By the time the robot stopped, its internal neural network finished learning the relationship between the robot’s motor actions and the volume it occupied in its environment. In other words, the robot built a spatial self-awareness, just like humans do. “We trained its deep neural network to understand how it moved in space,” says Boyuan Chen, one of the scientists who worked on it.
For decades robots have been doing helpful tasks that are too hard, too dangerous, or physically impossible for humans to carry out themselves. Robots are ultimately superior to humans in complex calculations, following rules to a tee and repeating the same steps perfectly. But even the biggest successes for human-robot collaborations—those in manufacturing and automotive industries—still require separating the two for safety reasons. Hardwired for a limited set of tasks, industrial robots don't have the intelligence to know where their robo-parts are in space, how fast they’re moving and when they can endanger a human.
Over the past decade or so, humans have begun to expect more from robots. Engineers have been building smarter versions that can avoid obstacles, follow voice commands, respond to human speech and make simple decisions. Some of them proved invaluable in many natural and man-made disasters like earthquakes, forest fires, nuclear accidents and chemical spills. These disaster recovery robots helped clean up dangerous chemicals, looked for survivors in crumbled buildings, and ventured into radioactive areas to assess damage.
Now roboticists are going a step further, training their creations to do even better: understand their own image in space and interact with humans like humans do. Today, there are already robot-teachers like KeeKo, robot-pets like Moffin, robot-babysitters like iPal, and robotic companions for the elderly like Pepper.
But even these reasonably intelligent creations still have huge limitations, some scientists think. “There are niche applications for the current generations of robots,” says professor Anthony Zador at Cold Spring Harbor Laboratory—but they are not “generalists” who can do varied tasks all on their own, as they mostly lack the abilities to improvise, make decisions based on a multitude of facts or emotions, and adjust to rapidly changing circumstances. “We don’t have general purpose robots that can interact with the world. We’re ages away from that.”
Robotic spatial self-awareness – the achievement by the team at Columbia – is an important step toward creating more intelligent machines. Hod Lipson, professor of mechanical engineering who runs the Columbia lab, says that future robots will need this ability to assist humans better. Knowing how you look and where in space your parts are, decreases the need for human oversight. It also helps the robot to detect and compensate for damage and keep up with its own wear-and-tear. And it allows robots to realize when something is wrong with them or their parts. “We want our robots to learn and continue to grow their minds and bodies on their own,” Chen says. That’s what Zador wants too—and on a much grander level. “I want a robot who can drive my car, take my dog for a walk and have a conversation with me.”
Columbia scientists have trained a robot to become aware of its own "body," so it can map the right path to touch a ball without running into an obstacle, in this case a square.
Jane Nisselson and Yinuo Qin/ Columbia Engineering
Today’s technological advances are making some of these leaps of progress possible. One of them is the so-called Deep Learning—a method that trains artificial intelligence systems to learn and use information similar to how humans do it. Described as a machine learning method based on neural network architectures with multiple layers of processing units, Deep Learning has been used to successfully teach machines to recognize images, understand speech and even write text.
Trained by Google, one of these language machine learning geniuses, BERT, can finish sentences. Another one called GPT3, designed by San Francisco-based company OpenAI, can write little stories. Yet, both of them still make funny mistakes in their linguistic exercises that even a child wouldn’t. According to a paper published by Stanford’s Center for Research on Foundational Models, BERT seems to not understand the word “not.” When asked to fill in the word after “A robin is a __” it correctly answers “bird.” But try inserting the word “not” into that sentence (“A robin is not a __”) and BERT still completes it the same way. Similarly, in one of its stories, GPT3 wrote that if you mix a spoonful of grape juice into your cranberry juice and drink the concoction, you die. It seems that robots, and artificial intelligence systems in general, are still missing some rudimentary facts of life that humans and animals grasp naturally and effortlessly.
How does one give robots a genome? Zador has an idea. We can’t really equip machines with real biological nucleotide-based genes, but we can mimic the neuronal blueprint those genes create.
It's not exactly the robots’ fault. Compared to humans, and all other organisms that have been around for thousands or millions of years, robots are very new. They are missing out on eons of evolutionary data-building. Animals and humans are born with the ability to do certain things because they are pre-wired in them. Flies know how to fly, fish knows how to swim, cats know how to meow, and babies know how to cry. Yet, flies don’t really learn to fly, fish doesn’t learn to swim, cats don’t learn to meow, and babies don’t learn to cry—they are born able to execute such behaviors because they’re preprogrammed to do so. All that happens thanks to the millions of years of evolutions wired into their respective genomes, which give rise to the brain’s neural networks responsible for these behaviors. Robots are the newbies, missing out on that trove of information, Zador argues.
A neuroscience professor who studies how brain circuitry generates various behaviors, Zador has a different approach to developing the robotic mind. Until their creators figure out a way to imbue the bots with that information, robots will remain quite limited in their abilities. Each model will only be able to do certain things it was programmed to do, but it will never go above and beyond its original code. So Zador argues that we have to start giving robots a genome.
How does one do that? Zador has an idea. We can’t really equip machines with real biological nucleotide-based genes, but we can mimic the neuronal blueprint those genes create. Genomes lay out rules for brain development. Specifically, the genome encodes blueprints for wiring up our nervous system—the details of which neurons are connected, the strength of those connections and other specs that will later hold the information learned throughout life. “Our genomes serve as blueprints for building our nervous system and these blueprints give rise to a human brain, which contains about 100 billion neurons,” Zador says.
If you think what a genome is, he explains, it is essentially a very compact and compressed form of information storage. Conceptually, genomes are similar to CliffsNotes and other study guides. When students read these short summaries, they know about what happened in a book, without actually reading that book. And that’s how we should be designing the next generation of robots if we ever want them to act like humans, Zador says. “We should give them a set of behavioral CliffsNotes, which they can then unwrap into brain-like structures.” Robots that have such brain-like structures will acquire a set of basic rules to generate basic behaviors and use them to learn more complex ones.
Currently Zador is in the process of developing algorithms that function like simple rules that generate such behaviors. “My algorithms would write these CliffsNotes, outlining how to solve a particular problem,” he explains. “And then, the neural networks will use these CliffsNotes to figure out which ones are useful and use them in their behaviors.” That’s how all living beings operate. They use the pre-programmed info from their genetics to adapt to their changing environments and learn what’s necessary to survive and thrive in these settings.
For example, a robot’s neural network could draw from CliffsNotes with “genetic” instructions for how to be aware of its own body or learn to adjust its movements. And other, different sets of CliffsNotes may imbue it with the basics of physical safety or the fundamentals of speech.
At the moment, Zador is working on algorithms that are trying to mimic neuronal blueprints for very simple organisms—such as earthworms, which have only 302 neurons and about 7000 synapses compared to the millions we have. That’s how evolution worked, too—expanding the brains from simple creatures to more complex to the Homo Sapiens. But if it took millions of years to arrive at modern humans, how long would it take scientists to forge a robot with human intelligence? That’s a billion-dollar question. Yet, Zador is optimistic. “My hypotheses is that if you can build simple organisms that can interact with the world, then the higher level functions will not be nearly as challenging as they currently are.”
Lina Zeldovich has written about science, medicine and technology for Popular Science, Smithsonian, National Geographic, Scientific American, Reader’s Digest, the New York Times and other major national and international publications. A Columbia J-School alumna, she has won several awards for her stories, including the ASJA Crisis Coverage Award for Covid reporting, and has been a contributing editor at Nautilus Magazine. In 2021, Zeldovich released her first book, The Other Dark Matter, published by the University of Chicago Press, about the science and business of turning waste into wealth and health. You can find her on http://linazeldovich.com/ and @linazeldovich.
Podcast: Wellness chatbots and meditation pods with Deepak Chopra
Over the last few decades, perhaps no one has impacted healthy lifestyles more than Deepak Chopra. While several of his theories and recommendations have been criticized by prominent members of the scientific community, he has helped bring meditation, yoga and other practices for well-being into the mainstream in ways that benefit the health of vast numbers of people every day. His work has led many to accept new ways of thinking about alternative medicine, the power of mind over body, and the malleability of the aging process.
His impact is such that it's been observed our culture no longer recognizes him as a human being but as a pervasive symbol of new-agey personal health and spiritual growth. Last week, I had a chance to confirm that Chopra is, in fact, a human being – and deserving of his icon status – when I talked with him for the Leaps.org podcast. He relayed ideas that were wise and ancient, yet highly relevant to our world today, with the fluidity and ease of someone discussing the weather. Showing no signs of slowing down at age 76, he described his prolific work, including the publication of two books in the past year and a range of technologies he’s developing, including a meditation app, meditation pods for the workplace, and a chatbot for mental health called Piwi.
Take a listen and get inspired to do some meditation and deep thinking on the future of health. As Chopra told me, “If you don’t have time to meditate once per day, you probably need to meditate twice per day.”
Highlights:
2:10: Chopra talks about meditation broadly and meditation pods, including the ones made by OpenSeed for meditation in the workplace.
6:10: The drawbacks of quick fixes like drugs for mental health.
10:30: The benefits of group meditation versus individual meditation.
14:35: What is a "metahuman" and how to become one.
19:40: The difference between the conditioned mind and the mind that's infinitely creative.
22:48: How Chopra's views of free will differ from the views of many neuroscientists.
28:04: Thinking Fast and Slow, and the role of intuition.
31:20: Athletic and creative geniuses.
32:43: The nature of fundamental truth.
34:00: Meditation for kids.
37:12: Never alone.Love and how AI chatbots can support mental health.
42:30: Extending lifespan, gene editing and lifestyle.
46:05: Chopra's mentor in living a long good life (and my mentor).
47:45: The power of yoga.
Links:
- OpenSeed meditation pods for people to meditate at work (Chopra is an advisor to OpenSeed).
- Chopra's book from 2021, Metahuman: Unleash Your Infinite Potential
- Chopra's book from 2022, Abundance: The Inner Path to Wealth
- NeverAlone.Love, Chopra's collaboration of businesses, policy makers, mental health professionals and others to raise awareness about mental health, advance scientific research and "create a global technology platform to democratize access to resources."
- The Piwi chatbot for mental health
- The Chopra Meditation & Well-Being App for people of all ages
- Only 1.6 percent of U.S. children meditate, according to the National Center for Complementary and Integrative Health