The Algorithm Will See You Now
Artificial intelligence in medicine, still in an early phase, stands to transform how doctors and nurses spend their time.
There's a quiet revolution going on in medicine. It's driven by artificial intelligence, but paradoxically, new technology may put a more human face on healthcare.
AI's usefulness in healthcare ranges far and wide.
Artificial intelligence is software that can process massive amounts of information and learn over time, arriving at decisions with striking accuracy and efficiency. It offers greater accuracy in diagnosis, exponentially faster genome sequencing, the mining of medical literature and patient records at breathtaking speed, a dramatic reduction in administrative bureaucracy, personalized medicine, and even the democratization of healthcare.
The algorithms that bring these advantages won't replace doctors; rather, by offloading some of the most time-consuming tasks in healthcare, providers will be able to focus on personal interactions with patients—listening, empathizing, educating and generally putting the care back in healthcare. The relationship can focus on the alleviation of suffering, both the physical and emotional kind.
Challenges of Getting AI Up and Running
The AI revolution, still in its early phase in medicine, is already spurring some amazing advances, despite the fact that some experts say it has been overhyped. IBM's Watson Health program is a case in point. IBM capitalized on Watson's ability to process natural language by designing algorithms that devour data like medical articles and analyze images like MRIs and medical slides. The algorithms help diagnose diseases and recommend treatment strategies.
But Technology Review reported that a heavily hyped partnership with the MD Anderson Cancer Center in Houston fell apart in 2017 because of a lack of data in the proper format. The data existed, just not in a way that the voraciously data-hungry AI could use to train itself.
The hiccup certainly hasn't dampened the enthusiasm for medical AI among other tech giants, including Google and Apple, both of which have invested billions in their own healthcare projects. At this point, the main challenge is the need for algorithms to interpret a huge diversity of data mined from medical records. This can include everything from CT scans, MRIs, electrocardiograms, x-rays, and medical slides, to millions of pages of medical literature, physician's notes, and patient histories. It can even include data from implantables and wearables such as the Apple Watch and blood sugar monitors.
None of this information is in anything resembling a standard format across and even within hospitals, clinics, and diagnostic centers. Once the algorithms are trained, however, they can crunch massive amounts of data at blinding speed, with an accuracy that matches and sometimes even exceeds that of highly experienced doctors.
Genome sequencing, for example, took years to accomplish as recently as the early 2000s. The Human Genome Project, the first sequencing of the human genome, was an international effort that took 13 years to complete. In April of this year, Rady Children's Institute for Genomic Medicine in San Diego used an AI-powered genome sequencing algorithm to diagnose rare genetic diseases in infants in about 20 hours, according to ScienceDaily.
"Patient care will always begin and end with the doctor."
Dr. Stephen Kingsmore, the lead author of an article published in Science Translational Medicine, emphasized that even though the algorithm helped guide the treatment strategies of neonatal intensive care physicians, the doctor was still an indispensable link in the chain. "Some people call this artificial intelligence, we call it augmented intelligence," he says. "Patient care will always begin and end with the doctor."
One existing trend is helping to supply a great amount of valuable data to algorithms—the electronic health record. Initially blamed for exacerbating the already crushing workload of many physicians, the EHR is emerging as a boon for algorithms because it consolidates all of a patient's data in one record.
Examples of AI in Action Around the Globe
If you're a parent who has ever taken a child to the doctor with flulike symptoms, you know the anxiety of wondering if the symptoms signal something serious. Kang Zhang, M.D., Ph.D., the founding director of the Institute for Genomic Medicine at the University of California at San Diego, and colleagues developed an AI natural language processing model that used deep learning to analyze the EHRs of 1.3 million pediatric visits to a clinic in Guanzhou, China.
The AI identified common childhood diseases with about the same accuracy as human doctors, and it was even able to split the diagnoses into two categories—common conditions such as flu, and serious, life-threatening conditions like meningitis. Zhang has emphasized that the algorithm didn't replace the human doctor, but it did streamline the diagnostic process and could be used in a triage capacity when emergency room personnel need to prioritize the seriously ill over those suffering from common, less dangerous ailments.
AI's usefulness in healthcare ranges far and wide. In Uganda and several other African nations, AI is bringing modern diagnostics to remote villages that have no access to traditional technologies such as x-rays. The New York Times recently reported that there, doctors are using a pocket-sized, hand-held ultrasound machine that works in concert with a cell phone to image and diagnose everything from pneumonia (a common killer of children) to cancerous tumors.
The beauty of the highly portable, battery-powered device is that ultrasound images can be uploaded on computers so that physicians anywhere in the world can review them and weigh in with their advice. And the images are instantly incorporated into the patient's EHR.
Jonathan Rothberg, the founder of Butterfly Network, the Connecticut company that makes the device, told The New York Times that "Two thirds of the world's population gets no imaging at all. When you put something on a chip, the price goes down and you democratize it." The Butterfly ultrasound machine, which sells for $2,000, promises to be a game-changer in remote areas of Africa, South America, and Asia, as well as at the bedsides of patients in developed countries.
AI algorithms are rapidly emerging in healthcare across the U.S. and the world. China has become a major international player, set to surpass the U.S. this year in AI capital investment, the translation of AI research into marketable products, and even the number of often-cited research papers on AI. So far the U.S. is still the leader, but some experts describe the relationship between the U.S. and China as an AI cold war.
"The future of machine learning isn't sentient killer robots. It's longer human lives."
The U.S. Food and Drug Administration expanded its approval of medical algorithms from two in all of 2017 to about two per month throughout 2018. One of the first fields to be impacted is ophthalmology.
One algorithm, developed by the British AI company DeepMind (owned by Alphabet, the parent company of Google), instantly scans patients' retinas and is able to diagnose diabetic retinopathy without needing an ophthalmologist to interpret the scans. This means diabetics can get the test every year from their family physician without having to see a specialist. The Financial Times reported in March that the technology is now being used in clinics throughout Europe.
In Copenhagen, emergency service dispatchers are using a new voice-processing AI called Corti to analyze the conversations in emergency phone calls. The algorithm analyzes the verbal cues of callers, searches its huge database of medical information, and provides dispatchers with onscreen diagnostic information. Freddy Lippert, the CEO of EMS Copenhagen, notes that the algorithm has already saved lives by expediting accurate diagnoses in high-pressure situations where time is of the essence.
Researchers at the University of Nottingham in the UK have even developed a deep learning algorithm that predicts death more accurately than human clinicians. The algorithm incorporates data from a huge range of factors in a chronically ill population, including how many fruits and vegetables a patient eats on a daily basis. Dr. Stephen Weng, lead author of the study, published in PLOS ONE, said in a press release, "We found machine learning algorithms were significantly more accurate in predicting death than the standard prediction models developed by a human expert."
New digital technologies are allowing patients to participate in their healthcare as never before. A feature of the new Apple Watch is an app that detects cardiac arrhythmias and even produces an electrocardiogram if an abnormality is detected. The technology, approved by the FDA, is helping cardiologists monitor heart patients and design interventions for those who may be at higher risk of a cardiac event like a stroke.
If having an algorithm predict your death sends a shiver down your spine, consider that algorithms may keep you alive longer. In 2018, technology reporter Tristan Greene wrote for Medium that "…despite the unending deluge of panic-ridden articles declaring AI the path to apocalypse, we're now living in a world where algorithms save lives every day. The future of machine learning isn't sentient killer robots. It's longer human lives."
The Risks of AI Compiling Your Data
To be sure, the advent of AI-infused medical technology is not without its risks. One risk is that the use of AI wearables constantly monitoring our vital signs could turn us into a nation of hypochondriacs, racing to our doctors every time there's a blip in some vital sign. Such a development could stress an already overburdened system that suffers from, among other things, a shortage of doctors and nurses. Another risk has to do with the privacy protections on the massive repository of intimately personal information that AI will have on us.
In an article recently published in the Journal of the American Medical Association, Australian researcher Kit Huckvale and colleagues examined the handling of data by 36 smartphone apps that assisted people with either depression or smoking cessation, two areas that could lend themselves to stigmatization if they fell into the wrong hands.
Out of the 36 apps, 33 shared their data with third parties, despite the fact that just 25 of those apps had a privacy policy at all and out of those, only 23 stated that data would be shared with third parties. The recipients of all that data? It went almost exclusively to Facebook and Google, to be used for advertising and marketing purposes. But there's nothing to stop it from ending up in the hands of insurers, background databases, or any other entity.
Even when data isn't voluntarily shared, any digital information can be hacked. EHRs and even wearable devices share the same vulnerability as any other digital record or device. Still, the promise of AI to radically improve efficiency and accuracy in healthcare is hard to ignore.
AI Can Help Restore Humanity to Medicine
Eric Topol, director of the Scripps Research Translational Institute and author of the new book Deep Medicine, says that AI gives doctors and nurses the most precious gift of all: time.
Topol welcomes his patients' use of the Apple Watch cardiac feature and is optimistic about the ways that AI is revolutionizing medicine. He says that the watch helps doctors monitor how well medications are working and has already helped to prevent strokes. But in addition to that, AI will help bring the humanity back to a profession that has become as cold and hard as a stainless steel dissection table.
"When I graduated from medical school in the 1970s," he says, "you had a really intimate relationship with your doctor." Over the decades, he has seen that relationship steadily erode as medical organizations demanded that doctors see more and more patients within ever-shrinking time windows.
"Doctors have no time to think, to communicate. We need to restore the mission in medicine."
In addition to that, EHRs have meant that doctors and nurses are getting buried in paperwork and administrative tasks. This is no doubt one reason why a recent study by the World Health Organization showed that worldwide, about 50 percent of doctors suffer from burnout. People who are utterly exhausted make more mistakes, and medical clinicians are no different from the rest of us. Only medical mistakes have unacceptably high stakes. According to its website, Johns Hopkins University recently announced that in the U.S. alone, 250,000 people die from medical mistakes each year.
"Doctors have no time to think, to communicate," says Topol. "We need to restore the mission in medicine." AI is giving doctors more time to devote to the thing that attracted them to medicine in the first place—connecting deeply with patients.
There is a real danger at this juncture, though, that administrators aware of the time-saving aspects of AI will simply push doctors to see more patients, read more tests, and embrace an even more crushing workload.
"We can't leave it to the administrators to just make things worse," says Topol. "Now is the time for doctors to advocate for a restoration of the human touch. We need to stand up for patients and for the patient-doctor relationship."
AI could indeed be a game changer, he says, but rather than squander the huge benefits of more time, "We need a new equation going forward."
When Wayne Jonas was in medical school 40 years ago, doctors would write out a prescription for placebos, spelling it out backwards in capital letters, O-B-E-C-A-L-P. The pharmacist would fill the prescription with a sugar pill, recalls Jonas, now director of integrative health programs at the Samueli Foundation. It fulfilled the patient's desire for the doctor to do something when perhaps no drug could help, and the sugar pills did no harm.
Today, that deception is seen as unethical. But time and time again, studies have shown that placebos can have real benefits. Now, researchers are trying to untangle the mysteries of placebo effect in an effort to better treat patients.
The use of placebos took off in the post-WWII period, when randomized controlled clinical trials became the gold standard for medical research. One group in a study would be treated with a placebo, a supposedly inert pill or procedure that would not affect normal healing and recovery, while another group in the study would receive an "active" component, most commonly a pill under investigation. Presumably, the group receiving the active treatment would have a better response and the difference from the placebo group would represent the efficacy of the drug being tested. That was the basis for drug approval by the U.S. Food and Drug Administration.
"Placebo responses were marginalized," says Ted Kaptchuk, director of the Program in Placebo Studies & Therapeutic Encounters at Harvard Medical School. "Doctors were taught they have to overcome it when they were thinking about using an effective drug."
But that began to change around the turn of the 21st century. The National Institutes of Health held a series of meetings to set a research agenda and fund studies to answer some basic questions, led by Jonas who was in charge of the office of alternative medicine at the time. "People spontaneously get better all the time," says Kaptchuk. The crucial question was, is the placebo effect real? Is it more than just spontaneous healing?
Brain mechanisms
A turning point came in 2001 in a paper in Science that showed physical evidence of the placebo effect. It used positron emission tomography (PET) scans to measure release patterns of dopamine — a chemical messenger involved in how we feel pleasure — in the brains of patients with Parkinson's disease. Surprisingly, the placebo activated the same patterns that were activated by Parkinson's drugs, such as levodopa. It proved the placebo effect was real; now the search was on to better understand and control it.
A key part of the effect can be the beliefs, expectations, context, and "rituals" of the encounter between doctor and patient. Belief by the doctor and patient that the treatment would work, and the formalized practices of administering the treatment can all contribute to a positive outcome.
Conditioning can be another important component in generating a response, as Pavlov demonstrated more than a century ago in his experiments with dogs. They were trained with a bell prior to feeding such that they would begin to salivate in anticipation at the sound of a bell even with no food present.
Translating that to humans, studies with pain medications and sleeping aids showed that patients who had a positive response with a certain dose of those medications could have the same response if the doses was reduced and a dummy pill substituted, even to the point where there was no longer any active ingredient.
Researchers think placebo treatments can work particularly well in helping people deal with pain and psychological disorders.
Those types of studies troubled Kaptchuk because they often relied on deception; patients weren't told they were receiving a placebo, or at best there was a possibility that they might be randomized to receive a placebo. He believed the placebo effect could work even if patients were told upfront that they were going to receive a placebo. More than a dozen so call "open-label placebo" studies across numerous medical conditions, by Kaptchuk and others, have shown that you don't have to lie to patients for a placebo to work.
Jonas likes to tell the story of a patient who used methotrexate, a potent immunosuppressant, to control her rheumatoid arthritis. She was planning a long trip and didn't want to be bothered with the injections and monitoring required in using the drug, So she began to drink a powerful herbal extract of anise, a licorice flavor that she hated, prior to each injection. She reduced the amount of methotrexate over a period of months and finally stopped, but continued to drink the anise. That process had conditioned her body "to alter her immune function and her autoimmunity" as if she were taking the drug, much like Pavlov's dogs had been trained. She has not taken methotrexate for more than a year.
An intriguing paper published in May found that mild, non-invasive electric stimulation to the brain could not only boost the placebo effect on pain but also reduce the "nocebo" effect — when patients report a negative effect to a sham treatment. While the work is very preliminary, it may open the door to directly manipulating these responses.
Researchers think placebo treatments can work particularly well in helping people deal with pain and psychological disorders, areas where drugs often are of little help. Still, placebos aren't a cure and only a portion of patients experience a placebo effect.
Nocebo
If medicine were a soap opera, the nocebo would be the evil twin of the placebo. It's what happens when patients have adverse side effects because of the expectation that they will. It's commonly seem when patients claims to experience pain or gastric distress that can occur with a drug even when they've received a placebo. The side effects were either imagined or caused by something else.
"Up to 97% of reported pharmaceutical side effects are not caused by the drug itself but rather by nocebo effects and symptom misattribution," according to one 2019 paper.
One way to reduce a nocebo response is to simply not tell patients that specific side effects might occur. An example is a liver biopsy, in which a large-gauge needle is used to extract a tissue sample for examination. Those told ahead of time that they might experience some pain were more likely to report pain and greater pain than those who weren't offered this information.
Interestingly, a nocebo response plays out in the hippocampus, a part of the brain that is never activated in a placebo response. "I think what we are dealing with with nocebo is anxiety," says Kaptchuk, but he acknowledges that others disagree.
Distraction may be another way to minimize the nocebo effect. Pediatricians are using virtual reality (VR) to engage children and distract them during routine procedures such as blood draws and changing wound dressings, and burn patients of all ages have found relief with specially created VRs.
Treatment response
Jonas argues that what we commonly call the placebo effect is misnamed and leading us astray. "The fact is people heal and that inherent healing capacity is both powerful and influenced by mental, social, and contextual factors that are embedded in every medical encounter since the idea of treatment began," he wrote in a 2019 article in the journal Frontiers in Psychiatry. "Our understanding of healing and ability to enhance it will be accelerated if we stop using the term 'placebo response' and call it what it is—the meaning response, and its special application in medicine called the healing response."
He cites evidence that "only 15% to 20% of the healing of an individual or a population comes from health care. The rest—nearly 80%—comes from other factors rarely addressed in the health care system: behavioral and lifestyle choices that people make in their daily life."
To better align treatments and maximize their effectiveness, Jonas has created HOPE (Healing Oriented Practices & Environments) Note, "a patient-guided process designed to identify the patient's values and goals in their life and for healing." Essentially, it seeks to make clear to both doctor and patient what the patient's goals are in seeking treatment. In an extreme example of terminal cancer, some patients may choose to extend life despite the often brutal treatments, while others might prefer to optimize quality of life in the remaining time that they have. It builds on practices already taught in medical schools. Jonas believes doctors and patients can use tools like these to maximize the treatment response and achieve better outcomes.
Much of the medical profession has been resistant to these approaches. Part of that is simply tradition and limited data on their effectiveness, but another very real factor is the billing process for how they are reimbursed. Jonas says a new medical billing code added this year gives doctors another way to be compensated for the extra time and effort that a more holistic approach to medicine may initially require. Other moves away from fee-for-service payments to bundling and payment for outcomes, and the integrated care provided by the Veterans Affairs, Kaiser Permanente and other groups offer longer term hope for the future of approaches that might enhance the healing response.
The Women of RNA: Two Award-Winners Share Why They Spent Their Careers Studying DNA's Lesser-Known Cousin
When Lynne Maquat, who leads the Center for RNA Biology at the University of Rochester, became interested in the ribonucleic acid molecule in the 1970s, she was definitely in the minority. The same was true for Joan Steitz, now professor of molecular biophysics and biochemistry at Yale University, who began to study RNA a decade earlier in the 1960s.
"My first RNA experiment was a failure, because we didn't understand how things worked," Steitz recalls. In her first undergraduate experiment, she unwittingly used a lab preparation that destroyed the RNA. "Unknowingly, our preparation contained enzymes that degraded our RNA."
At the time, scientists pursuing genetic research tended to focus on DNA, or deoxyribonucleic acid — and for good reason. It was clear that the enigmatic double-helix ribbon held the answers to organisms' heredity, genetic traits, development, growth and aging. If scientists could decipher the secrets of DNA and understand how its genetic instructions translate into the body's functions in health and disease, they could develop treatments for all kinds of diseases. On the contrary, the prevailing dogma of the time viewed RNA as merely a helper that passively carried out DNA's genetic instructions for protein-making — so it received much less attention.
But Maquat and Steitz weren't interested in heredity. They studied biochemistry and biophysics, so they wanted to understand how RNA functioned on the molecular level — how it carried instructions, catalyzed reactions, and helped build protein bonds, among other things.
"I'm a mechanistic biochemist, so I like to know how things happen," Maquat says. "Once you understand the mechanism, you can think of how to solve problems." And so the quest to understand how RNA does its job became the focus of both women's careers.
"People can now appreciate why some of us studied RNA for such a long time."
Half a century later, in 2021, their RNA work has earned two prestigious recognitions only months from each other. In February, they received the Wolf Prize in Medicine, followed by the Warren Alpert Foundation Prize in May, awarded to scientists whose achievements led to prevention, cure or treatments of human diseases.
It was the development of the COVID-19 vaccines that made RNA a household name. Made by Moderna and Pfizer, the vaccines use the RNA molecule to deliver genetic instructions for making SARS-CoV-2's characteristic spike protein in our cells. The presence of this foreign-looking protein triggers the immune system to attack and remember the pathogen. As the vaccines reached the finish line, RNA took center stage, and it was Maquat's and Steitz's research that helped reveal how these molecular cogwheels drive many biological functions within cells.
If you think of a cell as a kingdom, the DNA plays the role of a queen. Like a monarch in a palace, DNA nestles inside the cell's nucleus issuing instructions needed for the cell to function. But no queen can successfully govern without her court, her messengers, and her soldiers, as well as other players that make her kingdom work. That's what RNAs do — they act as the DNA's vassals. They carry instructions for protein assembly, catalyze reactions and supervise many other processes to make sure the cellular kingdom performs as it should.
There are a myriad of these RNA vassals in our cells, and each type has its own specific task. There are messenger RNAs that deliver genetic instructions for protein synthesis from DNA to ribosomes, the cells' protein-making factories. There are ribosomal RNAs that help stitch together amino acids to make proteins. There are transfer RNAs that can bring amino acids to this protein synthesis machine, keeping it going. Then there are circular RNAs that act as sponges, absorbing proteins to help regulate the activity of genes. And that's only the tip of the iceberg when it comes to RNA diversity, researchers say.
"We know what the most abundant and important RNAs are doing," says Steitz. "But there are thousands of different ones, and we still don't have a full knowledge of them."
Critical to RNA's proper functioning is a process called splicing, in which a precursor mRNA is transformed into mature, fully-functional mRNA — a phenomenon that Steitz's work helped elucidate. The splicing process, which takes place in cellular assembly lines, involves removing extra RNA sequences and stringing the remaining RNA pieces together. Steitz found that tiny RNA particles called snRNPs are crucial to this process. They act as handy helpers, finding and removing errant genetic material from the mRNA molecules.
A dysfunctional RNA assembly line leads to diseases, including many cancers. For instance, Steitz found that people with Lupus — an autoimmune disorder — have antibodies that mistakenly attack the little snRNP helpers. She also discovered that when snRNPs don't do their job properly, they can cause what scientists call mis-splicing, producing defective mRNAs.
Fortunately, cells have a built-in quality-control process that can spot and correct these mistakes, which is what Maquat studied in her work. In 1981, she discovered a molecular quality-control system that spots and destroys such incorrectly assembled mRNA. With the cryptic name "nonsense-mediated mRNA decay" or NMD, this process is vital to the health and wellbeing of a cellular kingdom in humans — because splicing mistakes happen far more often than one would imagine.
"We estimate that about a third of our mRNA are mistakes," Maquat says. "And nonsense-mediated mRNA decay cleans up these mistakes." When this quality-control system malfunctions, defective mRNA forge faulty proteins, which mess up the cellular machinery and cause disease, including various forms of cancer.
Scientists' newfound appreciation of RNA opens door to many novel treatments.
Now that the first RNA-based shots were approved, the same principle can be used for create vaccines for other diseases, the two RNA researchers say. Moreover, the molecule has an even greater potential — it can serve as a therapeutic target for other disorders. For example, Spinraza, a groundbreaking drug approved in 2016 for spinal muscular atrophy, uses small snippets of synthetic genetic material that bind to the RNA, helping fix splicing errors. "People can now appreciate why some of us studied RNA for such a long time," says Maquat.
Steitz is thrilled that the entire field of RNA research is enjoying the limelight. "I'm delighted because the prize is more of a recognition of the field than just our work," she says. "This is a more general acknowledgment of how basic research can have a remarkable impact on human health."
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.