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."
How dozens of men across Alaska (and their dogs) teamed up to save one town from a deadly outbreak
In 1925, health officials in Alaska came up with a creative solution to save a remote fishing town from a deadly disease outbreak.
During the winter of 1924, Curtis Welch – the only doctor in Nome, a remote fishing town in northwest Alaska – started noticing something strange. More and more, the children of Nome were coming to his office with sore throats.
Initially, Welch dismissed the cases as tonsillitis or some run-of-the-mill virus – but when more kids started getting sick, with some even dying, he grew alarmed. It wasn’t until early 1925, after a three-year-old boy died just two weeks after becoming ill, that Welch realized that his worst suspicions were true. The boy – and dozens of other children in town – were infected with diphtheria.
A DEADLY BACTERIA
Diphtheria is nearly nonexistent and almost unheard of in industrialized countries today. But less than a century ago, diphtheria was a household name – one that struck fear in the heart of every parent, as it was extremely contagious and particularly deadly for children.
Diphtheria – a bacterial infection – is an ugly disease. When it strikes, the bacteria eats away at the healthy tissues in a patient’s respiratory tract, leaving behind a thick, gray membrane of dead tissue that covers the patient's nose, throat, and tonsils. Not only does this membrane make it very difficult for the patient to breathe and swallow, but as the bacteria spreads through the bloodstream, it causes serious harm to the heart and kidneys. It sometimes also results in nerve damage and paralysis. Even with treatment, diphtheria kills around 10 percent of people it infects. Young children, as well as adults over the age of 60, are especially at risk.
Welch didn’t suspect diphtheria at first. He knew the illness was incredibly contagious and reasoned that many more people would be sick – specifically, the family members of the children who had died – if there truly was an outbreak. Nevertheless, the symptoms, along with the growing number of deaths, were unmistakable. By 1925 Welch knew for certain that diphtheria had come to Nome.
In desperation, Welch tried treating an infected seven-year-old girl with some expired antitoxin – but she died just a few hours after he administered it.
AN INACCESSIBLE CURE
A vaccine for diphtheria wouldn’t be widely available until the mid-1930s and early 1940s – so an outbreak of the disease meant that each of the 10,000 inhabitants of Nome were all at serious risk.
One option was to use something called an antitoxin – a serum consisting of anti-diphtheria antibodies – to treat the patients. However, the town’s reserve of diphtheria antitoxin had expired. Welch had ordered a replacement shipment of antitoxin the previous summer – but the shipping port that was set to deliver the serum had been closed due to ice, and no new antitoxin would arrive before spring of 1925. In desperation, Welch tried treating an infected seven-year-old girl with some expired antitoxin – but she died just a few hours after he administered it.
Welch radioed for help to all the major towns in Alaska as well as the US Public Health Service in Washington, DC. His telegram read: An outbreak of diphtheria is almost inevitable here. I am in urgent need of one million units of diphtheria antitoxin. Mail is the only form of transportation.
FOUR-LEGGED HEROES
When the Alaskan Board of Health learned about the outbreak, the men rushed to devise a plan to get antitoxin to Nome. Dropping the serum in by airplane was impossible, as the available planes were unsuitable for flying during Alaska’s severe winter weather, where temperatures were routinely as cold as -50 degrees Fahrenheit.
In late January 1925, roughly 30,000 units of antitoxin were located in an Anchorage hospital and immediately delivered by train to a nearby city, Nenana, en route to Nome. Nenana was the furthest city that was reachable by rail – but unfortunately it was still more than 600 miles outside of Nome, with no transportation to make the delivery. Meanwhile, Welch had confirmed 20 total cases of diphtheria, with dozens more at high risk. Diphtheria was known for wiping out entire communities, and the entire town of Nome was in danger of suffering the same fate.
It was Mark Summer, the Board of Health superintendent, who suggested something unorthodox: Using a relay team of sled-racing dogs to deliver the antitoxin serum from Nenana to Nome. The Board quickly voted to accept Summer’s idea and set up a plan: The thousands of units of antitoxin serum would be passed along from team to team at different towns along the mail route from Nenana to Nome. When it reached a town called Nulato, a famed dogsled racer named Leonhard Seppala and his experienced team of huskies would take the serum more than 90 miles over the ice of Norton Sound, the longest and most treacherous part of the journey. Past the sound, the serum would change hands several times more before arriving in Nome.
Between January 27 and 31, the serum passed through roughly a dozen drivers and their dog sled teams, each of them carrying the serum between 20 and 50 miles to the next destination. Though each leg of the trip took less than a day, the sub-zero temperatures – sometimes as low as -85 degrees – meant that every driver and dog risked their lives. When the first driver, Bill Shannon, arrived at his checkpoint in Tolovana on January 28th, his nose was black with frostbite, and three of his dogs had died. The driver who relieved Bill Shannon, named Edgar Kalland, needed the owner of a local roadhouse to pour hot water over his hands to free them from the sled’s metal handlebar. Two more dogs from another relay team died before the serum was passed to Seppala at a town called Ungalik.
THE FINAL STRETCHES
Seppala and his team raced across the ice of the Norton Sound in the dead of night on January 31, with wind chill temperatures nearing an astonishing -90 degrees. The team traveled 84 miles in a single day before stopping to rest – and once rested, they set off again in the middle of the night through a raging winter storm. The team made it across the ice, as well as a 5,000-foot ascent up Little McKinley Mountain, to pass the serum to another driver in record time. The serum was now just 78 miles from Nome, and the death toll in town had reached 28.
The serum reached Gunnar Kaasen and his team of dogs on February 1st. Balto, Kaasen’s lead dog, guided the team heroically through a winter storm that was so severe Kaasen later reported not being able to see the dogs that were just a few feet ahead of him.
Visibility was so poor, in fact, that Kaasen ran his sled two miles past the relay point before noticing – and not wanting to lose a minute, he decided to forge on ahead rather than doubling back to deliver the serum to another driver. As they continued through the storm, the hurricane-force winds ripped past Kaasen’s sled at one point and toppled the sled – and the serum – overboard. The cylinder containing the antitoxin was left buried in the snow – and Kaasen tore off his gloves and dug through the tundra to locate it. Though it resulted in a bad case of frostbite, Kaasen eventually found the cylinder and kept driving.
Kaasen arrived at the next relay point on February 2nd, hours ahead of schedule. When he got there, however, he found the relay driver of the next team asleep. Kaasen took a risk and decided not to wake him, fearing that time would be wasted with the next driver readying his team. Kaasen, Balto, and the rest of the team forged on, driving another 25 miles before finally reaching Nome just before six in the morning. Eyewitnesses described Kaasen pulling up to the town’s bank and stumbling to the front of the sled. There, he collapsed in exhaustion, telling onlookers that Balto was “a damn fine dog.”
A LIVING LEGACY
Just a few hours after Balto’s heroic arrival in Nome, the serum had been thawed and was ready to administer to the patients with diphtheria. Amazingly, the relay team managed to complete the entire journey in just 127 hours – a world record at the time – without one serum vial damaged or destroyed. The serum shipment that arrived by dogsled – along with additional serum deliveries that followed in the next several weeks – were successful in stopping the outbreak in its tracks.
Balto and several other dogs – including Togo, the lead dog on Seppala’s team – were celebrated as local heroes after the race. Balto died in 1933, while the last of the human serum runners died in 1999 – but their legacy lives on: In early 2021, an all-female team of healthcare workers made the news by braving the Alaskan winter to deliver COVID-19 vaccines to people in rural North Alaska, traveling by bobsled and snowmobile – a heroic journey, and one that would have been unthinkable had Balto, Togo, and the 1925 sled runners not first paved the way.
Jacob Brenner and his partners at the University of Pennsylvania's Perelman School of Medicine are finding new ways to get nanomedicines to arrive at their targets.
Its strength is in its lack of size.
Using materials on the minuscule scale of nanometers (billionths of a meter), nanomedicines have the ability to provide treatment more precise than any other form of medicine. Under optimal circumstances, they can target specific cells and perform feats like altering the expression of proteins in tumors so that the tumors shrink.
Another appealing concept about nanomedicine is that treatment on a nano-scale, which is smaller yet than individual cells, can greatly decrease exposure to parts of the body outside the target area, thereby mitigating side effects.
But this young field's huge potential has met with an ongoing obstacle: the recipient's immune system tends to regard incoming nanomedicines as a threat and launches a complement protein attack. These complement proteins, which act together through a wave of reactions to get rid of troubling microorganisms, have had more than 500 million years to refine their craft, so they are highly effective.
Seeking to overcome a half-billion-year disadvantage, nanomaterials engineers have tried such strategies as creating so-called stealth nanoparticles.
“All new technologies face technical barriers, and it is the job of innovators to engineer solutions to them,” Brenner says.
Despite these clever attempts, nanomedicines largely keep failing to arrive at their intended destinations. According to the most comprehensive meta-analysis of nanomedicines in oncology, fewer than 1 percent of nanoparticles manage to reach their targets. The remaining 99-plus percent are expelled to the liver, spleen, or lungs – thereby squandering their therapeutic potential. Though these numbers seem discouraging, systems biologist Jacob Brenner remains undaunted. “All new technologies face technical barriers, and it is the job of innovators to engineer solutions to them,” he says.
Brenner and his fellow researchers at the Perelman School of Medicine at the University of Pennsylvania have recently devised a method that, in a study published in late 2021 involving sepsis-afflicted mice, saw a longer half-life of nanoparticles in the bloodstream. This effect is crucial because “the longer our nanoparticles circulate, the more time they have to reach their target organs,” says Brenner, the study's co-principal investigator. He works as a critical care physician at the Hospital of the University of Pennsylvania, where he also serves as an assistant professor of medicine.
The method used by Brenner's lab involves coating nanoparticles with natural suppressors that safeguard against a complement attack from the recipient's immune system. For this idea, he credits bacteria. “They are so much smarter than us,” he says.
Brenner points out that many species of bacteria have learned to coat themselves in a natural complement suppressor known as Factor H in order to protect against a complement attack.
Humans also have Factor H, along with an additional suppressor called Factor I, both of which flow through our blood. These natural suppressors “are recruited to the surface of our own cells to prevent complement [proteins] from attacking our own cells,” says Brenner.
Coating nanoparticles with a natural suppressor is a “very creative approach that can help tone and improve the activity of nanotechnology medicines inside the body,” says Avi Schroeder, an associate professor at Technion - Israel Institute of Technology, where he also serves as Head of the Targeted Drug Delivery and Personalized Medicine Group.
Schroeder explains that “being able to tone [down] the immune response to nanoparticles enhances their circulation time and improves their targeting capacity to diseased organs inside the body.” He adds how the approach taken by the Penn Med researchers “shows that tailoring the surface of the nanoparticles can help control the interactions the nanoparticles undergo in the body, allowing wider and more accurate therapeutic activity.”
Brenner says he and his research team are “working on the engineering details” to streamline the process. Such improvements could further subdue the complement protein attacks which for decades have proven the bane of nanomedical engineers.
Though these attacks have limited nanomedicine's effectiveness, the field has managed some noteworthy successes, such as the chemotherapy drugs Abraxane and Doxil, the first FDA-approved nanomedicine.
And amid the COVID-19 pandemic, nanomedicines became almost universally relevant with the vast circulation of the Moderna and Pfizer-BioNTech vaccines, both of which consist of lipid nanoparticles. “Without the nanoparticle, the mRNA would not enter the cells effectively and would not carry out the therapeutic goal,” Schroeder explains.
These vaccines, though, are “just the start of the potential transformation that nanomedicine will bring to the world,” says Brenner. He relates how nanomedicine is “joining forces with a number of other technological innovations,” such as cell therapies in which nanoparticles aim to reprogram T-cells to attack cancer.
With a similar degree of optimism, Schroeder says, “We will see further growing impact of nanotechnologies in the clinic, mainly by enabling gene therapy for treating and even curing diseases that were incurable in the past.”
Brenner says that in the next 10 to 15 years, “nanomedicine is likely to impact patients” contending with a “huge diversity” of conditions. “I can't wait to see how it plays out.”