The Algorithm Will See You Now
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."
Doug Olson was 49 when he was diagnosed with chronic lymphocytic leukemia, a blood cancer that strikes 21,000 Americans annually. Although the disease kills most patients within a decade, Olson’s case progressed more slowly, and courses of mild chemotherapy kept him healthy for 13 years. Then, when he was 62, the medication stopped working. The cancer had mutated, his doctor explained, becoming resistant to standard remedies. Harsher forms of chemo might buy him a few months, but their side effects would be debilitating. It was time to consider the treatment of last resort: a bone-marrow transplant.
Olson, a scientist who developed blood-testing instruments, knew the odds. There was only a 50 percent chance that a transplant would cure him. There was a 20 percent chance that the agonizing procedure—which involves destroying the patient’s marrow with chemo and radiation, then infusing his blood with donated stem cells—would kill him. If he survived, he would face the danger of graft-versus-host disease, in which the donor’s cells attack the recipient’s tissues. To prevent it, he would have to take immunosuppressant drugs, increasing the risk of infections. He could end up with pneumonia if one of his three grandchildren caught a sniffle. “I was being pushed into a corner,” Olson recalls, “with very little room to move.”
Soon afterward, however, his doctor revealed a possible escape route. He and some colleagues at the University of Pennsylvania’s Abramson Cancer Center were starting a clinical trial, he said, and Olson—still mostly symptom-free—might be a good candidate. The experimental treatment, known as CAR-T therapy, would use genetic engineering to turn his T lymphocytes (immune cells that guard against viruses and other pathogens) into a weapon against cancer.
In September 2010, technicians took some of Olson’s T cells to a laboratory, where they were programmed with new molecular marching orders and coaxed to multiply into an army of millions. When they were ready, a nurse inserted a catheter into his neck. At the turn of a valve, his soldiers returned home, ready to do battle.
“I felt like I’d won the lottery,” Olson says. But he was only the second person in the world to receive this “living drug,” as the University of Pennsylvania investigators called it. No one knew how long his remission would last.
Three weeks later, Olson was slammed with a 102-degree fever, nausea, and chills. The treatment had triggered two dangerous complications: cytokine release syndrome, in which immune chemicals inflame the patient’s tissues, and tumor lysis syndrome, in which toxins from dying cancer cells overwhelm the kidneys. But the crisis passed quickly, and the CAR-T cells fought on. A month after the infusion, the doctor delivered astounding news: “We can’t find any cancer in your body.”
“I felt like I’d won the lottery,” Olson says. But he was only the second person in the world to receive this “living drug,” as the University of Pennsylvania investigators called it. No one knew how long his remission would last.
An Unexpected Cure
In February 2022, the same cancer researchers reported a remarkable milestone: the trial’s first two patients had survived for more than a decade. Although Olson’s predecessor—a retired corrections officer named Bill Ludwig—died of COVID-19 complications in early 2021, both men had remained cancer-free. And the modified immune cells continued to patrol their territory, ready to kill suspected tumor cells the moment they arose.
“We can now conclude that CAR-T cells can actually cure patients with leukemia,” University of Pennsylvania immunologist Carl June, who spearheaded the development of the technique, told reporters. “We thought the cells would be gone in a month or two. The fact that they’ve survived 10 years is a major surprise.”
Even before the announcement, it was clear that CAR-T therapy could win a lasting reprieve for many patients with cancers that were once a death sentence. Since the Food and Drug Administration approved June’s version (marketed as Kymriah) in 2017, the agency has greenlighted five more such treatments for various types of leukemia, lymphoma, and myeloma. “Every single day, I take care of patients who would previously have been told they had no options,” says Rayne Rouce, a pediatric hematologist/oncologist at Texas Children’s Cancer Center. “Now we not only have a treatment option for those patients, but one that could potentially be the last therapy for their cancer that they’ll ever have to receive.”
Immunologist Carl June, middle, spearheaded development of the CAR-T therapy that gave patients Bill Ludwig, left, and Doug Olson, right, a lengthy reprieve on their terminal cancer diagnoses.
Penn Medicine
Yet the CAR-T approach doesn’t help everyone. So far, it has only shown success for blood cancers—and for those, the overall remission rate is 30 to 40 percent. “When it works, it works extraordinarily well,” says Olson’s former doctor, David Porter, director of Penn’s blood and bone marrow transplant program. “It’s important to know why it works, but it’s equally important to know why it doesn’t—and how we can fix that.”
The team’s study, published in the journal Nature, offers a wealth of data on what worked for these two patients. It may also hold clues for how to make the therapy effective for more people.
Building a Better T Cell
Carl June didn’t set out to cure cancer, but his serendipitous career path—and a personal tragedy—helped him achieve insights that had eluded other researchers. In 1971, hoping to avoid combat in Vietnam, he applied to the U.S. Naval Academy in Annapolis, Maryland. June showed a knack for biology, so the Navy sent him on to Baylor College of Medicine. He fell in love with immunology during a fellowship researching malaria vaccines in Switzerland. Later, the Navy deployed him to the Fred Hutchinson Cancer Research Center in Seattle to study bone marrow transplantation.
There, June became part of the first research team to learn how to culture T cells efficiently in a lab. After moving on to the National Naval Medical Center in the ’80s, he used that knowledge to combat the newly emerging AIDS epidemic. HIV, the virus that causes the disease, invades T cells and eventually destroys them. June and his post-doc Bruce Levine developed a method to restore patients’ depleted cell populations, using tiny magnetic beads to deliver growth-stimulating proteins. Infused into the body, the new T cells effectively boosted immune function.
In 1999, after leaving the Navy, June joined the University of Pennsylvania. His wife, who’d been diagnosed with ovarian cancer, died two years later, leaving three young children. “I had not known what it was like to be on the other side of the bed,” he recalls. Watching her suffer through grueling but futile chemotherapy, followed by an unsuccessful bone-marrow transplant, he resolved to focus on finding better cancer treatments. He started with leukemia—a family of diseases in which mutant white blood cells proliferate in the marrow.
Cancer is highly skilled at slipping through the immune system’s defenses. T cells, for example, detect pathogens by latching onto them with receptors designed to recognize foreign proteins. Leukemia cells evade detection, in part, by masquerading as normal white blood cells—that is, as part of the immune system itself.
June planned to use a viral vector no one had tried before: HIV.
To June, chimeric antigen receptor (CAR) T cells looked like a promising tool for unmasking and destroying the impostors. Developed in the early ’90s, these cells could be programmed to identify a target protein, and to kill any pathogen that displayed it. To do the programming, you spliced together snippets of DNA and inserted them into a disabled virus. Next, you removed some of the patient’s T cells and infected them with the virus, which genetically hijacked its new hosts—instructing them to find and slay the patient’s particular type of cancer cells. When the T cells multiplied, their descendants carried the new genetic code. You then infused those modified cells into the patient, where they went to war against their designated enemy.
Or that’s what happened in theory. Many scientists had tried to develop therapies using CAR-T cells, but none had succeeded. Although the technique worked in lab animals, the cells either died out or lost their potency in humans.
But June had the advantage of his years nurturing T cells for AIDS patients, as well as the technology he’d developed with Levine (who’d followed him to Penn with other team members). He also planned to use a viral vector no one had tried before: HIV, which had evolved to thrive in human T cells and could be altered to avoid causing disease. By the summer of 2010, he was ready to test CAR-T therapy against chronic lymphocytic leukemia (CLL), the most common form of the disease in adults.
Three patients signed up for the trial, including Doug Olson and Bill Ludwig. A portion of each man’s T cells were reprogrammed to detect a protein found only on B lymphocytes, the type of white blood cells affected by CLL. Their genetic instructions ordered them to destroy any cell carrying the protein, known as CD19, and to multiply whenever they encountered one. This meant the patients would forfeit all their B cells, not just cancerous ones—but regular injections of gamma globulins (a cocktail of antibodies) would make up for the loss.
After being infused with the CAR-T cells, all three men suffered high fevers and potentially life-threatening inflammation, but all pulled through without lasting damage. The third patient experienced a partial remission and survived for eight months. Olson and Ludwig were cured.
Learning What Works
Since those first infusions, researchers have developed reliable ways to prevent or treat the side effects of CAR-T therapy, greatly reducing its risks. They’ve also been experimenting with combination therapies—pairing CAR-T with chemo, cancer vaccines, and immunotherapy drugs called checkpoint inhibitors—to improve its success rate. But CAR-T cells are still ineffective for at least 60 percent of blood cancer patients. And they remain in the experimental stage for solid tumors (including pancreatic cancer, mesothelioma, and glioblastoma), whose greater complexity make them harder to attack.
The new Nature study offers clues that could fuel further advances. The Penn team “profiled these cells at a level where we can almost say, ‘These are the characteristics that a T cell would need to survive 10 years,’” says Rouce, the physician at Texas Children’s Cancer Center.
One surprising finding involves how CAR-T cells change in the body over time. At first, those that Olson and Ludwig received showed the hallmarks of “killer” T-cells (also known as CD8 cells)—highly active lymphocytes bent on exterminating every tumor cell in sight. After several months, however, the population shifted toward “helper” T-cells (or CD4s), which aid in forming long-term immune memory but are normally incapable of direct aggression. Over the years, the numbers swung back and forth, until only helper cells remained. Those cells showed markers suggesting they were too exhausted to function—but in the lab, they were able not only to recognize but to destroy cancer cells.
June and his team suspect that those tired-looking helper cells had enough oomph to kill off any B cells Olson and Ludwig made, keeping the pair’s cancers permanently at bay. If so, that could prompt new approaches to selecting cells for CAR-T therapy. Maybe starting with a mix of cell types—not only CD8s, but CD4s and other varieties—would work better than using CD8s alone. Or perhaps inducing changes in cell populations at different times would help.
Another potential avenue for improvement is starting with healthier cells. Evidence from this and other trials hints that patients whose T cells are more robust to begin with respond better when their cells are used in CAR-T therapy. The Penn team recently completed a clinical trial in which CLL patients were treated with ibrutinib—a drug that enhances T-cell function—before their CAR-T cells were manufactured. The response rate, says David Porter, was “very high,” with most patients remaining cancer-free a year after being infused with the souped-up cells.
Such approaches, he adds, are essential to achieving the next phase in CAR-T therapy: “Getting it to work not just in more people, but in everybody.”
Doug Olson enjoys nature - and having a future.
Penn Medicine
To grasp what that could mean, it helps to talk with Doug Olson, who’s now 75. In the years since his infusion, he has watched his four children forge careers, and his grandkids reach their teens. He has built a business and enjoyed the rewards of semi-retirement. He’s done volunteer and advocacy work for cancer patients, run half-marathons, sailed the Caribbean, and ridden his bike along the sun-dappled roads of Silicon Valley, his current home.
And in his spare moments, he has just sat there feeling grateful. “You don’t really appreciate the effect of having a lethal disease until it’s not there anymore,” he says. “The world looks different when you have a future.”
What makes people turn against science? After two years of a global pandemic, the world has never felt more divided on questions of science. But this is not a new phenomenon. People have resisted scientific and technological advances throughout history.
This video by Leaps.org, with support from the Gordon and Betty Moore Foundation, captures noteworthy examples from history when people rejected science. What do these cases have in common? Scientific breakthroughs can be revolutionary, but revolutions can be disorienting and anxiety-producing. They transform our livelihoods, culture and even our understanding of what it means to be human. But there's reason for optimism. Many of history’s controversies were overcome. Science has a way of enduring, because it changes things for the better.