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."
A new way to help kids with ADHD: Treat adult ADHD
Adults who have ADHD can benefit from treatment, and some researchers think their kids' ADHD symptoms may get better as a result.
When a child is diagnosed with attention deficit hyperactivity disorder (ADHD), it can often be a surprise to the parents that one of them has ADHD as well. They may have experienced some of the symptoms but never had the condition diagnosed.
Physicians, however, are usually less surprised because they know that ADHD is a very heritable disorder. According to a 2015 study, if a parent has ADHD, the child has up to a 57 percent chance of having it, and the child’s risk is 32 percent if their sibling has it.
“There have been 20 to 30 twin studies that show that the heritability of ADHD is about 70 percent,” meaning that both twins have it, says Stephen Faraone, distinguished professor and vice chair for research at SUNY Upstate Medical University. “It is as heritable as schizophrenia, bipolar disorder, autism or other psychiatric disorders that people tend to think are more biological than ADHD for some reason.”
More attention needed for adult ADHD
Brad McAlister, CMSE, executive director of the American Professional Society of ADHD & Related Disorders, or APSARD, explains that the consequences of untreated ADHD in adults are very well documented. The prevalence of ADHD in U.S. adults is 4.4 percent or about 11 million people.
Many adults go undiagnosed for decades or are misdiagnosed by providers. McAlister says that 75 percent are not receiving treatment. “The U.S. economic burden of adult ADHD is $105 to $194 billion annually,” he says. “The negative consequences on peoples’ lives include higher risks of dropping out of school, losing jobs, financial debt, divorce, fractured relationships, substance use disorders, and co-occurring depression/anxiety.”
One of the negative impacts of undiagnosed ADHD in adults is the effect that it can have on their children who have ADHD.
Adult ADHD is currently treated by a broad range of health care providers with different educational backgrounds and in different practice settings. In August, APSARD published the first U.S. guidelines for adult ADHD. “The creation of guidelines for ADHD in adults will allow all practitioners to benefit from the best evidence about diagnosing and treating the disorder,” McAlister says.
Faraone explains that the guidelines are intended to help practitioners understand the best practices for adults with ADHD, including screening and other ways of evaluating whether someone has it. He recently completed a study of what he calls the Metrics of Quality Care for adults with ADHD.
“We looked at a sizable group of primary care practices in the U.S., and we learned that although quality care for adults with ADHD has been gradually improving over the past decade, there are many areas where it is still far behind where it needs to be,” he says. “That’s consistent with other studies that show that in primary care for adults, ADHD is not treated nearly as well as it is treated in specialty and psychiatry care.”
How kids with ADHD are affected
One of the negative impacts of undiagnosed ADHD in adults is the effect that it can have on their children who have ADHD because their ability to care for that child’s special needs may be impaired.
“The treatments that are most effective in treating children with ADHD are medication and behavioral interventions as their reward bait, and at home, it’s the parent that administers them,” says Mark A. Stein, director of the ADHD and Related Disorders Program at Seattle Children’s Hospital. “Adults with ADHD have difficulties with time management and organization skills, so they will have a hard time making sure their child is ready for school, has breakfast, has their medications, etcetera.”
Even more challenging than getting a prescription, Stein adds, is finding a psychologist or therapist who is skilled in evaluating and working with children with ADHD and their parents. If left undiagnosed and untreated, adult ADHD may also interfere with getting a good evaluation for the child.
“If you have ADHD and your mind is wandering and you don’t have all of the forms from the school for your provider, and you’re focused on the bad day you’re having rather than giving a history of your child, all of that is going to delay getting an effective treatment for your child,” Stein says. “So that’s why it’s important to identify ADHD in parents.”
Promising research and training
After delays due to the pandemic, Stein and his colleague Andrea Chronis-Tuscano, professor and director of the Maryland ADHD Program at the University of Maryland, are now about two years into what they anticipate will be a six-year study that involves treating parents who have children with untreated ADHD symptoms. The goal is to see whether treating the parent first with medication and training, or just the training, helps the child’s symptoms due to improved parenting. They are also studying whether they can postpone the need for medication until children are older, when it’s more effective.
“Pediatricians are more aware of ADHD in parents because of our study,” Stein says. “They’re also more aware of the shortcomings in our healthcare delivery system in terms of how hard it is to find providers who are comfortable treating adult ADHD.”
“Besides depression, ADHD is the other disorder that parents have that really impacts kids significantly," Stein says. “With treatment, many people with ADHD do very well."
That said, he’s seen a significant improvement in the past decade with increased recognition of ADHD in adults. “It started with pediatricians recognizing that post-partum depression impacted the mother’s ability to care for her children and making it routine to screen for depression in parents of kids,” he says. “Besides depression, ADHD is the other disorder that parents have that really impacts kids significantly, so it’s important for them to be aware of characteristics of [ADHD in] parents and have resources they can give parents to help them.”
Stein emphasizes that even if someone displays symptoms of ADHD, that does not mean that they have it. They should seek a physician’s evaluation to confirm a diagnosis, which would enable them to get the medication and behavioral treatment they need.
The medication can take effect in parents within an hour. Meanwhile, when parents participate in the behavioral parent training courses, their kids with ADHD start showing significant improvement within about four to five weeks, according to Stein.
“With treatment, many people with ADHD do very well,” he says. “Especially if they get through formal schooling, find the right fit with their job, and if they make the right choices with their relationships, those three things can go a long way to make their ADHD fade into the background.”
Patients voice hope and relief as FDA gives third-ever drug approval for ALS
On Sept. 29, the FDA approved Relyvrio, a new drug for ALS, even though a study of 137 ALS patients did not result in “substantial evidence” that Relyvrio was effective.
At age 52, Glen Rouse suffered from arm weakness and a lot of muscle twitches. “I first thought something was wrong when I could not throw a 50-pound bag of dog food over the tailgate of my truck—something I use to do effortlessly,” said the 54-year-old resident of Anderson, California, about three hours north of San Francisco.
In August, Rouse retired as a forester for a private timber company, a job he had held for 31 years. The impetus: amyotrophic lateral sclerosis, or ALS, a progressive neuromuscular disease that is commonly known as Lou Gehrig’s disease, named after the New York Yankees’ first baseman who succumbed to it less than a month shy of his 38th birthday in 1941. ALS eventually robs an individual of the ability to talk, walk, chew, swallow and breathe.
Rouse is now dependent on ventilation through a nasal mask and uses a powerchair to get around. “I can no longer walk or use my arms very well,” he said. “I can still move my wrists and fingers. I can also transfer from my chair to the toilet if I have two of my friends help me.”
It’s “shocking” that modern medicine has very little to offer to people with this devastating condition, Rouse said. But there is hope on the horizon. Yesterday, the U.S. Food and Drug Administration approved Relyvrio, a drug made up of two parts, sodium phenylbutyrate and taurursodiol, to treat patients with ALS.
“This approval provides another important treatment option for ALS, a life-threatening disease that currently has no cure,” said Billy Dunn, director of the Office of Neuroscience in the FDA’s Center for Drug Evaluation and Research, in a statement. “The FDA remains committed to facilitating the development of additional ALS treatments.”
Until this point, the FDA had approved only two other medications—Riluzole (rilutek) in 1995 and Radicava (edaravone) in 2017—to extend life in patients with ALS, which typically kills within two to five years after diagnosis. That’s why earlier this week, Rouse was optimistic about the FDA’s likely approval of a controversial new drug for ALS.
When Relyvrio is taken in addition to Riluzole, it appears to slow functional decline by an additional 25 percent and extend life by another 6 to 10 months, said Richard Bedlak, director of the Duke ALS Clinic. “It is not a cure, but it is definitely a step forward.”
“The whole ALS community is extremely excited about it,” he said the day before Relyvrio’s expected approval. “We are very hopeful. We’re on pins and needles.”
A study of 137 ALS patients did not result in “substantial evidence” that Relyvrio was effective, the agency’s Peripheral and Central Nervous System Drugs Advisory Committee concluded in March. However, after some persuasion from FDA officials, patients and their families, the committee met again and decided to recommend approving the drug.
In January 2019, following an ALS diagnosis at age 58 in October the previous year, Jeff Sarnacki, of Chester, Maryland, was accepted into a trial for Relyvrio. “Because of the trial, we did experience hope and a greater sense of help than had we not had that opportunity,” said Juliet Taylor, his wife and caregiver. They both believed the drug “worked for him in giving him more time.”
In June 2019, Sarnacki chose an open-label extension, offered to patients by drug researchers after a study ends, and took the active drug until he died peacefully at home under hospice care in May 2020, five days after his 60th birthday. A retired agent with the federal Bureau of Alcohol, Tobacco, Firearms and Explosives who later worked as a security consultant, Sarnacki lived about 19 months after diagnosis, which is shorter than the typical prognosis.
His symptoms began with leg cramps in fall 2017 and foot drop in early 2018. A feeding tube was placed in 2019, as it became necessary early in his illness, Taylor said. He also took Radicava and Riluzole, the two previously approved drugs, for his ALS. “We were both incredulous that, so many years after Lou Gehrig’s own diagnosis, there were so few treatments available,” she said.
The dearth of successful treatments for ALS is “certainly not for lack of trying,” said Karen Raley Steffens, a registered nurse and ALS support services coordinator at the Les Turner ALS Foundation in Skokie, Ill. “There are thousands of researchers and scientists all over the world working tirelessly to try to develop treatments for ALS.”
Unfortunately, she added, research takes time and exorbitant amounts of funding, while bureaucratic challenges persist. The rare disease also manifests and progresses in many different ways, so many treatments are needed.
As of 2017, the Centers for Disease Control and Prevention estimated that more than 31,000 people in the U.S. live with ALS, and an average of 5,000 people are newly diagnosed every year. It is slightly more common in men than women. Most people are diagnosed between the ages of 55 and 75.
Most cases of ALS are sporadic, meaning that doctors don’t know the cause. There is about a one-year interval between symptom onset and an ALS diagnosis for most patients, so many motor neurons are lost by the time individuals can enroll in a clinical trial, said Richard Bedlack, professor of neurology and director of the Duke ALS Clinic in Durham, North Carolina.
Bedlack found the new drug, Relyvrio, to be “very promising,” which is why he testified to the FDA in favor of approval. (He’s a consultant and disease state speaker for multiple companies including Amylyx, manufacturer of Relyvrio.)
The “drug has different mechanisms of action than the currently approved treatments,” Bedlack said. He added that, when Relyvrio is taken in addition to Riluzole, it appears to slow functional decline by an additional 25 percent and extend life by another 6 to 10 months. “It is not a cure, but it is definitely a step forward.”
T. Scott Diesing, a neurohospitalist and director of general neurology at the University of Nebraska Medical Center in Omaha, said he hopes the drug is “as good as people anticipated it should be, because there are not too many options for these patients.”
"FDA went out on a limb in approving Relyvrio based on limited results from a small trial while a larger study remains in progress," said Florian P. Thomas, co-director of the ALS Center at Hackensack University Medical Center and Hackensack Meridian School of Medicine in New Jersey. "While it is definitely promising, clearly, the last word on this drug has not been spoken."
So far, Rouse's voice is holding up, but he knows the day will come when ALS will steal that and much more from him.
ALS is 100 percent fatal, with some patients dying as soon as a year after diagnosis. A few have lasted as long as 15 years, but those are the exceptions, Diesing said.
“If this drug can provide even months of additional life, or would maintain quality of life, that’s a big deal,” he noted, adding that “the patients are saying, ‘I know it’s not proven conclusively, but what do we have to lose?’ So, they would like to try it while additional studies are ongoing.” The drug has already been conditionally approved in Canada.
As his disease progresses, Rouse hopes to get a speech-to-text voice-generating computer that he can control with his eyes. So far, his voice is holding up, but he knows the day will come when ALS will steal that and much more from him. He works at I AM ALS, a patient-led community, and six of his friends have already died of the disease.
“Every time I lose a friend to ALS, I grieve and am sad but I resolve myself to keep working harder for them, myself and others,” Rouse said. “People living with ALS find great purpose in life advocating and trying to make a difference.”