Connect with us

Science

Opinion: It's not just hype. AI could revolutionize diagnosis in medicine

Published

on

Opinion: It's not just hype. AI could revolutionize diagnosis in medicine

The history of medical diagnosis is a march through painstaking observation. Ancient Egyptian physicians first diagnosed urinary tract infections by observing patterns in patients’ urine. To diagnose diseases of the heart and lungs, medieval doctors added core elements of the physical examination: pulse, palpation and percussion. The 20th century saw the addition of laboratory studies, and the 21st century of sophisticated imaging and genetics.

Despite advances, however, diagnosis has largely remained a human endeavor, with doctors relying on so-called illness scripts — clusters of signs, symptoms and diagnostic findings that are hallmarks of a disease. Medical students spend years memorizing such scripts, training themselves to, for example, identify the sub-millimeter variations in electrocardiogram wave measurements that might alert them to a heart attack.

But human beings, of course, err. Sometimes, misdiagnosis occurs because a doctor overlooks something — when the patterns of illness fit the script, but the script is misread. This happens in an estimated 15% to 20% of medical encounters. Other times, misdiagnosis occurs because the illness has features that do not match known patterns — they do not fit the script, such as when a heart attack occurs without telltale symptoms or EKG findings.

Artificial intelligence can help solve these two fundamental problems — if it’s given enough financial support and deployed correctly.

First, AI is less susceptible to common factors that lead doctors to make diagnostic errors: fatigue, lack of time and cognitive bandwidth when treating many patients, gaps of knowledge and reliance on mental shortcuts. Even when illnesses conform to scripts, computers will sometimes be better than humans at identifying details buried within voluminous healthcare data.

Advertisement

Using AI to improve the accuracy and timeliness with which doctors recognize illness can mean the difference between life and death. Ischemic stroke, for example, is a life-threatening emergency where a blocked artery impedes blood flow to the brain. Brain imaging clinches the diagnosis, but that imaging must be performed and interpreted by a radiologist quickly and accurately. Studies show that AI, through superhuman pattern matching abilities, can identify strokes seconds after imaging is performed — tens of minutes sooner than by often-busy radiologists. Similar capabilities have been demonstrated in diagnosing sepsis, pneumonia, blood clot in the lungs (pulmonary embolism), acute kidney injury and other conditions.

Second, computers can be useful for illnesses for which we haven’t developed the right scripts. AI can, in fact, diagnose disease using new patterns too subtle for humans to identify. Consider, for example, hypertrophic cardiomyopathy, a rare genetic condition in which the heart’s muscle has grown more than it should, leading to eventual heart failure and sometimes death. Experts estimate that only 20% of those affected are diagnosed, a process that requires consultation with a cardiologist, a heart ultrasound and often genetic testing. What, then, of the remaining 80%?

Researchers across the country, including at the Mayo Clinic and UC San Francisco, have demonstrated that AI can detect complex, previously unrecognized patterns to identify patients likely to have hypertrophic cardiomyopathy, meaning AI-driven algorithms will be able to screen for the condition in routine EKGs.

AI was able to recognize these patterns after examining the EKGs of many people with and without the disease. The rapid growth in healthcare data — including detailed electronic health records, imaging, genomic data, biometrics and behavioral data — combined with advancements in artificial intelligence technology has created a major opportunity. Because of its unique ability to identify patterns from the data, AI has helped radiologists to find hidden cancers, pathologists to characterize liver fibrosis and ophthalmologists to detect retinal disease.

One challenge is that AI is expensive, requiring large-scale data to train computer algorithms and the technology to do so. As these resources become more ubiquitous, that can make the associated intellectual property difficult to protect, discouraging private investment in these products. More generally, diagnostics have long been considered unattractive investments. Unlike their therapeutic counterparts, which see around $300 billion in research and development investment a year, diagnostics receive a modest $10 billion in private funding.

Advertisement

Then there’s the question of who pays for the use of AI-based tools in medicine specifically. Some applications, such as detecting strokes, save insurers money (by preventing costly ICU stays and subsequent rehabilitation). These technologies tend to get reimbursed more quickly. But other AI solutions, such as detecting hypertrophic cardiomyopathy, may lead to increased spending on costly downstream therapies to treat newly identified chronic illness. Although the use of AI may improve quality of care and long-term outcomes in such cases, without financial incentives for insurers, reimbursement and thus adoption may be slow.

Life sciences companies have on rare occasion agreed to subsidize development or reimbursement of AI-based diagnostics. This will help bridge the gap, but the federal government may need to play a greater role. Federal support for COVID diagnostics during the pandemic drove rapid development of critical tests, and the cancer moonshot project has helped drive R&D in screening and new treatments.

It is usually tough to marshal funding at the scale needed for new medical frontiers. But the National Academies of Medicine has estimated that tens of billions of dollars and countless lives could be saved from improving diagnosis in medicine.

Artificial intelligence offers a path toward that. It should complement, rather than replace, the human expertise that already saves so many lives. The future of medical diagnosis doesn’t mean handing over the keys to AI but, rather, making use of what it can do that we can’t. This could be a special moment for diagnosis, if we invest enough and do it right.

Gaurav Singal is a computer scientist and physician at Harvard Medical School and was previously the chief data officer of Foundation Medicine, a cancer diagnostics company. Anupam B. Jena is an economist, physician and professor at Harvard Medical School and co-author of “Random Acts of Medicine: The Hidden Forces That Sway Doctors, Impact Patients, and Shape Our Health” and the Random Acts of Medicine Substack.

Advertisement

Science

What’s in a Name? For These Snails, Legal Protection

Published

on

What’s in a Name? For These Snails, Legal Protection

The sun had barely risen over the Pacific Ocean when a small motorboat carrying a team of Indigenous artisans and Mexican biologists dropped anchor in a rocky cove near Bahías de Huatulco.

Mauro Habacuc Avendaño Luis, one of the craftsmen, was the first to wade to shore. With an agility belying his age, he struck out over the boulders exposed by low tide. Crouching on a slippery ledge pounded by surf, he reached inside a crevice between two rocks. There, lodged among the urchins, was a snail with a knobby gray shell the size of a walnut. The sight might not dazzle tourists who travel here to see humpback whales, but for Mr. Avendaño, 85, these drab little mollusks represent a way of life.

Marine snails in the genus Plicopurpura are sacred to the Mixtec people of Pinotepa de Don Luis, a small town in southwestern Oaxaca. Men like Mr. Avendaño have been sustainably “milking” them for radiant purple dye for at least 1,500 years. The color suffuses Mixtec textiles and spiritual beliefs. Called tixinda, it symbolizes fertility and death, as well as mythic ties between lunar cycles, women and the sea.

The future of these traditions — and the fate of the snails — are uncertain. The mollusks are subject to intense poaching pressure despite federal protections intended to protect them. Fishermen break them (and the other mollusks they eat) open and sell the meat to local restaurants. Tourists who comb the beaches pluck snails off the rocks and toss them aside.

A severe earthquake in 2020 thrust formerly submerged parts of their habitat above sea level, fatally tossing other mollusks in the snail’s food web to the air, and making once inaccessible places more available to poachers.

Advertisement

Decades ago, dense clusters of snails the size of doorknobs were easy to find, according to Mr. Avendaño. “Full of snails,” he said, sweeping a calloused, violet-stained hand across the coves. Now, most of the snails he finds are small, just over an inch, and yield only a few milliliters of dye.

Continue Reading

Science

Video: This Parrot Has No Beak, But Is at the Top of the Pecking Order

Published

on

Video: This Parrot Has No Beak, But Is at the Top of the Pecking Order

new video loaded: This Parrot Has No Beak, But Is at the Top of the Pecking Order

Bruce, a disabled kea parrot, is missing his top beak. The bird uses tools to keep himself healthy and developed a jousting technique that has made him the alpha male of his group.

By Meg Felling and Carl Zimmer

April 20, 2026

Continue Reading

Science

Contributor: Focus on the real causes of the shortage in hormone treatments

Published

on

Contributor: Focus on the real causes of the shortage in hormone treatments

For months now, menopausal women across the U.S. have been unable to fill prescriptions for the estradiol patch, a long-established and safe hormone treatment. The news media has whipped up a frenzy over this scarcity, warning of a long-lasting nationwide shortage. The problem is real — but the explanations in the media coverage miss the mark. Real solutions depend on an accurate understanding of the causes.

Reporters, pharmaceutical companies and even some doctors have blamed women for causing the shortage, saying they were inspired by a “menopause moment” that has driven unprecedented demand. Such framing does a dangerous disservice to essential health advocacy.

In this narrative, there has been unprecedented demand, and it is explained in part by the Food and Drug Administration’s recent removal of the “black-box warning” from estradiol patches’ packaging. That inaccurate (and, quite frankly, terrifying) label had been required since a 2002 announcement overstated the link between certain menopause hormone treatments and breast cancer. Right-sizing and rewording the warning was long overdue. But the trouble with this narrative is that even after the black-box warning was removed, there has not been unprecedented demand.

Around 40% of menopausal women were prescribed hormone treatments in some form before the 2002 announcement. Use plummeted in its aftermath, dipping to less than 5% in 2020 and just 1.8% in 2024. According to the most recent data, the number has now settled back at the 5% mark. Unprecedented? Hardly. Modest at best.

Nor is estradiol a new or complex drug; the patch formulation has existed for decades, and generic versions are widely manufactured. There is no exotic ingredient, no rare supply chain dependency, no fluke that explains why women are suddenly being told their pharmacy is out of stock month after month.

Advertisement

The story is far more an indictment of the broken insurance industry: market concentration, perverse incentives and the consequences of allowing insurance companies to own the pharmacy benefit managers that effectively control drug access for the majority of users. Three companies — CVS Caremark, Express Scripts and OptumRx — manage 79% of all prescription drug claims in the United States. Those companies are wholly owned subsidiaries of three insurance behemoths: CVS Health, Cigna and UnitedHealth Group, respectively. This means that the same corporation that sells you your insurance plan also decides which drugs get covered, at what price, and whether your pharmacy can stock them. This is called vertical integration. In another era, we might have called it a cartel. The resulting problems are not unique to hormone treatments; they have affected widely used medications including blood thinners, inhalers and antibiotics. When a low-cost generic such as estradiol — a medication with no blockbuster profit margins and no patent protection — runs into friction in this system, the friction is not random. It is structural. Every decision in that chain is filtered through the same corporate profit motive. And when the drug in question is an off-patent estradiol patch that has negligible profit margins because of generic competition but requires logistical investment to keep consistently in stock? The math on “how much does this company care about ensuring access” is not complicated.

Unfortunately, there is little financial incentive to ensure smooth, consistent access. There is, however, significant financial incentive to steer patients toward branded alternatives, or simply to let supply tighten — because the companies aren’t losing much profit if sales of that product dwindle. This is not a conspiracy theory: The Federal Trade Commission noted this dynamic in a report that documented how pharmacy benefit managers’ practices inflate costs, reduce competition and harm patient access, particularly for independent pharmacies and for generic drugs.

Any claim that the estradiol patch shortage is meaningfully caused by more women now demanding hormone treatments is a distraction. It is also misogyny, pure and simple, to imply that the solution to the shortage is for women’s health advocates to dial it down and for women to temper their expectations. The scarcity of estradiol patches is the outcome of a broken system refusing to provide adequate supply.

Meanwhile, there are a few strategies to cope.

  • Ask your prescriber about alternatives. Estradiol is available in multiple formulations, including gel, spray, cream, oral tablet, vaginal ring and weekly transdermal patch, which is a different product from the twice-weekly patch and may be more consistently available depending on manufacturer and region.
  • Consider an online pharmacy. Many are doing a good job locating and filling these prescriptions from outside the pharmacy benefit manager system.
  • Call ahead. Patch shortages are inconsistent across regions and distributors. A call to pharmacies in your area, or a broader geographic radius if you’re able, can locate stock that your regular pharmacy doesn’t have.
  • Consider a compounding pharmacy. These sources can sometimes meet needs when commercially manufactured products are inaccessible. The hormones used are the same FDA-regulated bulk ingredients.

Beyond those Band-Aid solutions, more Americans need to fight for systemic change. The FTC report exists because Congress asked for it and committed to legislation that will address at least some of the problems. The FDA took action to change the labeling on estrogen in the face of citizen and medical experts’ pressure; it should do more now to demand transparency from patch manufacturers.

Most importantly, it is on all of us to call out the cracks in the current system. Instead of repeating “there’s a patch shortage” or a “surge in demand,” say that a shockingly small minority of menopausal women still even get hormonal treatments prescribed at all, and three drug companies control the vast majority of claims in this country. Those are the real problems that need real solutions.

Advertisement

Jennifer Weiss-Wolf, the executive director of the Birnbaum Women’s Leadership Center at New York University School of Law, is the author of the forthcoming book When in Menopause: A User’s Manual & Citizen’s Guide. Suzanne Gilberg, an obstetrician and gynecologist in Los Angeles, is the author of “Menopause Bootcamp.”

Continue Reading
Advertisement

Trending