A recent study in The Lancet Oncology showed that AI found 20 percent more cancers on mammogram screens than radiologists alone.
Published in The Lancet Oncology, the study analyzed the scans of 80,000 Swedish women with a moderate hereditary risk of breast cancer who had undergone a mammogram between April 2021 and July 2022. Half of these scans were read by AI and then a radiologist to double-check the findings. The second group of scans was read by two researchers without the help of AI. (Currently, the standard of care across Europe is to have two radiologists analyze a scan before diagnosing a patient with breast cancer.)
The study showed that the AI group detected cancer in 6 out of every 1,000 scans, while the radiologists detected cancer in 5 per 1,000 scans. In other words, AI found 20 percent more cancers than the highly-trained radiologists.
Scientists have been using MRI images (like the ones pictured here) to train artificial intelligence to detect cancers earlier and with more accuracy. Here, MIT's AI system, MIRAI, looks for patterns in a patient's mammograms to detect breast cancer earlier than ever before. news.mit.edu
But even though the AI was better able to pinpoint cancer on an image, it doesn’t mean radiologists will soon be out of a job. Dr. Laura Heacock, a breast radiologist at NYU, said in an interview with CNN that radiologists do much more than simply screening mammograms, and that even well-trained technology can make errors. “These tools work best when paired with highly-trained radiologists who make the final call on your mammogram. Think of it as a tool like a stethoscope for a cardiologist.”
AI is still an emerging technology, but more and more doctors are using them to detect different cancers. For example, researchers at MIT have developed a program called MIRAI, which looks at patterns in patient mammograms across a series of scans and uses an algorithm to model a patient's risk of developing breast cancer over time. The program was "trained" with more than 200,000 breast imaging scans from Massachusetts General Hospital and has been tested on over 100,000 women in different hospitals across the world. According to MIT, MIRAI "has been shown to be more accurate in predicting the risk for developing breast cancer in the short term (over a 3-year period) compared to traditional tools." It has also been able to detect breast cancer up to five years before a patient receives a diagnosis.
The challenges for cancer-detecting AI tools now is not just accuracy. AI tools are also being challenged to perform consistently well across different ages, races, and breast density profiles, particularly given the increased risks that different women face. For example, Black women are 42 percent more likely than white women to die from breast cancer, despite having nearly the same rates of breast cancer as white women. Recently, an FDA-approved AI device for screening breast cancer has come under fire for wrongly detecting cancer in Black patients significantly more often than white patients.
As AI technology improves, radiologists will be able to accurately scan a more diverse set of patients at a larger volume than ever before, potentially saving more lives than ever.
Hiking is one of Marci Flory's favorite activities, but her chronic Lyme disease sometimes renders her unable to walk. Biotech companies Pfizer and Valneva are testing a vaccine for Lyme disease in a Phase III clinical trial.
“Initially doctors thought I had ALS, or less likely, multiple sclerosis,” she says. “But after repeated MRI scans for a year, they concluded I had a rare neurological condition called acute transverse myelitis.”
But Flory was not convinced. After ordering a variety of private blood tests, she discovered she was infected with a range of bacteria in the genus Borrelia that live in the guts of ticks, the infectious agents responsible for Lyme disease.
“It made sense,” she says. “Looking back, I was bitten in high school and misdiagnosed with mononucleosis. This was probably the start, and my immune system kept it under wraps for a while. The Lyme bacteria can burrow into every tissue in the body, go into cyst form and become dormant before reactivating.”
The reason why cases of Lyme disease are increasing is down to changing weather patterns, triggered by climate change, meaning that ticks are now found across a much wider geographic range than ever before.
When these species of bacteria are transmitted to humans, they can attack the nervous system, joints and even internal organs which can lead to serious health complications such as arthritis, meningitis and even heart failure. While Lyme disease can sometimes be successfully treated with antibiotics if spotted early on, not everyone responds to these drugs, and for patients who have developed chronic symptoms, there is no known cure. Flory says she knows of fellow Lyme disease patients who have spent hundreds of thousands of dollars seeking treatments.
Concerningly, statistics show that Lyme and other tick-borne diseases are on the rise. Recently released estimates based on health insurance records suggest that at least 476,000 Americans are diagnosed with Lyme disease every year, and many experts believe the true figure is far higher.
The reason why the numbers are growing is down to changing weather patterns, triggered by climate change, meaning that ticks are now found across a much wider geographic range than ever before. Health insurance data shows that cases of Lyme disease have increased fourfold in rural parts of the U.S. over the last 15 years, and 65 percent in urban regions.
As a result, many scientists who have studied Lyme disease feel that it is paramount to bring some form of protective vaccine to market which can be offered to people living in the most at-risk areas.
“Even the increased awareness for Lyme disease has not stopped the cases,” says Eva Sapi, professor of cellular and molecular biology at the University of New Haven. “Some of these patients are looking for answers for years, running from one doctor to another, so that is obviously a very big cost for our society at so many levels.”
Emerging vaccines – and backlash
But with the rising case numbers, interest has grown among the pharmaceutical industry and research communities. Vienna-based biotech Valneva have partnered with Pfizer to take their vaccine – a seasonal jab which offers protection against the six most common strains of Lyme disease in the northern hemisphere – into a Phase III clinical trial which began in August. Involving 6,000 participants in a number of U.S. states and northern Europe where Lyme disease is endemic, it could lead to a licensed vaccine by 2025, if it proves successful.
“For many years Lyme was considered a small market vaccine,” explains Monica E. Embers, assistant professor of parasitology at Tulane University in New Orleans. “Now we know that this is a much bigger problem, Pfizer has stepped up to invest in preventing this disease and other pharmaceutical companies may as well.”
Despite innovations, patient communities and their representatives remain ambivalent about the idea of a vaccine. Some of this skepticism dates back to the failed LYMErix vaccine which was developed in the late 1990s before being withdrawn from the market.
At the same time, scientists at Yale University are developing a messenger RNA vaccine which aims to train the immune system to respond to tick bites by exposing it to 19 proteins found in tick saliva. Whereas the Valneva vaccine targets the bacteria within ticks, the Yale vaccine attempts to provoke an instant and aggressive immune response at the site of the bite. This causes the tick to fall off and limits the potential for transmitting dangerous infections.
But despite these innovations, patient communities and their representatives remain ambivalent about the idea of a vaccine. Some of this skepticism dates back to the failed LYMErix vaccine which was developed in the late 1990s before being withdrawn from the market in 2002 after concerns were raised that it might induce autoimmune reactions in humans.
While this theory was ultimately disproved, the lingering stigma attached to LYMErix meant that most vaccine manufacturers chose to stay away from the disease for many years, something which Gregory Poland, head of the Mayo Clinic’s Vaccine Research Group in Minnesota, describes as a tragedy.
“Since 2002, we have not had a human Lyme vaccine in the U.S. despite the increasing number of cases,” says Poland. “Pretty much everyone in the field thinks they’re ten times higher than the official numbers, so you’re probably talking at least 400,000 each year. It’s an incredible burden but because of concerns about anti-vax protestors, until very recently, no manufacturer has wanted to touch this.”
Such was the backlash surrounding the failed LYMErix program that scientists have even explored the most creative of workarounds for protecting people in tick-populated regions, without needing to actually vaccinate them. One research program at the University of Tennessee came up with the idea of leaving food pellets containing a vaccine in woodland areas with the idea that rodents would eat the pellets, and the vaccine would then kill Borrelia bacteria within any ticks which subsequently fed on the animals.
Even the Pfizer-Valneva vaccine has been cautiously designed to try and allay any lingering concerns, two decades after LYMErix. “The concept is the same as the original LYMErix vaccine, but it has been made safer by removing regions that had the potential to induce autoimmunity,” says Embers. “There will always be individuals who oppose vaccines, Lyme or otherwise, but it will be a tremendous boost to public health to have the option.”
Vaccine alternatives
Researchers are also considering alternative immunization approaches in case sufficiently large numbers of people choose to reject any Lyme vaccine which gets approved. Researchers at UMass Chan Medical School have developed an artificially generated antibody, administered via an annual injection, which is capable of killing Borrelia bacteria in the guts of ticks before they can get into the human host.
So far animal studies have shown it to be 100 percent effective, while the scientists have completed a Phase I trial in which they tested it for safety on 48 volunteers in Nebraska. Because this approach provides the antibody directly, rather than triggering the human immune system to produce the antibody like a vaccine would, Embers predicts that it could be a viable alternative for the vaccine hesitant as well as providing an option for immunocompromised individuals who cannot produce enough of their own antibodies.
At the same time, many patient groups still raise concerns over the fact that numerous diagnostic tests for Lyme disease have been reported to have a poor accuracy. Without this, they argue that it is difficult to prove whether vaccines or any other form of immunization actually work. “If the disease is not understood enough to create a more accurate test and a universally accepted treatment protocol, particularly for those who weren’t treated promptly, how can we be sure about the efficacy of a vaccine?” says Natasha Metcalf, co-founder of the organization Lyme Disease UK.
Flory points out that there are so many different types of Borrelia bacteria which cause Lyme disease, that the immunizations being developed may only stop a proportion of cases. In addition, she says that chronic Lyme patients often report a whole myriad of co-infections which remain poorly understood and are likely to also be involved in the disease process.
Marci Flory undergoes an infusion in an attempt to treat her Lyme disease symptoms.
Marci Flory
“I would love to see an effective Lyme vaccine but I have my reservations,” she says. “I am infected with four types of Borrelia bacteria, plus many co-infections – Babesia, Bartonella, Erlichiosis, Rickettsia, and Mycoplasma – all from a single Douglas County Kansas tick bite. Lyme never travels alone and the vaccine won’t protect against all the many strains of Borrelia and co-infections.”
Valneva CEO Thomas Lingelbach admits that the Pfizer-Valneva vaccine is not perfect, but predicts that it will still have significant impact if approved.
“We expect the vaccine to have 75 percent plus efficacy,” he says. “There is this legacy around the old Lyme vaccines, but the world is very, very different today. The number of clinical manifestations known to be caused by infection with Lyme Borreliosis has significantly increased, and the understanding around severity has certainly increased.”
Embers agrees that while it will still be important for doctors to monitor for other tick-borne infections which are not necessarily covered by the vaccine, having any clinically approved jab would still represent a major step forward in the fight against the disease.
“I think that any vaccine must be properly vetted, and these companies are performing extensive clinical trials to do just that,” she says. “Lyme is the most common tick-borne disease in the U.S. so the public health impact could be significant. However, clinicians and the general public must remain aware of all of the other tick-borne diseases such as Babesia and Anaplasma, and continue to screen for those when a tick bite is suspected.”
A mosquito under the microscope.
The association between climate and infectious disease is poorly understood, says Irina Tezaur, a computational scientist at Sandia National Laboratories. “Correlations have been observed but it’s not known if these correlations translate to causal relationships.”
To make accurate longer-term predictions, scientists need more empirical data, multiple datasets specific to locations and diseases, and the ability to calculate risks that depend on unpredictable nature and human behavior. Another obstacle is that climate scientists and epidemiologists are not collaborating effectively, so some researchers are calling for a multidisciplinary approach, a new field called Outbreak Science.
Climate scientists are far ahead of epidemiologists in gathering essential data.
Earth System Models—combining the interactions of atmosphere, ocean, land, ice and biosphere—have been in place for two decades to monitor the effects of global climate change. These models must be combined with epidemiological and human model research, areas that are easily skewed by unpredictable elements, from extreme weather events to public environmental policy shifts.
“There is never just one driver in tracking the impact of climate on infectious disease,” says Joacim Rocklöv, a professor at the Heidelberg Institute of Global Health & Heidelberg Interdisciplinary Centre for Scientific Computing in Germany. Rocklöv has studied how climate affects vector-borne diseases—those transmitted to humans by mosquitoes, ticks or fleas. “You need to disentangle the variables to find out how much difference climate makes to the outcome and how much is other factors.” Determinants from deforestation to population density to lack of healthcare access influence the spread of disease.
Even though climate change is not the primary driver of infectious disease today, it poses a major threat to public health in the future, says Rocklöv.
The promise of predictive modeling
“Models are simplifications of a system we’re trying to understand,” says Jeremy Hess, who directs the Center for Health and the Global Environment at University of Washington in Seattle. “They’re tools for learning that improve over time with new observations.”
Accurate predictions depend on high-quality, long-term observational data but models must start with assumptions. “It’s not possible to apply an evidence-based approach for the next 40 years,” says Rocklöv. “Using models to experiment and learn is the only way to figure out what climate means for infectious disease. We collect data and analyze what already happened. What we do today will not make a difference for several decades.”
To improve accuracy, scientists develop and draw on thousands of models to cover as many scenarios as possible. One model may capture the dynamics of disease transmission while another focuses on immunity data or ocean influences or seasonal components of a virus. Further, each model needs to be disease-specific and often location-specific to be useful.
“All models have biases so it’s important to use a suite of models,” Tezaur stresses.
The modeling scientist chooses the drivers of change and parameters based on the question explored. The drivers could be increased precipitation, poverty or mosquito prevalence, for instance. Later, the scientist may need to isolate the effect of one driver so that will require another model.
There have been some related successes, such as the latest models for mosquito-borne diseases like Dengue, Zika and malaria as well as those for flu and tick-borne diseases, says Hess.
Rocklöv was part of a research team that used test data from 2018 and 2019 to identify regions at risk for West Nile virus outbreaks. Using AI, scientists were able to forecast outbreaks of the virus for the entire transmission season in Europe. “In the end, we want data-driven models; that’s what AI can accomplish,” says Rocklöv. Other researchers are making an important headway in creating a framework to predict novel host–parasite interactions.
Modeling studies can run months, years or decades. “The scientist is working with layers of data. The challenge is how to transform and couple different models together on a planetary scale,” says Jeanne Fair, a scientist at Los Alamos National Laboratory, Biosecurity and Public Health, in New Mexico.
Disease forecasting will require a significant investment into the infrastructure needed to collect data about the environment, vectors, and hosts a tall spatial and temporal resolutions.
And it’s a constantly changing picture. A modeling study in an April 2022 issue of Nature predicted that thousands of animals will migrate to cooler locales as temperatures rise. This means that various species will come into closer contact with people and other mammals for the first time. This is likely to increase the risk of emerging infectious disease transmitted from animals to humans, especially in Africa and Asia.
Other things can happen too. Global warming could precipitate viral mutations or new infectious diseases that don’t respond to antimicrobial treatments. Insecticide-resistant mosquitoes could evolve. Weather-related food insecurity could increase malnutrition and weaken people’s immune systems. And the impact of an epidemic will be worse if it co-occurs during a heatwave, flood, or drought, says Hess.
The devil is in the climate variables
Solid predictions about the future of climate and disease are not possible with so many uncertainties. Difficult-to-measure drivers must be added to the empirical model mix, such as land and water use, ecosystem changes or the public’s willingness to accept a vaccine or practice social distancing. Nor is there any precedent for calculating the effect of climate changes that are accelerating at a faster speed than ever before.
The most critical climate variables thought to influence disease spread are temperature, precipitation, humidity, sunshine and wind, according to Tezaur’s research. And then there are variables within variables. Influenza scientists, for example, found that warm winters were predictors of the most severe flu seasons in the following year.
The human factor may be the most challenging determinant. To what degree will people curtail greenhouse gas emissions, if at all? The swift development of effective COVID-19 vaccines was a game-changer, but will scientists be able to repeat it during the next pandemic? Plus, no model could predict the amount of internet-fueled COVID-19 misinformation, Fair noted. To tackle this issue, infectious disease teams are looking to include more sociologists and political scientists in their modeling.
Addressing the gaps
Currently, researchers are focusing on the near future, predicting for next year, says Fair. “When it comes to long-term, that’s where we have the most work to do.” While scientists cannot foresee how political influences and misinformation spread will affect models, they are positioned to make headway in collecting and assessing new data streams that have never been merged.
Disease forecasting will require a significant investment into the infrastructure needed to collect data about the environment, vectors, and hosts at all spatial and temporal resolutions, Fair and her co-authors stated in their recent study. For example real-time data on mosquito prevalence and diversity in various settings and times is limited or non-existent. Fair also would like to see standards set in mosquito data collection in every country. “Standardizing across the US would be a huge accomplishment,” she says.
Understanding how climate change contributes to the spread of disease is critical for thwarting future calamities.
Jeanne Fair
Hess points to a dearth of data in local and regional datasets about how extreme weather events play out in different geographic locations. His research indicates that Africa and the Middle East experienced substantial climate shifts, for example, but are unrepresented in the evidentiary database, which limits conclusions. “A model for dengue may be good in Singapore but not necessarily in Port-au-Prince,” Hess explains. And, he adds, scientists need a way of evaluating models for how effective they are.
The hope, Rocklöv says, is that in the future we will have data-driven models rather than theoretical ones. In turn, sharper statistical analyses can inform resource allocation and intervention strategies to prevent outbreaks.
Most of all, experts emphasize that epidemiologists and climate scientists must stop working in silos. If scientists can successfully merge epidemiological data with climatic, biological, environmental, ecological and demographic data, they will make better predictions about complex disease patterns. Modeling “cross talk” and among disciplines and, in some cases, refusal to release data between countries is hindering discovery and advances.
It’s time for bold transdisciplinary action, says Hess. He points to initiatives that need funding in disease surveillance and control; developing and testing interventions; community education and social mobilization; decision-support analytics to predict when and where infections will emerge; advanced methodologies to improve modeling; training scientists in data management and integrated surveillance.
Establishing a new field of Outbreak Science to coordinate collaboration would accelerate progress. Investment in decision-support modeling tools for public health teams, policy makers, and other long-term planning stakeholders is imperative, too. We need to invest in programs that encourage people from climate modeling and epidemiology to work together in a cohesive fashion, says Tezaur. Joining forces is the only way to solve the formidable challenges ahead.
This article originally appeared in One Health/One Planet, a single-issue magazine that explores how climate change and other environmental shifts are increasing vulnerabilities to infectious diseases by land and by sea. The magazine probes how scientists are making progress with leaders in other fields toward solutions that embrace diverse perspectives and the interconnectedness of all lifeforms and the planet.