Amid the COVID-19 pandemic, Mayo Clinic Center for Individualized Medicine is leading the way in this new era of transforming human health through individualized medicine and tailoring medical therapies to each patient’s unique genome.
At this year’s all-virtual Mayo Clinic Center for Individualized Medicine conference, Advancing Care Through Genomics, physicians and researchers will highlight innovative discoveries and medical advances that focus on the power of omics data, including artificial intelligence, precision cancer care, gene therapy, advances in the microbiome and more.
If you have never had the opportunity to attend the conference, now is your chance. This all-new virtual, interactive experience will come to you, wherever you are, starting with a speaker series on August 25. Stay ahead of the emerging research and update your practice by tuning into a session of the Advancing Care Through Genomics Virtual Speaker Series.
Registration is also now open for the virtual 9th annual Individualizing Medicine Conference on Oct. 14, offering an opportunity to learn from experts and see first-hand how this field is impacting clinical practice, research, and education.
Designed for the clinical and medical researcher, presentations focus on the latest topics in individualized medicine with an interactive virtual format. Recorded for flexibility in viewing, the conference features expert speakers, virtual posters and small group fireside chats.
Upcoming: Join the individualized medicine conversation on Mayo Clinic Radio to learn more about upcoming topics and speakers.
“Here at Mayo Clinic, we place a high value on sharing knowledge and expertise with the precision medicine community to advance care for patients—that need has only increased in the wake of COVID-19,” says Carolyn (Caer) Rohrer Vitek, Ed.D, M.S., conference director.
“The conference team continues that spirit of educating and collaborating with experts around the globe in light of safety and unknown travel restrictions.”
Bacteriophages, or phages, may play a significant role in treating complex bacterial infections in prosthetic joints, according to new Mayo Clinic research. The findings suggest phage therapy could provide a potential treatment for managing such infections, including those involving antibiotic-resistant microbes.
“The treatment for chronic prosthetic joint infection has been surgery plus antibiotics, with surgery being the backbone of therapy. When these efforts fail, there can be significant suffering, loss of limb, and even death,” says author Gina Suh, M.D., Mayo Clinic infectious diseases specialist. “Phage therapy has the potential to be paradigm-shifting in how we treat infections in this era of increasing medical device use and antibiotic resistance.”
Phages are naturally occurring viruses found throughout the earth that target and kill specific bacterial cells, including those that have grown resistant to multiple antibiotics. The microscopic organisms, numbering in the billions, destroy bacteria by injecting their DNA or RNA into the bacteria to replicate and burst the cells open.
“Phage therapy has the potential to be paradigm-shifting in how we treat infections in this era of increasing medical device use and antibiotic resistance.” – Dr. Gina Suh
Although phage therapy is new to Mayo Clinic, the bacterial predators were discovered more than a century ago, predating antibiotics. Today, much of the basic science of phages remains to be discovered.
Dr. Suh oversaw the first phage treatment at Mayo Clinic in June 2019, when a 62-year-old man was facing potential amputation after multiple failed courses of antibiotics and surgery. The intravenous use of phage therapy was approved by the U.S. Food and Drug Administration on a compassionate-use basis.
“We started phage therapy as kind of a last-ditch effort to save his limb, and the patient responded beautifully,” Dr. Suh says. “He has remained asymptomatic after completing treatment and he experienced no adverse effects.”
The patient’s infection involved a biofilm that formed on his knee-joint replacement device — a common complication among the millions of people worldwide who undergo life-enhancing joint replacements every year.
Study co-author Robin Patel, M.D., says biofilms are communities of bacteria held together in a slimelike substance and that growth in biofilms enables bacteria to evade the effects of many antibiotics.
“We’re looking for the ability of phage to either kill or keep these bacteria from growing as a measure of activity.” – Dr. Robin Patel
“When bacteria grow as biofilms on surfaces, such as joint replacement devices, bacteria are difficult to eradicate because being in biofilm state makes them resistant to many of the antibiotics that would otherwise work against them,” says Dr. Patel, director of Mayo Clinic’s Infectious Diseases Research Laboratory.
Dr. Patel uses proteomic analysis to identify a patient’s bacterium to begin the process of matching it with a phage.
“We then test a collection of phage against that particular patient’s species of bacteria to determine which might work best,” Dr. Patel says. “We’re looking for the ability of phage to either kill or keep these bacteria from growing as a measure of activity.”
She says as the world faces a growing public health threat from drug-resistant bacterial infections, and that it is possible phage therapy could save lives, but more study is needed.
“There have been several patients who have been treated with phage with promising outcomes, but as a scientist, a single case like ours, or even a collection of single cases, is not enough to prove that a therapy is active,” Dr. Patel says.
The next step in the study is to expand the clinical use of phage therapy on prosthetic-joint infections of the hip and knee. Mayo Clinic is launching a two-year clinical trial later this year to continue to evaluate phage therapy in the treatment of infectious diseases.
The research was funded in part by the Congressionally Directed Medical Research Program (Work Unit Number A1427), Naval Medical Research Center, and by the Mayo Clinic CTSA through grant number UL1TR002377 from the National Center for Advancing Translational Sciences (NCATS), a component of the National Institutes of Health (NIH).
Read more stories about advances in individualized medicine.
COVID-19 and multisystem inflammatory syndrome in children
Though children of all ages can become sick with coronavirus disease 2019 (COVID-19), most kids who are infected typically don’t become as sick as adults do. Some children who have an active infection with the virus that causes COVID-19 might not show any signs or symptoms at all.
Still, you may have heard about a serious inflammatory syndrome in children, including some teenagers, that appears to be linked to COVID-19. It’s called multisystem inflammatory syndrome in children (MIS-C). This syndrome is rare, and most children who have it eventually get better with medical care. But some kids rapidly get worse, to the point where their lives are at risk.
Much remains to be learned about this new and emerging inflammatory syndrome, and the cause is not known yet. But if your child shows any signs or symptoms, get help fast. Here’s what you need to know.
What is multisystem inflammatory syndrome in children?
Multisystem inflammatory syndrome in children (MIS-C) is a serious condition in which some parts of the body — such as the heart, blood vessels, kidneys, digestive system, brain, skin or eyes — become inflamed. Inflammation typically includes swelling, often with redness and pain.
Many, but not all, children with MIS-C test negative for a current infection with the virus that causes COVID-19. Yet evidence indicates that many of these children were infected with the COVID-19 virus in the past, as shown by positive antibody test results.
COVID-19 and high blood pressure: Am I at risk?
I have high blood pressure. What should I do to lower my risk of getting seriously ill with COVID-19?
Answer: High blood pressure is a serious condition. Left untreated, it can lead to many other health issues. Health risks linked to high blood pressure include heart disease, stroke and dementia.
Some studies suggest that people with high blood pressure are more at risk of getting seriously ill with and dying of coronavirus disease 2019 (COVID-19). But some experts say that the people with high blood pressure who’ve gotten the sickest with COVID-19 were older and had other medical conditions, too. Diabetes, obesity and serious heart issues are examples. Research into the link between high blood pressure and COVID-19 is ongoing. However, people with untreated high blood pressure seem to be more at risk of complications from COVID-19 than those whose high blood pressure is managed with medication.
If you have high blood pressure, the most important step you can take is to manage it. Follow the treatment plan you’ve created with your doctor. Protecting yourself against the serious health issues that high blood pressure can cause is especially important with COVID-19.
Medication and lifestyle changes offer a powerful combination for preventing or reducing the health issues high blood pressure can cause. Read more.
Read more stories about advances in individualized medicine.
Contact tracing and COVID-19: What is it and how does it work?
I’ve heard about contact tracing being done during the COVID-19 pandemic. What is it and how does it work?
Answer: Contact tracing is a tool that can help slow the spread of infectious diseases, such as coronavirus disease 2019 (COVID-19). In communities using contact tracing, clinics, labs and hospitals send the names of people who have recently been diagnosed with COVID-19 to their local health department.
The health department asks each person with COVID-19 about people with whom they’ve recently had close contact. Health department officials then quickly (usually within 24 hours) alert people who are close contacts that they may have been exposed to the COVID-19 virus. Officials don’t share the name of the person who may have exposed them. This makes the contact tracing process anonymous and confidential.
The sooner health officials can alert close contacts, the lower the risk of the COVID-19 virus spreading further. But not all health departments have enough staff to do contact tracing. Some areas are researching and experimenting with contact tracing apps that can be used. They also research how they can maintain and protect the privacy of individuals who use the apps. The hope is these apps can make it faster and easier to find and notify people who’ve been exposed to the COVID-19 virus.
How do COVID-19 antibody tests differ from diagnostic tests?
I’ve heard about new antibody testing for COVID-19. What is antibody testing? Is it the same as testing to diagnose COVID-19?
Answer: With all the talk about coronavirus disease 2019 (COVID-19) testing in the news, it’s not surprising that there’s confusion about tests and how they differ. Antibody testing determines whether you had COVID-19 in the past and now have antibodies against the virus. A test to diagnose COVID-19 determines if you currently have the disease. Here’s what you need to know about testing.
When is antibody testing done and why is it important?
Antibody testing, also known as serology testing, is done after full recovery from COVID-19. Eligibility may vary, depending on the availability of tests. A health care professional takes a blood sample, usually by a finger prick or by drawing blood from a vein in the arm. Then the sample is tested to determine whether you’ve developed antibodies against the virus. The immune system produces these antibodies — proteins that are critical for fighting and clearing out the virus.
If test results show that you have antibodies, it indicates that you were likely infected with COVID-19 at some time in the past. It may also mean that you have some immunity. But the World Health Organization cautions that there’s a lack of evidence on whether having antibodies means you’re protected against reinfection with COVID-19. The level of immunity and how long immunity lasts are not yet known. Ongoing studies will eventually reveal more data on this.
The timing and type of antibody test affects accuracy. If you have testing too early in the course of infection, when the immune response is still building up in your body, the test may not detect antibodies, so you may have to wait several days to get tested. Also, the U.S. Food and Drug Administration (FDA) authorized and verified certain antibody tests, but many tests with questionable accuracy are now on the market.
A vaccine to prevent COVID-19 is perhaps the best hope for ending the pandemic. Currently, there is no vaccine to prevent infection with the COVID-19 virus, but researchers are racing to create one.
Coronavirus vaccine research
Coronaviruses are a family of viruses that cause illnesses such as the common cold, severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS). COVID-19 is caused by a virus that’s closely related to the one that causes SARS. For this reason, scientists named the new virus SARS-CoV-2.
While vaccine development can take years, researchers aren’t starting from scratch to develop a COVID-19 vaccine. Past research on SARS and MERS vaccines has identified potential approaches.
Coronaviruses have a spike-like structure on their surface called an S protein. (The spikes create the corona-like, or crown-like, appearance that gives the viruses their name.) The S protein attaches to the surface of human cells. A vaccine that targets this protein would prevent it from binding to human cells and stop the virus from reproducing.
Coronavirus vaccine challenges
Past research on vaccines for coronaviruses has also identified some challenges to developing a COVID-19 vaccine, including:
Ensuring vaccine safety. Several vaccines for SARS have been tested in animals. Most of the vaccines improved the animals’ survival but didn’t prevent infection. Some vaccines also caused complications, such as lung damage. A COVID-19 vaccine will need to be thoroughly tested to make sure it’s safe for humans.
Providing long-term protection. After infection with coronaviruses, re-infection with the same virus — though usually mild and only happening in a fraction of people — is possible after a period of months or years. An effective COVID-19 vaccine will need to provide people with long-term infection protection.
Protecting older people. People older than age 50 are at higher risk of severe COVID-19. But older people usually don’t respond to vaccines as well as younger people. An ideal COVID-19 vaccine would work well for this age group.
Scientists around the world are working feverishly on vaccines, what’s the status of vaccine research?
The U.S. Food and Drug Administration released a guidance document for the development of COVID-19 vaccines. It’s what we would have hoped for, it’s reasonable and reassuring. It should go a long way toward addressing concerns that urgency could influence the process.
On a global view, one vaccine has already been approved in China. And there are three vaccines in phase three clinical trials, eight in phase two trials, eleven in phase in one and 120 in pre-clinical, including here at Mayo Clinic. Those three that are in phase three clinical trials are the front runners.
Here’s the nuance. These are vaccines that are utilizing methods or vaccine platforms that have not been used before. So a lot of careful safety and efficacy studies have to be done. What we need to do, at some point, is engage in a national conversation about which vaccines are best for which patients. We will also have to know the characteristics of immunity produced by these vaccines. It won’t be simple. This will be a complicated vaccine decision that health care providers and patients will need to discuss, in the months ahead.
COVID-19 vaccines could be released to the public in two ways: through an Emergency Use Authorization (EUA) or through the full regulatory licensing process. The EUA process could result in a vaccine being released this Fall/Winter. Full licensing would likely mean release in the Winter/Spring timeframe.
There’s a flu virus just discovered in China, not related to COVID-19, that’s causing concern. What do you know about that?
The good thing is we know about this because of the kind of surveillance that’s currently being done. In the past, things like this happened and we often didn’t know about it until they reached the outbreak or even pandemic stage.
The concerning thing is that this is a virus that has avian genes in it, that came out of a pig, that resembles the 2009 pandemic virus. It has the markers of the type of influenza virus that with further changes could become a pandemic virus. Now, that’s speculation and it’s very early. It bears close scrutiny and further testing to understand if this virus is changing or mutating in anyway and if we’re seeing any spread.
But if there’s any vaccine that we would have to make a pandemic vaccine for, an H1N1 influenza virus (and that’s what this new virus is) is one of the easier ones. We know how to do that. We did it in 2009. The concern would be, if something like this were to emerge at the same time that we have an increase in COVID-19 cases, say this fall or winter. We’d be trying to make a lot of vaccine against two different respiratory viruses whose initial symptoms could overlap.
What about school concerns for children, since many classrooms may be opening soon?
The goal, like all things in life, is to make things safer.
Since there’s so much value, especially for younger children, to have in-person educational interaction, we have to look at a multitude of interventions that lower the risks and increase the safety for school children and the teaching staff. For example, if all we did was wash our hands or we only wore masks, those actions alone don’t protect us as much as doing them together.
You can get infected in any setting where you are not taking adequate precautions. Simply put, when you’re outdoors and around people you need to be in a mask or you run the risk of contracting this highly contagious coronavirus.
Dr. Gregory Poland
School districts and states have released guidelines for how to safely open schools that involve considerations of mask wearing, distancing, foregoing some activities, health checks and others. All the plans I’ve been asked to review to date have been solid and well thought out.
It seems some people think you can’t get COVID-19 outdoors. Could you please address this?
While it’s true, being outside gives you the option for better social distancing and you might have wind currents diluting the viruses, etc., you can get infected in any setting where you are not taking adequate precautions.
When you’re outdoors and not around people, you essentially have no risk … but these outside bars and beaches, with people jammed shoulder to shoulder, are definitely putting people at risk. Simply put, when you’re outdoors and around people you need to be in a mask or you run the risk of contracting this highly contagious coronavirus.
How has Mayo Clinic met the challenges of the pandemic?
I am, personally, immensely proud of the institution I’ve devoted my adult life and career to. Mayo has done what we always do, even in the toughest circumstances of being in the midst of a pandemic, and that is to garner the best data and research, and use it to inform our medical practice.
We’ve taken difficult and appropriate steps to protect patients and health care providers. And the institution has done a massive job in sharing what we know with the public and with other health care providers.
Mayo continues to assist and facilitate critical research that needs to be done to advance the science and save lives. I am very, very proud of Mayo and my colleagues.
Six months into this pandemic, what message do you want to convey to the public?
The canvas that we call COVID-19 was absolutely blank 25 weeks ago. We’ve learned a tremendous amount and we scientists are vigorously engaged but we cannot always predict who will have severe disease. So remember your health is a precious gift. Preserve it all cost. Please follow all the precautions that are science based for you, your family, and your community. We care and we want our patients to be safe and healthy.
Read more stories about advances in individualized medicine.
In recognition of their high impact work of advancing the field of genetic risk profiling for disease risk stratification, the National Institutes of Health (NIH) has awarded Mayo Clinic researchers Iftikhar Kullo, M.D. and Richard Sharp Ph.D. part of $75 million in funding over five years to improve the role of genomics in assessing and managing disease risk.
“The work has the potential to transform how we estimate disease risk in clinical practice.” – Iftikhar Kullo, M.D.
Dollars from the award will be used to build upon the Electronic Medical Records and Genomics (eMERGE) Network, a consortium of medical research organizations, to fund a coordinating center and clinical sites. The work will be supported in part by Mayo Clinic Center of Individualized Medicine.
The goal of the clinical sites is to conduct and validate genomic risk-assessment and management methods for a number of common diseases in the general population, such as coronary heart disease (CHD), Alzheimer’s disease, and diabetes, by recruiting people from diverse groups, including ethnic minority populations, underserved populations, or populations who experience poorer medical outcomes.
The research will be done in collaboration with Mountain Park Health Center, Phoenix Arizona, a Federally Qualified Health Center. To enhance diversity in genetic research, more than one third of the study’s participants will belong to minority groups.
“We are delighted to be part of eMERGE Network phase IV in which investigators will develop and implement Polygenic Risk Scores (disease risk based on DNA variants) for common diseases, and assess outcomes following disclosure of these scores to those at the highest risk,” says Principal Investigator, Dr. Kullo, professor and consultant with the Department of Cardiovascular Medicine. “The work has the potential to transform how we estimate disease risk in clinical practice.”
“I’m especially pleased that studies of ethical issues will be part of this work. Patients often worry that genetic information could be misused by insurance companies and others.” – Richard Sharp, Ph.D.
Dr. Kullo says his team will focus on using polygenic risk scores for cardiovascular diseases, particularly CHD, the leading cause of death in the United States.
“CHD often occurs in the young, leading to devastating consequences for the individual and the family,” Dr. Kullo says. “Preventive measures at the societal level coupled with aggressive risk reduction in individuals with high polygenic risk could substantially reduce the burden of CHD, particularly premature CHD.”
“I’m especially pleased that studies of ethical issues will be part of this work. Patients often worry that genetic information could be misused by insurance companies and others,” says Richard Sharp, Ph.D., co-principal investigator and director of Mayo Clinic’s Bioethics Program. “Those fears can result in patients declining medical testing that would otherwise play an important role in their care. Dr. Kullo and I will be looking more closely at those concerns, with the goal of developing new ways of talking with patients about their genomic screening results.”
Building predictions based on a set of variables, an effort called modeling, has gotten a lot of airtime during the COVID-19 pandemic. Understanding both the virus and the disease, including how it spreads and its impacts on population health, guides advice to the public on how to stay safe. At Mayo Clinic – an academic medical center – those kinds of epidemiological and biological modeling are part of the research done every day. However, Mayo researchers have taken it to the next level.
“The unique aspects of the modeling we are doing is about taking care of our patients in a safe and effective way,” says Mayo cardiologist Henry Ting, M.D., and program co-lead for Mayo Clinic’s COVID-19 Data Governance Task Force, which oversees COVID-19 modeling efforts.
Behind the scenes
Every morning, Mayo health sciences researcher Hongfang Liu, Ph.D., statistician Curtis Storlie, Ph.D., and their team, run COVID-19 predictive modeling programs to forecast the latest trends. Those programs are automated, but required the human interpretation to generate targeted information for Mayo Clinic leaders.
Their raw materials are numbers — lots, and lots, of numbers. Those numbers take a different shape every day, and the team’s job is to interpret those shapes, or signs of shifts — or potential shifts — in the spread and severity of the disease, and specifically what that means to Mayo Clinic’s hospitals and outpatient practices.
“We have outbreaks, hospital census [number of filled beds], community, county, state, and world data,” says Dr. Liu. “We get estimates of the signals — what might affect our practice — and how strong those signals are.”
Their goal is to make scientifically sound predictions and make recommendations for safe care of patients while reducing community disease transmission. In the early days, modeling potential outcomes of efforts to limit social activities, and implementation of stay at home orders led to the decision to pause most of Mayo Clinic’s normal operations and send people home to telework.
Stopping all but the most essential face-to-face interactions in March 2020 allowed time for Mayo Clinic to better understand COVID-19 and figure out how to operate safely, says Dr. Liu.
Modeling also enabled the team to predict for Mayo leadership when cases would start to level off, instead of exponentially increasing each day. The U.S. case doubling time has been over 50 days since May 25. The number of daily new cases has been sitting around 20,000 in the past two weeks.
“The longer doubling time implies the number of deaths will trend down dramatically,” she says.
Another colleague, statistician Rickey Carter, Ph.D., is leading a team focused on complementary efforts.
Very early on, he says the team began to predict how many hospitalized patients Mayo and the regions surrounding its hospitals would see, answering questions like, “would we have enough beds, enough ICU beds, enough ventilators?”
To answer some of these questions for Mayo, a scalable data infrastructure that could support all Mayo Clinic’s needs was needed.
“The next focal point became the personal protective equipment,” says Dr. Carter. “We needed to estimate how much PPE the COVID practice would need, and now, we have to estimate the demands for PPE for other staff and patients as the practice rapidly ramps up.”
In March, Dr. Carter says, “We thought the doubling time [how quickly the number of new cases doubles] was a day or two,” he says. “Fortunately it’s much, much slower.”
The models weren’t perfect, and that’s pretty much the rule in modeling.
“Models aren’t crystal balls, they are trying to predict the future based on what has happened in the past,” says Dr. Ting. Without previous human experience with SARS-CoV-2 and COVID-19, the modeling was bound to be less accurate early on. But in this case, any overestimation of need led to better preparedness to help Mayo Clinic’s patients.
Careful review of modeling assumptions and the calibration of the predictions with the changing landscape of COVID-19 across the Mayo enterprise and world led to a series of modeling improvements.
These significant efforts were led by Dr. Storlie, who led development of a highly sophisticated Bayesian model that incorporates a variety of data sources and updates it predictions every day. This model includes inputs such as social distancing behaviors, spatial location of public health reported cases of COVID-19 over time, county-level mobility trend data from Unacast, state-level and Mayo specific hospitalization data, in order to provide tailored predictions of impact to Mayo’s hospital operations in near real time, says Dr. Storlie.
“If there is one thing we learned about modeling COVID-19, it’s that things are not static,” says Dr. Storlie. “Things like infection and hospital admission rates trend quite differently across regions and in time. People change their behavior, in response to what they see around them or in the news, and/or government messaging and intervention. Testing strategy also changes over time in a different manner in each region. In order to build a reliable model, we had to explicitly account for all of these variations so that the model forecasts can include similar variation in the future.”
Research drives the best practice of medicine
“The most important thing we can try to predict is the number of patients who will need to be hospitalized,” says Dr. Ting.
“The constraints we have are hospital beds, ICU and staff capacity, PPE requirements and availability,” Dr. Ting continues. “Some of these we can modify.”
As the crisis unfolded, his team was able to predict when each hospital across Mayo Clinic and Mayo Clinic Health System would reach critical junctures, without intervention, and with various interventions implemented in different communities
“We are able to give our clinical practice the information they need to safely and effectively operate,” says Dr. Ting.
More than 100 years ago, William Mayo, M.D., is quoted as saying,”… in order that the sick may have the benefit of advancing knowledge, union of forces is necessary.” The current union of forces in modeling cuts across many disciplines and departments, and beyond the walls of Mayo Clinic.
“Back in about mid-February, the American Hospital Association put out a model predicting the health care system would be overwhelmed,” says Ben Pollock, Ph.D., a Mayo Clinic health services researcher.
Soon after that, Dr. Ting, along with Dr. Shah and Poe, put together the COVID-19 Data Governance Task Force.
“We came together as a team and began evaluating emerging COVID risk models, including their [appropriate use] of existing methodologies,” says Dr. Pollock. Today he says they are using a compilation of tools to predict 2-3 weeks in advance for Mayo Clinic’s practice in Arizona, Florida, and the Midwest.
Dr. Pollock leads the task force’s efforts to develop and maintain interactive dashboards with Mayo-centric information.
On another effort, he says, “We have been using Google’s mobility data to inform our social distancing suggestions. We are also trying to figure out ways to track what people are searching for on Google, and what the connections are to shifts and impacts on our practice.”
These efforts are not just for use at Mayo Clinic. Mayo Clinic’s COVID-19 modeling is also informing Minnesota Governor Tim Walz and Minnesota’s COVID-19 response, as well other leaders across the nation.
Now and moving forward
However, the driving force for Dr. Ting and the COVID-19 Data Governance Task Force remains Mayo Clinic.
“We are modeling for OUR hospital – for our patients,” says Dr. Ting,
As he considers the future – health care with COVID-19 in the wings – and the eventual reopening of all clinical services, he sees continued need for modeling support.
“For reopening – we have a pretty high confidence in how many COVID patients are going to need hospitalization,” he says. “We know how many resources need to be set aside to take care of them.
“Now that we know that, what can we do to safely reintroduce non-COVID patients and limit transmission?”
Dr. Ting says in coming weeks, disease prevalence surveillance and prediction will become more of focus for the team – both among staff and in adjacent communities. In addition, investigators will be studying how COVID-19 may be transmitted while patients are hospitalized. Explaining why, he repeats that this work is to “give our clinical practice the information they need to safely and effectively operate.”
For the researchers at the academic medical center that is Mayo Clinic, it’s all in a day’s work.
Read more stories about advances in individualized medicine.
Mayo is working with NASA to sequence the path of cancer — from what causes it to what drives it, and potentially how to prevent it.
Mayo researchers and NASA Frontier Development Lab data scientists are embarking on a research sprint this month to optimize an artificial intelligence (AI) algorithm for colorectal cancer and possibly other cancers.
“Our research shows the algorithm is able to predict the evolutionary trajectory by which colorectal cancer is going to occur,” says Nicholas Chia, Ph.D., the Bernard and Edith Waterman co-director for the Mayo Clinic Center for Individualized Medicine’s Microbiome Program. “We have information from this algorithm in terms of what event came first, what events are most important and exactly what the path to cancer was or what it will be.”
For eight weeks, Mayo will work with a team of NASA engineers, computer scientists and software developers in order to get the algorithm optimized for multi-omics data integration and causal modeling.
Dr. Chia says the project will also use complex multi-omics data, including the microbiome, to sequence the path of cancer — starting with what causes it, to what drives it, and potentially, how to prevent it.
“Our research shows the algorithm is able to predict the evolutionary trajectory by which colorectal cancer is going to occur.” – Nicholas Chia, Ph.D.
John Kalantari Ph.D., a machine learning scientist within the Center’s Microbiome Program, says he was inspired to develop the algorithm by contemporary applications of an AI technique known as reinforcement learning — popularized by its use in autonomous driving and defeating human experts in computer games, such as chess, Go, and StarCraft.
“We had a eureka moment when we realized that if we viewed our patient cancers as the result of an optimal game of cell evolution, then we could use inverse reinforcement learning techniques to learn the optimal ‘moves’ and environmental conditions that enable cancer progression, metastasis, recurrence, immune system evasion, and/or changes in treatment efficacy,” Dr. Kalantari explains. “By reverse-engineering how a tumor survived and thrived to become cancer in each individual patient, we are able to enhance our understanding of cancer systems biology and also improve our ability to predict treatment outcomes, discover early biomarkers of progression and identify new therapeutic/preventative targets in a more holistic manner.”
Recent results inspire confidence
Dr. Chia says his team chose to test the algorithm on colorectal cancer because of its canonical pathway of development, which was first discovered in 1993 by Bert Vogelstein, M.D., a pioneer in cancer genomics who found the gene responsible for inherited colon cancer and discovered how genes influence the susceptibility, leading to a blood test that can help identify people who are genetically predisposed to colon cancer.
“We had a eureka moment when we realized that if we viewed our patient cancers as the result of an optimal game of cell evolution, then we could use inverse reinforcement learning techniques to learn the optimal ‘moves’ and environmental conditions that enable cancer progression, metastasis, recurrence, immune system evasion, and/or changes in treatment efficacy.” – John Kalantari Ph.D.
In a recent study, Dr. Chia’s team tested the algorithm on 27 patients with colorectal cancer, using whole genome sequencing and DNA methylation to see if it could accurately identify spatial and temporal patterns of cancer progression. Many machine learning methodologies that strive to predict system dynamics require access to time-series data. Longitudinal patient tumor samples are few and far between, making existing techniques impractical to use.
“In order to innovate in both medicine and AI, we need to rethink how we can leverage our existing knowledge and data more efficiently,” Dr. Kalantari explains.
The result was a new Bayesian nonparametric algorithm called the ‘Pop-Up Restaurant for Inverse Reinforcement Learning’ (PUR-IRL). With their patient cohort and novel algorithm, the team was able to re-identify mutations associated with colorectal cancer progression and also predict the correct causal ordering in which they occurred.
“We were able to show a path to the same exact canonical pathway that Bert Vogelstein outlined by using just data from tumor samples,” Dr. Chia explains. “So this is promising because lots of cancers don’t have precursor lesions, and there is not a way of assessing the order like in colorectal cancer. The fact that we got the same answer as what’s already established tells us we’re on the right path and this algorithm works.”
The ultimate goal is to demonstrate the feasibility in order to study a larger cohort of patients with colorectal cancer and possibly apply the algorithm to other cancers.
“When the results come out, we hope in the near future we will be able to provide a report that can be interpreted by a clinician to understand what genes are driving this particular tumor in this particular patient,” Dr. Chia explains. “Through this inference, we can better understand the causal role of the microbiome in colorectal cancer and potentially other cancers.”
The Mayo Clinic Center for Individualized Medicine was selected for the prestigious NASA AI accelerator program after its AI cancer algorithm paper was awarded “Outstanding Paper Honorable Mention” out of 9,000 submissions at the Association for the Advancement of Artificial Intelligence conference in February. The project was also recently selected to be funded $100,000 by the Amazon Web Services Machine Learning Research Awards program.
Read more stories about advances in individualized medicine.