Biomedical engineer Kevin Zhao has a sensor in his arm and his chest that monitors his oxygen level in those tissues in real time.
Last month, at a conference celebrating DARPA, the research arm of the Defense Department, FBI Special Agent Edward You declared, "The 21st century will be the revolution of the life sciences."
Biomedical engineer Kevin Zhao has a sensor in his arm and chest that monitors his oxygen level in real time.
Indeed, four years ago, the agency dedicated a new office solely to advancing biotechnology. Its primary goal is to combat bioterrorism, protect U.S. forces, and promote warfighter readiness. But its research could also carry over to improve health care for the general public.
With an annual budget of about $3 billion, DARPA's employees oversee about 250 research and development programs, working with contractors from corporations, universities, and government labs to bring new technologies to life.
Check out these three current programs:
1) IMPLANTABLE SENSORS TO MEASURE OXYGEN, LACTATE, AND GLUCOSE LEVELS IN REAL TIME
Biomedical engineer Kevin Zhao has a sensor in his arm and his chest that monitors his oxygen level in those tissues in real time. With funding from DARPA for the program "In Vivo Nanoplatforms," he developed soft, flexible hydrogels that are injected just beneath the skin to perform the monitoring and that sync to a smartphone app to give the user immediate health insights.
A first-in-man trial for the glucose sensor is now underway in Europe for monitoring diabetics, according to Zhao. Volunteers eat sugary food to spike their glucose levels and prompt the monitor to register the changes.
"If this pans out, with approval from FDA, then consumers could get the sensors implanted in their core to measure their levels of glucose, oxygen, and lactate," Zhao said.
Lactate, especially, interests DARPA because it's a first responder molecule to the onset of trauma, sepsis, and potentially infection.
"The sensor could potentially detect rise of these [body chemistry numbers] and alert the user to prevent onset of dangerous illness."
2) NEAR INSTANTANEOUS VACCINE PROTECTION DURING A PANDEMIC
Traditional vaccines can take months or years to develop, then weeks to become effective once you get it. But when an unknown virus emerges, there's no time to waste.
This program, called P3, envisions a much more ambitious approach to stop a pandemic in its tracks.
"We want to confer near instantaneous protection by doing it a different way – enlist the body as a bioreactor to produce therapeutics," said Col. Matthew Hepburn, the program manager.
So how would it work?
To fight a pandemic, we will need 20,000 doses of a vaccine in 60 days.
If you have antibodies against a certain infection, you'll be protected against that infection. This idea is to discover the genetic code for the antibody to a specific pathogen, manufacture those pieces of DNA and RNA, and then inject the code into a person's arm so the muscle cells will begin producing the required antibodies.
"The amazing thing is that it actually works, at least in animal models," said Hepburn. "The mouse muscles made enough protective antibodies so that the mice were protected."
The next step is to test the approach in humans, which the program will do over the next two years.
But the hard part is actually not discovering the genetic code for highly potent antibodies, according to Hepburn. In fact, researchers already have been able to do so in two to four weeks' time.
"The hard part is once I have an antibody, a large pharma company will say in 2 years, I can make 100-200 doses. Give us 4 years to get to 20,000 doses. That's not good enough," Hepburn said.
To fight a pandemic, we will need 20,000 doses of a vaccine in 60 days.
"We have to fundamentally change the idea that it takes a billion dollars and ten years to make a drug," he concluded. "We're going to do something radically different."
3) RAPID DIAGNOSING OF PATHOGEN EXPOSURE THROUGH EPIGENETICS
Imagine that you come down with a mysterious illness. It could be caused by a virus, bacteria, or in the most extreme catastrophe, a biological agent from a weapon of mass destruction.
What if a portable device existed that could identify--within 30 minutes—which pathogen you have been exposed to and when? It would be pretty remarkable for soldiers in the field, but also for civilians seeking medical treatment.
This is the lofty ambition of a DARPA program called Epigenetic Characterization and Observation, or ECHO.
Its success depends on a biological phenomenon known as the epigenome. While your DNA is relatively immutable, your environment can modify how your DNA is expressed, leaving marks of exposure that register within seconds to minutes; these marks can persist for decades. It's thanks to the epigenome that identical twins – who share identical DNA – can differ in health, temperament, and appearance.
These three mice are genetically identical. Epigenetic differences, however, result in vastly different observed characteristics.
Reading your epigenetic marks could theoretically reveal a time-stamped history of your body's environmental exposures.
Researchers in the ECHO program plan to create a database of signatures for exposure events, so that their envisioned device will be able to quickly scan someone's epigenome and refer to the database to sort out a diagnosis.
"One difficult part is to put a timestamp on this result, in addition to the sign of which exposure it was -- to tell us when this exposure happened," says Thomas Thomou, a contract scientist who is providing technical assistance to the ECHO program manager.
Other questions that remain up in the air for now: Do all humans have the same epigenetic response to the same exposure events? Is it possible to distinguish viral from bacterial exposures? Does dose and duration of exposure affect the signature of epigenome modification?
The program will kick off in January 2019 and is planned to last four years, as long as certain milestones of development are reached along the way. The desired prototype would be a simple device that any untrained person could operate by taking a swab or a fingerprick.
"In an outbreak," says Dr. Thomou, "it will help everyone on the ground immediately to have a rapidly deployable machine that will give you very quick answers to issues that could have far-reaching ramifications for public health safety."
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.