Vanessa G. Ahern

home

authors

vanessa-g-ahern

It could be the next big step for diagnoses. Researchers at California Institute of Technology’s Division of Chemistry and Chemical Engineering department have worked to integrate magnetic resonance technology into microscale smart pill devices, according to a study published in 

“We said, ‘Let’s take the principles of [magnetic resonance imaging] but instead of building a MRI machine, we are going to create microchips that embody the principles of natural atoms (water, fat, muscle molecules), using the principle of an MRI machine that tells us where natural atoms are in the body,” says Mikhail Shapiro, PhD, assistant professor of chemical engineering at Caltech and Heritage Principal Investigator, co-author of the study.

Although the current way of taking pictures of the gastrointestinal tract is sophisticated, the new microscopic device, called Addressable Transmitters Operated as Magnetic Spin (ATOMS), could give physicians the ability to locate trouble areas more precisely—and without snapping photos. The technology could greatly improve diagnostic testing, experts say.

So, how does it work? First, consider the global positioning system (GPS) in your car. That technology helps you get to within a few centimeters of your destination, which is good enough when driving, but a few centimeters in the body could mean focusing on the wrong organ. Instead of using GPS principles, researchers used a conceptual approach, inspired by magnetic resonance technology that is widely used in hospitals.

“Our device contains a magnetic field sensor, integrated antennas, and a circuit (smaller than 1mm3) that adjusts its radio frequency signal based on the local magnetic field strength to wirelessly relay its location,” explains Manuel Monge, PhD, a lead author of the study.

As of now, patients swallow a pill that randomly travels through the gastrointestinal tract, capturing as much information as it can, Shapiro notes. But ATOMS enables many components to traverse the route, simultaneously transmitting information to the clinician. “It allows you to get a much more comprehensive view within your gut so there are many different locations you could read out at all times,” Shapiro says.

In the future, the technology could bring relief to patients and physicians by requiring fewer invasive procedures. Such a smart pill might one day detect a polyp in the colon, at least to the extent that an optical or biomedical measurement can do so, Shapiro says. But is the method strong enough to bring on a colon cancer diagnosis without a colonoscopy? He says it will take years of research before anyone can make that claim.

Even so, the team responsible for the innovation sees many potential uses.

“We believe that by integrating ATOMS technology with biological sensing and actuation techniques, we could enable future medical devices for a wide range of applications, from distributed monitoring of local biomarkers to targeted drug release and tissue imaging for disease diagnosis with high precision,” Monge notes. “For example, the device could monitor the health of a patient's gastrointestinal tract, blood, or brain, and relay that information to doctors.”

It will likely take several years before ATOMS hits the market, researchers say. “It is not measuring anything or taking pictures of anything, not releasing any drugs. So now our task is to combine this core technology with other elements we have previously developed,” Shapiro adds.

So far, the small size of the smart pill has proved challenging. For reference, the device can be located inside a mouse. To fit the necessary components in such a confined space while keeping power levels low required some hard work, Monge says.

ATOMS illustration has been resized. Courtesy of Ella Marushchenko for Caltech.

Articles

Caltech researchers continue to refine the microscopic device, whose potential continues to grow.

How New MRI-Inspired "Smart Pills" Could Optimize Diagnostic Testing

A new form of artificial intelligence (AI) that doesn’t need internet access could become a powerful healthcare tool, according to one of its creators.

Researchers and technicians from the University of Waterloo in Ontario, Canada recently presented the potentially groundbreaking new deep learning AI technology at the 

International Conference for Computer Vision in Venice, Italy

. The team made the AI less reliant on iCloud and Wi-Fi systems, using deep intelligence that mimics nature by incorporating “sexual evolutionary synthesis” to improve deep neural networks, according to the study.

This new technology has the potential to improve communication in a wide range of industries, including healthcare, where such AI could give physicians and healthcare staff the edge in crisis situations, a study author told 

“This technology, which produces highly efficient and compact deep learning AI that can run on low-power devices without being tethered to the internet, can be a great enabler for producing AI software that can aid clinical practitioners to make more accurate and faster clinical decisions and treatment planning directly from their smartphones, tablets, and other handheld devices from wherever they are,” says co-inventor Alexander Wong, PEng.

He is the Canada research chair in medical imaging systems and co-director of the Vision and Image Processing Research Group in the University of Waterloo’s Department of Systems Design Engineering. He and his teammates came up with the name “evolutionary synthesis” because the AI “attempts to mimic processes in biological evolution within a probabilistic framework to synthesize very compact deep neural networks,” Wong says.

The results: A network synthesized in this manner had “double the architectural efficiency” of a network touched by asexual evolutionary synthesis, according to the study. Both networks boasted 97% testing accuracy.

Sexual evolutionary synthesis can be useful in developing countries where clinical specialists are less widely available, Wong explains. Many people in underdeveloped countries have access to low-cost smartphones on which the AI can be installed, enhancing public health, for instance, through water quality testing. “Water quality is a big issue in underdeveloped countries, as safe drinking water is scarce, and this can be used to help them test their water more readily,” Wong says.

Across the world, this brand of efficient yet powerful AI can augment the healthcare system to provide better quality of care, he adds.

Surgeons who guide robotic operations could receive assistance from sexual evolutionary synthesis. “This new AI technology may be leveraged to build more efficient and compact deep learning AI that can sit directly within the surgical robots, where reducing lag and latency is very important and relying on the internet is not well-suited for such real-time, mission-critical operations,” Wong says. During their trials, researchers installed the technology in small chips in smartphones and tablets, opening the door to additional possibilities.

In the last decade, hospitals have struggled through power outages due to hurricanes and flooding. “Because this technology can build more efficient and compact deep learning AI, the energy requirements for running that AI can be lower,” Wong says, “and so [it] is more suitable for cases during a blackout where only a more limited amount of backup power or batteries are available.” It also enables deep learning AI to run on mobile devices, allowing low-power devices to be widely used during crises, he notes.

The software is entering the commercial realm this year through a start-up called 

By mirroring nature, “sexual evolutionary synthesis” AI proved just as accurate but more efficient than its asexual counterpart.

The AI That Aims to Break Free From Wi-Fi Dependence

In a recent study of people being treated for depression and mood disorders at primary care facilities, University of Pittsburgh researchers found that those who participated in an interactive online computerized cognitive behavior therapy program (CCBT) called Beat the Blues performed better than those receiving standard primary care alone.

But using an online support group, available via smartphone, in conjunction with therapy did not show any additional improvements, according to the study, which spanned 704 adults in the Pittsburgh area and was published in 

The Beat the Blues video included tasks and assignments for patients to complete over 6 months. In the study, college students with a mental health background worked as care managers sending emails, making phone calls, and texting to follow up and see how participants were doing.

The study’s lead author Bruce L. Rollman, MD, MPH, director of behavioral health and smart technology at the University of Pittsburgh’s division of general internal medicine, says the results suggest that CCBT will work in primary care in the USA, but he stresses the importance of collaborating with human caregivers who can check in with patients. “It’s more than just giving people a link to a computer program and hope that it will work,” says Rollman.

CCBT programs have been used with great success in Australia, England, and the Netherlands. For example, 100,000 people in Australia use 

 every year, strengthening skills to prevent and manage symptoms of anxiety and depression.

Rollman says CCBT could work as an adjunct for patients who do not have access to a therapist when one is recommended. The potential benefit of this form of e-mental health could be determined on a case-by-case basis to low-risk patients with moderate depression and mood disorders.

Patients opt out of visiting face-to-face therapists for a range of reasons—they cannot afford co-pays, work/life difficulties, or their rural community has limited access. Rollman does not recommend CCBT to patients who are suicidal, have trauma, physical abuse, or substance abuse, as these patients should be referred to more traditional in-person therapies.

In the study, two-thirds of patients were on an antidepressant medication, at baseline, and two-thirds were on antidepressant medications 6 months later, which is typical in primary care treatment. “For primary care physicians, I think that the CCBT delivered through a patient-centered medical home can be an effective first-line treatment for patients presenting with mood and anxiety disorders, and can be delivered at scale as a supplement to any medications a patient may already be getting,” Rollman says. “It could be an alternative to people who have access issues, who have nothing.”

The researchers were pleased to see that improvements were durable. On average, people stayed remitted after the intervention program was over for 6 months. “Unlike medications where there can be a relapse, people learned skills,” Rollman says. The researchers found that the more the patient engaged with the intervention, the more the patient improved.

“We hope that our study findings have implications in how mental health is delivered in primary care, and also focus further attention on e-mental health in the United States,” Rollman notes. “It is also important to test not only that these programs work, but also the most effective way that they work, which is certainly having a human on the other end, providing encouragement.”

Patients who underwent the cutting-edge cognitive behavior therapy did better than those who received typical care, according to a new study.

Vanessa G. Ahern

Articles

How New MRI-Inspired "Smart Pills" Could Optimize Diagnostic Testing

The AI That Aims to Break Free From Wi-Fi Dependence

How Computerized Therapy Can Help Patients with Depression, Mood Disorders