Upgrade 2020: MEI LAB
Distinguished Scientist, MEI Lab | NTT Research
Bio Digital Twin Technology Promises Autonomous Therapy for Cardio Diseases
Imagine you’ve got heart trouble but instead of going to a doctor every few months for a checkup, your condition is constantly monitored through a series of smart sensors. Any required therapeutics are delivered through smart robotics, actuators and nanotechnology devices – no doctor visit required. That’s the vision Dr. Joe Alexander of NTT Research painted during his talk at Upgrade 2020. Dr. Alexander, who works in the NTT Research Medical and Health Informatics (MEI) lab, was describing the concept of a cardiovascular bio digital twin.
Digital twin technology is a fairly recent development in information technology (IT) circles. The idea is to create in software a digital representation of something from the physical world. You can then perform “what-if” scenarios on the digital twin to see what would happen under various scenarios and to make predictions on various outcomes given different parameters.
The goal of his work in the MEI Lab is to apply this concept to healthcare. “We’re aiming for precision medicine and predictive health maintenance,” he said.
While he ultimately intends to create bio digital twins of multiple organ systems and the diseases affecting them, the initial target is the cardiovascular system. Specifically, his work addresses what he said are the two most common forms of heart failure, ischemic and hypertensive.
Director of Japan Reach | Stanford Center for Asian Health Research & Education
Stanford Program Produces New Medical Devices that Meet Well-defined Needs
Academics and industry alike often struggle to move ideas and concepts out of research and turn them into viable products that enjoy commercial success. In 2001, Stanford University started its Byers Center for Biodesign to focus on solving the problem by offering entrepreneurship education aimed at creating new medical devices.
Dr. Fumiaki Ikeno, a Research Associate in Cardiovascular Medicine at Stanford, explained in his Upgrade 2020 talk how the program seeks to avoid the usual roadblocks to medical product development by focusing on unmet needs in medical settings.
Innovation typically follows one of two processes. One is “technology push,” which is driven by research laboratories and is suitable for pharma and biotechnology innovation. The other is needs-driven, which is more suitable for medical devices.
The process for innovation that Dr. Ikeno espouses includes three steps: identify, invent, and implement. “The most important step is the first, which is identify,” he said. “Identifying a well-characterized need is the DNA of a great invention.” The most common reason for failure in medical device development is the lack of unmet needs – basically a solution in search of a problem.
His approach is working. So far, more than 50 startups have emerged from the Biodesign program, which has been replicated at universities in India, Singapore, and Japan.
Senior Distinguished Researcher | NTT Basic Research Labs
Stanford Program Produces New Medical Devices that Meet Well-defined Needs
At Upgrade 2020, Dr. Kunio Kashino from the Biomedical Informatics Research Center of NTT Basic Research Laboratories, presented groundbreaking work on technology that enables an automated system to listen to heart sounds and output a “caption” that describes the sound and whether it’s normal. If not, the system can even determine what kind of defect may be in play.
After listening to sounds, the neural audio model is trained to deliver two outputs: a classification of what family of disease the sounds represent, including the presence or absence of 12 difficult heart diseases, and a description or caption that is essentially a diagnosis of what the heart sound represents.
The model was trained using a set of heart sounds representing 55 difficult heart diagnoses. Class levels and seven kinds of explanation sentences were given manually for each case. His system was charged with listening to the heart sounds and applying the correct “diagnosis.”
Such a neural audio captioning system could be used for applications such as telemedicine or simply to relieve health care professionals from having to spend time listening to and evaluating various sounds. Instead, the captioning system could do it for them, immediately pointing medical professionals to those patients who need attention.
Research Scientist, MEI Lab | TUM, NTT Research
Toward Implantable Electrodes: A Miniaturized System for Cell Handling and Analysis
Wearable electrodes are becoming more common, to continuously monitor vital data such as heart rates, ECG and EMG waveforms for rapid diagnosis and early stage treatment of diseases. But the rigid metals and metal-plated fibers these electrodes are typically made of have some issues that researchers are hoping to address by developing smaller, more flexible electrodes that can actually be implanted inside the human body, directly on the organ to be monitored.
Dr. Tetsuhiko Teshima, a Research Scientist with the NTT Research MEI Lab, gave a talk on his research at Update 2020.
Current forms of electrodes lack flexibility and biocompatibilities, which results in excess noise and data distortion. With long-term use, they can also cause allergic reactions such as rashes and itching in patients.
His research is focused on developing implantable electrodes that attach to tissues and organs, increasing the variety of vital data that doctors can collect. The electrodes may also be used as surgical tools, Dr. Teshima said, such as to control CRT pacing.
The challenge is developing materials that are:
- Able to function inside the “very humid” human body
- Able to transform into soft, three dimensional structures in order to fit the shape of cells and tissues they attach to
In his talk, Dr. Teshima explained the evolution of his work, including the materials that are delivering positive results.
Senior Researcher | Stanford University
Why Humanized Mice Have the Potential to Shorten Drug and Vaccine Development
As has been made all too clear by the Covid-19 pandemic, the ability to rapidly develop drugs and vaccines is crucial to saving lives. In a recent talk, Dr. Toshiya Nishimura detailed his research that promises to shrink the duration of the trickiest part of the development process: testing in humans.
Dr. Nishimura is Director of the Stanford University Lab for Drug, Device Development and Regulatory Science (SLDDDRS). He explained how his team is working to repair a shortcoming in testing traditionally performed on mice by giving the mice more human-like qualities.
Some 90% of clinically tested drug compounds ultimately fail, he said. The U.S. Food and Drug Administration confirmed that one of the reasons for the low success rate is there’s a large gap between preclinical proof of concepts (POCs) and clinical POCs.
Dr. Nishimura’s team set out to test their hypothesis that the reason for the gap is data from the mice used in pre-clinical trials misrepresents the results of the drug under test. The reason for that is because mice are missing certain genes and enzymes that humans have, most notably affecting the immune system and liver.
The solution is to “humanize” the mice by introducing the missing genes or enzymes.
Professor | Keio University
Building a Real-time Emotion Detector from Simple EEG Readings Plus Noise Reduction
Dr. Yasue Mitsukura has developed a system that uses simple devices to measure the emotions people feel while doing everyday things, including eating and performing different tasks. The tool could be a boon for companies looking to determine how potential customers feel about their products.
Dr. Mitsukura, a professor at Keio University in Japan, gave a presentation outlining her work at Upgrade 2020. She developed a technique called the KANSEI model, which uses simple EEG devices to measure brainwaves and determine what a subject is feeling, including stress, interest, sleepiness, “like” or pleasure, and concentration.
Her work involves calculating the signal-to-noise ratio from EEG readings and removing the noise to ultimately determine what the subject was feeling at any point in time.
Dr. Mitsukura showed a demonstration video with a young woman wearing the system, the productized version of which is called Neurocam. As she moves about, whenever her KANSEI reading is higher than 60%, it triggers the camera to start filming. The video shows her in various ordinary situations – eating a donut, looking at a cute dog, window shopping, meeting a young man – while the system calculates her KANSAI score and determines what she’s feeling at various moments. She clearly liked the donut and the dog, for example, but especially the young man, who scored a 99.