IBM 5 in 5: Medical labs “on a chip” will serve as health detectives for tracing disease at the nanoscale

Share this post:

A silicon wafer designed to sort particles found in bodily fluids for the purpose of early disease detection.

A silicon wafer designed to sort particles found in bodily fluids for the purpose of early disease detection.

The earlier a disease is diagnosed, the more likely it is to be cured or successfully managed. For example, breast cancer and prostate cancer detected and treated at stage one have five-year survival rates of nearly 100 percent. At stage four, this rate drops to around 26 percent for breast cancer and 28 percent for prostate cancer.

The challenge to finding a disease early is that many of us don’t seek treatment until we have symptoms, which means the disease has already progressed. Today’s detection technologies like mammograms are often uncomfortable, inconvenient and not always accurate.

IBM 5 in 5

I’ve been working on cancer genomics for over a decade and a half, during which I’ve seen incredible progress, mostly coming from advances in genomics technology. In the beginning, my work was mostly focused on crunching massive sets of genomics data coming from technologies new at the time like gene expression arrays and, later, RNA sequencing.

About 10 years ago, I recognized that the incredible expertise and resources in micro and nano technology we have at IBM Research could be used to advance DNA sequencing. About three years ago, my team and I started to think how to use nanotechnology to create diagnostics devices that, like detectives searching for clues, could inspect bodily fluids for nanoscopic, disease-related biomarkers at the very early stages. Such devices could greatly improve the outlook for patients, making a major contribution to health care in areas such as cancer, infectious disease and neurodegenerative disorders.

After three years, we are close to realizing this vision with the nanoscale deterministic lateral displacement, or nanoDLD, device we are working on within the IBM Nanobiotechnology group. Our goal is that, in the next five years, we will be able to combine this and other nanotechnology with artificial intelligence to overcome current challenges and detect diseases like cancer at the earliest possible stages.

What is our prediction?

In five years, advances in nanobiotechnology techniques will allow us to examine and filter bodily fluids for tiny bioparticles that reveal signs of disease like cancer before we have any symptoms, letting us know immediately if we should consult a doctor.

Why will this change the world?

Treating a disease like cancer is expensive. According to the American Society of Clinical Oncology, the most recently approved cancer medicine can cost $10,000 a month, on average; some therapies can cost $30,000 per month or more. When your doctor can diagnose cancer in its early stages, your odds of bankruptcy — and death — decrease significantly. By making it nearly as easy to detect early stage cancer as taking a home pregnancy test, we will change the economics of cancer and greatly diminish its physical and emotional toll for future generations.

At the same time, the vision of a medicine that is both preventative and personalized can only be realized when technology allows individuals to have periodic snapshot of the physiological, psychological, molecular and cellular markers of their health. Our technology will enable a seamless tracking of the molecular and cellular health of an individual.

What is the underlying technology?

Several companies are looking at the use of bioparticles such as exosomes to diagnose disease early, though IBM is the first to get down to the necessary scale and do the separation and detection of exosomes on a chip. Our approach uses the nanoDLD to process a liquid sample through a silicon chip with a special, IBM-designed asymmetric pillar array. The array is key — it allows the system to sort and separate particles in the sample. Smaller particles move in a zig-zag motion in the direction of the fluid, while larger particles bump through the array along the direction of pillar asymmetry. Big particles behave like truck drivers forced to deviate into the truck lane on a freeway, whereas small particles behave like smaller cars flowing straight without deviation. In a similar way, our pillar arrays allow for materials of different sizes to be separated and isolated for detection or analysis. If you are familiar with the game Plinko from the Price is Right or the Japanese version Pachinko, it looks something like that.

The information extracted from these chips is a signal that can indicate whether or not a disease is present. This can be combined with data from IoT enabled devices, like sleep monitors and smart watches, and processed by cognitive systems to give us a complete view of our health.

Related Papers and Patents

Benjamin H. Wunsch, Joshua T. Smith, Stacey M. Gifford, Chao Wang, Markus Brink, Robert L. Bruce, Robert H. Austin, Gustavo Stolovitzky and Yann Astier, “Nanoscale lateral displacement arrays for the separation of exosomes and colloids down to 20 nm.Nature Nanotechnology.

US Patent No. 9,012,329 – “Nanogap in-between noble metals”

Read all of IBM’s 2016 technology predictions at IBM 5 in 5.



More stories

AI Can Predict your Age Based on Your Microbiome

The human microbiome consists of a community of trillions of micro-organisms, such as bacteria, fungi, viruses, and live all over the body including on the skin, in the mouth and along the digestive tract. A balanced microbiome is important for an individual’s health and wellbeing, including proper functionality the digestive and immune systems. The human […]

Continue reading

Helping Advance Huntington’s Disease Research by Using AI to Map the Human Brain

In a new study, IBM and CHDI researchers studied the relationship between the pace of subtle cognitive decline in patients before full-fledged symptoms and their brain activity, as shown by a functional MRI. The results demonstrate that measuring the potential progression of HD could eventually be done from a single brain scan, acquired in one visit.

Continue reading

AI Year in Review: Highlights of Papers from IBM Research in 2019

IBM’s leadership in AI continued in earnest in 2019, which was notable for a growing focus on critical topics such as making trustworthy AI work in practice, creating new AI engineering paradigms to scale AI for a broader use, and continuing to advance core AI capabilities.

Continue reading