IMTS was a blast, but it was great to be back home in lovely Northern California this week. On this episode of QDL, we covered the skills that workers need and the innovations that organizations want. Plus, we brought you a live interview with author Mark Graban, and one on tape from Burt Mason of Hexagon Manufacturing Intelligence captured at IMTS. Let’s take a look:

“Only 20 Percent of Employees Have Skills Needed for Their Current Roles and Future Careers”

Adapting to the coming digital transformation means that organizations must hire, train, and motivate workers in a whole new way. Gartner research indicates that companies can best do this by identifying and developing so-called “connected learners.”

Can you imagine a future where the question, “Did you bring a copy of your test results?” becomes entirely unnecessary? That could happen, but the methods that most healthcare providers use to exchange healthcare information are little different than they were 5,000 years ago, when physicians caring for the same patient exchanged scrolls of papyrus and clay tablets.

Since the inception of computing technology, healthcare systems and doctors have been trying to find ways to dispense with the inefficiency and to share information electronically. One of the building blocks for this information bridge is something called a health information exchange. These exchanges allow for the transfer of electronic health information—such as your medical records, laboratory test results, and medication lists—among hospitals and providers. Yet, our recent research shows that, despite clear benefits of health information exchanges, they are not being utilized as often as they could be.

‘How is it that in the middle of a relatively small town of about 125,000 people in Minnesota, you’ve got the No. 1-rated healthcare system probably in the world?”

The question was put to Jeffrey Bolton—the Mayo Clinic’s chief administrative officer—by Larry Jameson, executive vice president of the University of Pennsylvania Health System, during the recent Wharton Leadership Conference. Jameson, who was interviewing Bolton, said he wanted to understand “the Mayo magic.”

During the past decade, advances in understanding of cancer biology have led to the development of targeted treatments that are more effective than the chemotherapies of the past century. These therapies are demonstrating response rates large in magnitude or response durations prolonged in early trials, or both. Patient demand to enter these trials has increased, and so have calls to expedite the drug development and approval processes, all while maintaining high standards for safety and efficacy.

The U.S. Food and Drug Administration (FDA) never loses sight of its dedication to patients faced with a life-threatening disease, and to making progress in the fight against cancer.

The administration works with industry, researchers, and other stakeholders developing innovative cancer therapies to ensure clear understanding of the FDA’s latest thinking on how clinical trials can be efficiently and effectively designed to demonstrate a cancer therapy’s safety and efficacy.

Last week, the FDA published a draft guidance to help advance effective and innovative clinical trial designs early in drug development to help bring new cancer therapies to patients as quickly as possible. Below is a quick summary of this guidance:

We spend much of our time in buildings, and they can have a profound effect on our well-being, for better or for worse. As long ago as 1943, Winston Churchill told Britain’s House of Commons that “we shape our buildings, and afterwards our buildings shape us.”

Research is showing that effective building design is especially important in hospitals, the potential of which is often overlooked. For example, a recent study of the design of operating rooms—one of the most critical areas in a hospital—reveals how research-informed design can improve safety and performance.

We have studied for years how to improve the delivery of healthcare, including through better design of healthcare buildings. Based on our studies and those of others, we are advocates for using evidence-based design to benefit hospital patients, staff, and patients’ families.

During the early 20th century, Americans were inundated with ineffective and dangerous drugs, as well as adulterated and deceptively packaged foods.

A cosmetic eyelash and eyebrow dye called Lash Lure, for example, which promised women that it would help them “radiate personality,” in fact contained a poison that caused ulceration of the corneas and degeneration of the eyeballs. An elixir called Banbar claimed to cure diabetes as an alternative to insulin, but actually provided no real treatment and caused harm to those patients who substituted this for effective insulin therapy.

Food producers short-changed consumers by substituting cheaper ingredients. Some products labeled as peanut butter, for instance, were filled with lard and contained just a trace of peanuts, and some products marketed as “jellies” had no fruit in them at all. Unscrupulous vendors even sold products to farmers, falsely promising they could treat sick animals—in at least one case, a product called Lee’s Gizzard Capsules killed an entire flock of turkeys instead of curing them.

Medical image registration is a common technique that involves overlaying two images, such as magnetic resonance imaging (MRI) scans, to compare and analyze anatomical differences in great detail. If a patient has a brain tumor, for instance, doctors can overlap a brain scan from several months ago onto a more recent scan to analyze small changes in the tumor’s progress.

This process, however, can often take two hours or more, as traditional systems meticulously align each of potentially a million pixels in the combined scans. In a pair of upcoming conference papers, MIT researchers describe a machine-learning algorithm that can register brain scans and other 3D images more than 1,000 times faster using novel learning techniques.

The algorithm works by “learning” while registering thousands of pairs of images. In doing so, it acquires information about how to align images and estimates some optimal alignment parameters. After training, it uses those parameters to map all pixels of one image to another, all at once. This reduces registration time to a minute or two using a normal computer, or less than a second using a graphics processing unit with comparable accuracy to state-of-the-art systems.