During the first week of February, a winter storm blew through Chicago, leaving piles of snow before subzero temperatures set in. Eve Bloomgarden, an endocrinologist at Northwestern Memorial Hospital, got a call from a worried patient who was scheduled to receive a covid-19 vaccine that week. She was preparing to brave the weather—and drive for the first time since the start of the pandemic—because she was concerned that this would be her only chance to get a shot.
“I’m seeing immense frustration and fear that they’re going to be left behind,” Bloomgarden says.
Chicago, like many parts of the US, has found the distribution of covid-19 vaccines slower than anyone hoped. Just 6% of the city’s 2.7 million residents have been vaccinated so far, and people have said the process is “like the Hunger Games,” requiring them to stay up late to refresh multiple websites in the hope that an open slot will pop up. Making things worse, official sign-up websites are clunky and hard to navigate.
In early February, the Department of Public Health announced a plan to help ease some of those technical problems: a partnership with Zocdoc, the popular online health-care scheduling company. Zocdoc is acting as a unified portal for multiple providers, so that people can sign up with a single, more user-friendly tool rather than wrestle with several different systems at once. While Chicago is the first city to make this specific agreement with Zocdoc, other health agencies are launching similar partnerships with private startups.
Before the pandemic, Zocdoc acted as a one-stop shop where patients could check out different doctors, compare medical providers, and make appointments. The company’s CEO, Oliver Kharraz, says the years spent bridging a fragmented health-care system unknowingly prepared it for taking on covid-19 vaccination appointments. After the idea was tested with the Mount Sinai Health System in New York, Zocdoc says, Chicago reached out about a partnership—and the system was up and running within a few weeks. Zocdoc connects with 1,400 different scheduling systems: doctors’ workflows remain unchanged, but patients all see the same simple interface no matter which provider they’re using.
“If you’re not plugged into the right system, then how are you going to get access?”
“You don’t have to register 10 times, and you know when the next available shot is for you,” Kharraz says.
Bloomgarden, the doctor at Northwestern Memorial, says the new Zocdoc tool will be a “great addition” to Chicago’s vaccine drive, but that it addresses only one of the issues with the rollout. After all, it’s still a version of the same first-come, first-served approach, which means it’s not solving the most critical problem: vaccines aren’t reaching the people who need them most.
Christina Anderson, deputy commissioner of the Chicago Department of Public Health and chief of operations for covid-19 response, says that while Zocdoc may not be the solution needed to reach and vaccinate elderly Chicagoans, it has the potential to help others who are struggling to get vaccinated, such as those without a primary care provider.
But Bloomgarden says truly making vaccines accessible will require targeted outreach—much of it offline.
Who you know matters
Local and federal officials in the US seem to be coming to the same conclusion. On February 9, President Joe Biden announced a new program that will provide vaccines directly to community health centers serving 30 million people across the US, two-thirds of whom are at or below the federal poverty line. Federally qualified community health centers receive federal funding to provide care to underserved populations.
Keon L. Gilbert, an associate professor in behavioral science and health education at Saint Louis University, says the approaches to serving particularly vulnerable populations have varied widely from state to state. Some states have moved adults over 65 up the priority list regardless of their other risk factors. Other strategies have come up against obstacles: when Dallas attempted to prioritize vaccinations for eligible people living in hard-hit zip codes—who tend to be people of color—the state threatened to reduce the county’s allotment of doses.
A new training model, dubbed “KnowNo,” aims to address this problem by teaching robots to ask for our help when orders are unclear. At the same time, it ensures they seek clarification only when necessary, minimizing needless back-and-forth. The result is a smart assistant that tries to make sure it understands what you want without bothering you too much.
Andy Zeng, a research scientist at Google DeepMind who helped develop the new technique, says that while robots can be powerful in many specific scenarios, they are often bad at generalized tasks that require common sense.
For example, when asked to bring you a Coke, the robot needs to first understand that it needs to go into the kitchen, look for the refrigerator, and open the fridge door. Conventionally, these smaller substeps had to be manually programmed, because otherwise the robot would not know that people usually keep their drinks in the kitchen.
That’s something large language models (LLMs) could help to fix, because they have a lot of common-sense knowledge baked in, says Zeng.
Now when the robot is asked to bring a Coke, an LLM, which has a generalized understanding of the world, can generate a step-by-step guide for the robot to follow.
The problem with LLMs, though, is that there’s no way to guarantee that their instructions are possible for the robot to execute. Maybe the person doesn’t have a refrigerator in the kitchen, or the fridge door handle is broken. In these situations, robots need to ask humans for help.
KnowNo makes that possible by combining large language models with statistical tools that quantify confidence levels.
When given an ambiguous instruction like “Put the bowl in the microwave,” KnowNo first generates multiple possible next actions using the language model. Then it creates a confidence score predicting the likelihood that each potential choice is the best one.
The news: A new robot training model, dubbed “KnowNo,” aims to teach robots to ask for our help when orders are unclear. At the same time, it ensures they seek clarification only when necessary, minimizing needless back-and-forth. The result is a smart assistant that tries to make sure it understands what you want without bothering you too much.
Why it matters: While robots can be powerful in many specific scenarios, they are often bad at generalized tasks that require common sense. That’s something large language models could help to fix, because they have a lot of common-sense knowledge baked in. Read the full story.
—June Kim
Medical microrobots that travel inside the body are (still) on their way
The human body is a labyrinth of vessels and tubing, full of barriers that are difficult to break through. That poses a serious hurdle for doctors. Illness is often caused by problems that are hard to visualize and difficult to access. But imagine if we could deploy armies of tiny robots into the body to do the job for us. They could break up hard-to-reach clots, deliver drugs to even the most inaccessible tumors, and even help guide embryos toward implantation.
We’ve been hearing about the use of tiny robots in medicine for years, maybe even decades. And they’re still not here. But experts are adamant that medical microbots are finally coming, and that they could be a game changer for a number of serious diseases. Read the full story.
We haven’t always been right (RIP, Baxter), but we’ve often been early to spot important areas of progress (we put natural-language processing on our very first list in 2001; today this technology underpins large language models and generative AI tools like ChatGPT).
Every year, our reporters and editors nominate technologies that they think deserve a spot, and we spend weeks debating which ones should make the cut. Here are some of the technologies we didn’t pick this time—and why we’ve left them off, for now.
New drugs for Alzheimer’s disease
Alzmeiher’s patients have long lacked treatment options. Several new drugs have now been proved to slow cognitive decline, albeit modestly, by clearing out harmful plaques in the brain. In July, the FDA approved Leqembi by Eisai and Biogen, and Eli Lilly’s donanemab could soon be next. But the drugs come with serious side effects, including brain swelling and bleeding, which can be fatal in some cases. Plus, they’re hard to administer—patients receive doses via an IV and must receive regular MRIs to check for brain swelling. These drawbacks gave us pause.
Sustainable aviation fuel
Alternative jet fuels made from cooking oil, leftover animal fats, or agricultural waste could reduce emissions from flying. They have been in development for years, and scientists are making steady progress, with several recent demonstration flights. But production and use will need to ramp up significantly for these fuels to make a meaningful climate impact. While they do look promising, there wasn’t a key moment or “breakthrough” that merited a spot for sustainable aviation fuels on this year’s list.
Solar geoengineering
One way to counteract global warming could be to release particles into the stratosphere that reflect the sun’s energy and cool the planet. That idea is highly controversial within the scientific community, but a few researchers and companies have begun exploring whether it’s possible by launching a series of small-scale high-flying tests. One such launch prompted Mexico to ban solar geoengineering experiments earlier this year. It’s not really clear where geoengineering will go from here or whether these early efforts will stall out. Amid that uncertainty, we decided to hold off for now.
