One of the proven methods of fighting cancer tumors is by injecting the tumor with a stimulant that will recruit immune cells to destroy tumor cells. Usually, this is done by injecting directly into the tumor, but it can be challenging when the tumor is in a hard-to-reach location.

Stanford’s new research has developed a new synthetic molecule that combines a tumor-targeting agent with another molecule that triggers the immune system to attack the tumor. The immunotherapy can be administered intravenously and can target either a specific location or multiple tumors.

The research team has just completed testing on laboratory animals and they were able to induce complete tumor regression in half the test population infected with aggressive triple negative breast cancers with just one injection. They had similar results from a group of mice infected with pancreatic cancer.

“We essentially cured some animals with just a few injections,” said Jennifer Cochran, PhD, the Shriram Chair of the Department of Bioengineering. “It was pretty astonishing. When we looked within the tumors, we saw they went from a highly immunosuppressive microenvironment to one full of activated B and T cells — similar to what happens when the immune-stimulating molecule is injected directly into the tumor. So, we’re achieving intra-tumoral injection results but with an IV delivery.”

Building on Earlier Research. The work in this study builds on that done in 2018 by Ronald Levy, MD and Edit Saga-Barfi, PhD, both of Stanford School of Medicine. That study used the same immune-activating agent and a different one injected directly into the tumor site. The results of that trial were complete tumor eradication, elimination of distant metastases and also blocked recurrence in mammary tumors. The research group then launched a clinical trial in people with non-Hodgkin lymphoma.

“The surprising result of the new research was that the sculpting of the tumor microenvironment by this intravenously administered molecule was identical to that achieved by injecting immune stimulating agents directly into the tumor,” Levy said. “This is a big advantage because it’s no longer necessary to have an easily or safely injectable tumor site.”

Next Steps. Before any human testing can occur, much more research needs to be done. The level of optimism is high in the research team because the tumor-targeting portion of the PIP-CpG molecule (PIP) appears to recognize proteins called interns. Because these are found at high levels on the surface of many cancer types, there is a possibility for an off-the-shelf treatment for patients with a variety of cancer types.
Cochran and her team have coupled the PIP-CpG molecule with probes that can be visualized with near-infrared imaging or positron emission tomography. This gives them the tool to track the location of hard-to-see cancers.
​
“These integrin-targeting molecules act like guided missiles,” Cochran said. “They can deliver toxic drugs or imaging agents. Now we’re using them to deliver a signal that riles up the immune cells to fight the tumor.” That signal, CpG, mimics a pattern of DNA common in bacteria and viruses but rarely found in vertebrates.
“After more than 10 years of work on PIP, it is rewarding to experience this convergence of expertise from laboratories around Stanford, which allowed us to develop a highly promising new cancer treatment strategy,” Cochran said.

The single most important factor in surviving a battlefield injury is the combat medic. The medic is first on the scene and can administer help within the Golden Hour or even Golden Ten Minutes. Quick, effective medical procedures can be the difference between life and death.

The Defense Advanced Research Projects Agency (DARPA) has selected Raytheon BBN to lead a team to develop an augmented reality device that will provide the combat medic with a virtual assistant. The system will use a set of AR goggles, which will provide visual information on 50 different medical procedures.

Medics are highly trained in the most common battlefield injuries, but they aren’t doctors or surgeons and often have no experience in little-used procedures which may be needed at a moment’s notice. This is why DARPA is working on its Medical Assistance, Guidance, Instruction and Correction (MAGIC) system. 

MAGIC uses a pair of augmented reality goggles equipped with audio and video sensors and special artificial intelligence software that can act as an assistant to monitor the situation and advise the medic on how to proceed.

Raytheon will use machine learning technology to ‘teach’ the system both medical skills and situation assessment skills. The initial prototype will study 2,500 stereo videos and almost 50 million images. The machine learning process will review the historical data and synthesize useful concepts and solutions from that data.

When the AI software is ready, MAGIC should be able to provide spoken suggestions to medics or project visual overlays on the scene to guide their hands through needed medical procedures. The system will also provide events timing from engagement to final hand-off to field hospital personnel. MAGIC will also provide dosage guidance for in-field medications.

A first prototype is expected in about 18 months.
​
"The combat medical environment is challenging and chaotic," said Raytheon BBN scientist Brian VanVoorst. "Our goal for the Raytheon BBN MAGIC AI tool is to help support personnel to provide guidance as needed without disrupting their concentration."

Nobody enjoys getting the jab. Whether it's a standard shot, an epidural or dental injection, or a daily shot for needed medicine, the experience has created a class of phobias, with one Harvard study estimating that fear of needles affects up to 25% of adults. 

Despite so much innovation in other areas of medicine, the experience of getting a shot or injection hasn't really changed all that much in the last century. But thankfully new technologies are finally catching on and changing how people think about needles, and the technology is being embraced readily by providers.

"Our injection technologies serving the dental and epidural community have been growing," says Arjan Haverhals, CEO of Milestone Scientific, which has pioneered a computer-controlled injection technology that guides the injection below the patient's pain threshold, making injections precise, efficient, and virtually painless. "We have a growing number of hospitals embracing our technology. We’ve also entered the private pain clinic market to treat chronic back pain. Our dental delivery system, which is available nationwide and in Canada, has seen growing interest from all dental professionals worldwide."

A handful of technology innovators like Milestone Scientific are bent on improving the jab through wearables, computer guidance, and needle-free injection technologies. 

Portal Instruments, an MIT spinoff, is another player in the space. The company is bringing a needle-free injection device to market that delivers a rapid, high-pressure stream of medicine, as thin as a strand of hair, through the skin in adjustable dosages, causing little to no pain. A connected app tracks each dose and the medicine's effects and uploads that information to the cloud, for patients and doctors. The device would be sold as a drug-device combination product to medical professionals and provided to patients with a prescription.

Enable Injection designs, manufactures, and sells wearable delivery devices for injectable drugs. Patients attach the device onto the skin by themselves, and trigger needle insertion and retraction by pressing a button on the device. Through a partnership with Flex, Enable also offers a version of the drug delivery platform that may connect to smartphones via Bluetooth. According to the company's website, the Enable Smart enFuse product could be "pre-integrated" into the digital health platform or strategy of an organization for improved patient data collection. 

It's little surprise there's so much activity around increasing outcomes and lowering pain associated with injections. Growth of the global injectable drug delivery devices market is expected to increase from $16 billion in 2019 to $21.3 billion in 2023, partly due to increased demand for injection devices that can be used and monitored in the home environment. Milestone, for one, has seen significant interest in the U.S, where epidural-specific systems are in place and trials underway in Florida, Michigan, Texas, South Carolina, Illinois, and Massachusetts, to name a few. The Dental delivery system is used widely throughout the country with growing interest from specialty practices including periodontic, cosmetic, and pediatric. 

"For medical, this means healthcare outcome for patients at lower costs. For dental, it means pain-free injections, more comfort, and less fear for patients," says Haverhals, "plus the ability for additional business for dentists. In fact, many of our dentists have noted word-of-mouth as a marketing tool for growing their business just by adopting our injection technology."

Engineers from Yale University have developed a wearable device that can help individuals assess whether they have been exposed to SARS-CoV-2, the coronavirus that causes COVID-19. The cheap device can clip onto a person’s clothes and capture aerosolized viral particles in the surrounding environment.

From rapid tests to vaccines, many extraordinary innovations have helped us navigate this global pandemic. While we have several ways to determine whether a person has been infected with SARS-CoV-2, we still can only guess when and how someone has been exposed to the virus.

This innovation from a team of Yale University researchers is hoping to fill that surveillance gap. Called the Fresh Air Clip, the device is cheap, designed to attach to a person’s collar and capture aerosolized viral particles around a person’s mouth and nose.

The clip captures viral particles on a polydimethylsiloxane (PDMS) surface. At the end of a day, or several days, a wearer removes the clip and sends it to a lab, which uses polymerase chain reaction (PCR) analysis to determine the presence of SARS-CoV-2.

A new study is reporting on several tests of the Fresh Air Clip establishing it can effectively capture airborne viral particles. One experiment involved supplying the clips to several volunteers who wore the monitors for up to five days. Of the 62 monitors deployed, five returned positive results, showing exposure to SARS-CoV-2.

“Of the positive Fresh Air Clips, four were worn by restaurant servers and one was worn by a homeless shelter staff person,” the study shows. “Notably, two positive samples collected in restaurants with indoor dining were found to have high viral load when compared to the other samples (>100 copies per clip), suggestive of close contact with one or more infected individuals.”

As well as establishing the wearable monitor as being able to capture detectable levels of viral particles, the researchers note the device is sensitive enough to catch exposure events at sub infectious doses. This suggests the volume of viral particles picked up by the monitor allows for the quantification of environmental exposure to the virus. This is important, as it means the device does not simply offer an indication of viral exposure but a measure of the level of exposure.

Krystal Pollitt, a researcher working on the device, says one interesting potential use for the device could be to test the effectiveness of ventilation settings in COVID positive patient hospital rooms. Speaking to Yale News recently, Pollitt said her team found airborne traces of SARS-CoV-2 in hospital rooms that were thought to be well ventilated.

“We found this to be really interesting because we know that one of the infection control measures that is being highly recommended is enhanced ventilation,” said Pollitt. “Within the hospital network we had very high air change rates. Despite having those high air change rates, we could still detect airborne levels across the room.”

In its current form, the Fresh Air Clip can screen indoor environments and establish whether they are high-risk areas for exposure. Pollitt also said the wearable can also be used to identify indoor exposure events days before positive cases appear.

“The Fresh Air Clip can be useful for early identification of exposure events and allow for rapid action to be taken,” Pollitt said. “Exposed individuals can get tested or quarantine to prevent potential community transmission.”

The next big step for the device will be to develop ways for the monitor to offer real-time notification of viral exposure, in much the same way a radiation strip can immediately notify a wearer they are exposed to gamma or x-rays. Pollitt says she is interested in further developing the device with real-time exposure notifications.
​
“It’s key to report back results quick,” Pollitt says. “We are keen to incorporate techniques for real-time SARS-CoV-2 detection.”
The new study was published in the journal Environmental Science & Technology Letters.

Amazon plans to expand its virtual health service benefit to all its U.S. employees this summer while also making it available to other companies.

Eighteen months ago, the tech giant announced it was piloting a new virtual health service benefit for employees and their families in the Seattle region called Amazon Care.

The service offers virtual visits, in-person primary care visits at patients' homes or offices and prescription delivery. The on-demand healthcare service enables employees to connect with medical professionals via chat or video conference, typically in less than 60 seconds, and eliminates lengthy wait and travel times to get medical attention, Amazon said in a press release.

Starting Wednesday, Amazon Care is available to serve other Washington-based companies. Beginning this summer, Amazon Care will expand its virtual care to companies and Amazon employees in all 50 states. Amazon Care’s in-person service will expand to Washington, D.C., Baltimore and other cities in the coming months, the company said.

Services include video care, in-app text chat with clinicians, mobile care visits, prescription delivery from a care courier and in-person care, where Amazon Care can dispatch a medical professional to a patient’s home for services ranging from routine blood draws to listening to a patient’s lungs.

Officials said Amazon Care will be able to help with urgent issues like colds, allergies, infections, minor injuries, preventive health consults, vaccines, lab work, sexual health services like contraception and sexually transmitted infection testing and general health questions. 

Patients also can access preventive care such as annual vaccinations, health screenings and lifestyle advice. The service also supports patients’ wellness needs including nutrition, pre-pregnancy planning, sexual health, help to quit smoking and more, the tech giant said.

Amazon and other companies are increasingly focused on the home as a site of care. The company joined with Intermountain Healthcare and Ascension along with other health systems and home care companies to form the Moving Health Home coalition, which aims to change the way policymakers think about the home as a site of clinical service. The group is lobbying Congress to make permanent changes to home health care reimbursement policies.

Amazon officials said the program has received positive feedback from employees as the service is uniquely focused on patients and their changing needs. During shutdowns forced by the COVID-19 pandemic, doctors’ offices were seeing fewer children for pediatric vaccines, so Amazon Care quickly adjusted its services to offer the vaccines in families’ homes, the company said.

Gina Baird, whose spouse works at Amazon, participated in the Amazon Care pilot program when her three-year-old daughter woke up at 2 a.m. with a terrible cough.

"Of course we were worried about COVID-19 and certainly did not want to go to an urgent care center or emergency room if we could avoid it,” said Baird in a statement in the Amazon press release. “Using Amazon Care, we were able to connect with a clinician in under a minute who provided medical advice that helped us get through the night. She also prescribed a medication that was delivered to our doorstep by 9 a.m. the next day. Thanks to Amazon Care, we were able to manage her illness without ever having to leave the house.”

Ashley Bennett, senior operations manager at Amazon’s fulfillment center in Kent, Washington, said the on-demand healthcare services offered by Amazon Care make her feel that she has more control over the system.

"It’s at my leisure. That’s power. I’m not waiting on someone else to show up on their schedule," Bennett said in a statement. 

Amazon has been rapidly expanding its reach in the healthcare space, most notably in 2018 with its acquisition of online pharmacy PillPack. In November, the tech giant launched Amazon Pharmacy, the long-anticipated online storefront that will enable customers to purchase prescription drugs online and have them shipped to their homes.

Amazon started an ambitious health tech startup, Haven, with JPMorgan Chase and Berkshire Hathaway in 2018, but that venture shuttered in January.
​
The tech giant has instead pivoted to address healthcare costs by focusing on employee healthcare through primary care models. Amazon teamed up with trendy tech-enabled primary care group Crossover Health to launch health centers in five major regions—Dallas-Fort Worth, Phoenix, Louisville, Detroit and two California metro areas—to serve Amazon employees and their families.

Apple is working on technology to detect a user's blood pressure using neural networks and seismocardiogram data, negating the need for a blood pressure cuff.

According to a patent application published Thursday, a wearable device, potentially paired with Apple Watch, might one day be capable of monitoring a user's blood pressure without the need for any additional peripherals.

The patent application, titled "Interpretable neural networks for cuffless blood pressure estimation," explores the use of neural networks to estimate blood pressure using seismocardiogram data. Unlike an electrocardiogram, which relies on electrical signals to monitor a heart rate, a seismocardiogram measures the micro-vibrations produced by the heart beating.

There exist seismocardiogram devices small enough to be considered wearable, though these sensitive systems are typically placed over a user's sternum to measure minute vibrations in or near the heart. How Apple intends to deploy such a device was not discussed in the patent filing.

According to Apple's patent, the system would work by leveraging an individually pruned neutral network accepting a seismocardiogram as input. That neural network would then use the data to estimate blood pressure.

For example, Apple could create a baseline model by training the neural networks with seismocardiogram data and blood pressure measurements from a group of subjects. Using that as a baseline, the system could then prune the model for subsequent users. The initial dataset would be collected from users performing different sedentary activities.

From there, Apple contends that the neural network could be used to accurately estimate a user's blood pressure without a cuff. As the patent points out, the system could use the neutral network "to determine blood pressure based on accelerometer or gyroscope data," which are already present in Apple devices.

Current versions of the Apple Watch can be used to monitor and analyze different types of health data, including heart rates with an optical sensing system, heart rhythms via a built-in electrocardiogram or blood oxygen sensing on the Apple Watch Series 6. Since the Apple Watch release, Apple has been continually expanding the device's health toolkit, and Apple may be looking to build out a set of health-minded accessories. 

The patent lists Siddharth Khullar, Nicholas E. Apostoloff, and Amruta Pai as its inventors. Among them, Apostoloff has been named on a previous patent dedicated to facial analysis and emotion detection.
​
This isn't Apple's first patent focused on blood pressure monitoring. In 2020, the company filed a patent application for an Apple Watch-supported system that could use pulse transit time to measure blood pressure. Another system could use pressure sensor data, and Apple has explored how to monitor blood pressure without a cuff in the past.

No one disputes that cars, trucks, and SUVs will become increasingly connected over the next decade. From Amazon Alexa compatibility to navigation-linked speed limiters, the list of internet-powered features you’ll one day use during your commute grows every year.

Some technologies will make driving more convenient, especially when it becomes a tedious task. That, however, is just the start. Your car might save your life by becoming a doctor – no medical school training required.

In a recent interview, Steve Surhigh, the vice president and general manager of automotive cloud services for Samsung-owned Harman, explained how a car could monitor the driver’s health.

Eyes On The Driver. Keeping an eye on the driver is nothing new; millions of cars already do it. Mercedes-Benz inaugurated Attention Assist technology on the 2009 E-Class, and the on-going race toward autonomy has created vehicles that literally look you right in the eyes.

Cadillac’s Super Cruise system relies on a driver-facing camera to tell whether the driver is paying attention. If it notices you’re looking down at a smartphone or looking nowhere because you’re dozing off, it emits visual and audible warnings prompting you to stay focused and wake up. In some cases, the automated system might even take control.

Surhigh says Harman can build wellness monitoring technology on these foundations.

Teledoctors. “Some carmakers are talking about a teledoctor-type service. So, if there is a system that monitors the driver’s vital signs, and it detects something is noticeably wrong, having a teledoctor available could be part of the vehicle’s connectivity package,” Surhigh explained. “Not only can you monitor vitals, but you can also be proactive in terms of responding to an issue, whether that’s something that would be heart rate-based or based on blood sugar levels.”

Are you curious about how your car can monitor your heart rate? Look no further than the nearest gym. Sensors in the steering wheel, similar to those found on treadmills or stationary bikes, could track your pulse. Alternatively, Surhigh says, your car could receive this information from wearable devices, like smartwatches and fitness trackers. Data could be shared via Bluetooth or in-car 5G. Ford has even floated the idea of burying six pulse sensors in the driver’s seat.

“Carmakers are already integrating technology that monitors driver attentiveness. Once you get some of those foundational use cases built, the incremental costs of being able to do other things are very manageable. At that point, it’s more of a software type of build than one related to hardware,” explained Surhigh.

The possibilities don’t end at being able to track the driver’s heart rate. It’s not far-fetched to imagine mandatory breathalyzer-based ignitions for motorists who have a long history of driving under the influence, for example.

Whether you’ll tick the “heart rate monitor” box on an options list depends on your profile. If you’re a 24-year old buying a Volkswagen GTI, there’s a good chance you’re more interested in a surround-sound system and Amazon Alexa compatibility. If you’re an 84-year old in the market for a Ford Expedition? Well, I’m not going to generalize, but there’s a better chance you’ll be concerned about your pulse than someone born 60 years after you.

Although pulse tracking isn’t for everyone, it’s one of several dozen functions car companies are looking at integrating into their infotainment systems.
​
“The digital experience is replacing a lot of what previously differentiated carmakers, whether it was horsepower or some other vehicle experience linked to the engine, the braking system, or other components,” Surhigh said. “Now, they’re largely looking at the car’s digital components for differentiation.”

From predicting outbreaks to devising treatments, doctors are turning to AI to combat the COVID-19 pandemic.

Why It Matters. While machine learning algorithms were already becoming a part of health care, COVID-19 is likely to accelerate their adoption. But lack of data and testing time could hinder their effectiveness – for this pandemic, at least.

What's Happening. With millions of cases and outbreaks in every corner of the world, speed is of the essence when it comes to diagnosing and treating COVID-19. So it's no surprise doctors were quick to employ AI tools to get ahead of what could be the worst pandemic in a century.

• HealthMap, a web service run by Boston Children's Hospital that uses AI to scan social media and other reports for signals of disease outbreaks, spotted some of the first signs of what would become the COVID-19 outbreak. This was days before the WHO formally alerted the rest of the world.
• Early in the epidemic, the Chinese tech company Alibaba released an AI algorithm that uses CT scans of possible coronavirus patients and can diagnose cases automatically in a matter of seconds.
• In New York, Mount Sinai Health System and NYU Langone Health have developed AI algorithms that can predict whether a COVID-19 patient is likely to suffer adverse events soon and determine when patients will be ready to be discharged. Such systems can help overburdened hospitals better manage the flow of supplies and personnel during a medical crisis. 

The Big Picture. Even before COVID-19, AI was already becoming a more significant part of modern health care. Nearly $2 billion was invested in companies involved in health care AI in 2019, and in the first quarter of 2020, investments hit $635 million – more than four times the amount seen in the same period of 2019, according to digital health technology funder Rock Health.

• The advance of AI is partially a result of the rapid increase in data, the lifeblood of any machine learning system. The amount of medical data in the world is estimated to double every two months.
• Engineer and entrepreneur Peter Diamandis told Wired an estimated 200 million physicians, scientists, technologists, and engineers are now working on COVID-19, generating and sharing data "with transparency and at speeds we've never seen before."
• "We understand who is at risk and how they're at risk, and then we can get the right treatment to them," says Zeeshan Syed, the CEO of Health[at]Scale, an AI health care startup.

In Trials. AI has demonstrated in recent trials a decent record of success, especially when it comes to rapidly diagnosing COVID-19 by interpreting medical scans.

• A study published in Nature Medicine in May found an AI system was more accurate than a radiologist in diagnosing COVID-19 patients using CT scans – X-ray images of lungs – combined with clinical symptoms. 
• A systematic review of preprint and published studies of AI diagnostic systems for COVID-19 published in the British Medical Journal in April noted the models reported "good to excellent predictive performance." However, they cautioned the data was still limited for real-world applications and at high risk for bias.

The Catch. That's the perennial challenge for AI systems in any field. Experts worry models that perform well in an experiment may not be able to replicate that success in a hospital under stress.

• "There is a lot of promise in using algorithms, but the data in the biomedical space can be really difficult to deal with," says Gabe Musso, the chief science officer at BioSymetrics. This biomedical AI company uses machine learning for simulation-based drug discovery. Genetic data, imaging data, and data from electronic health records are often unstructured and rarely share a common format, complicating efforts to feed the information into an algorithm.
• Many of the AI diagnostic systems being rushed into the fight against COVID-19 were developed before the pandemic and thus were trained on other respiratory diseases like tuberculosis. That reduces their accuracy – especially if their training datasets don't match the gender or age of typical COVID-19 patients.
• As a result, pioneering computer scientist Kai-fu Lee wrote recently, "I would give [AI] a B-minus at best" for its performance during the pandemic.

The Bottom Line. As both the size and quality of medical data on COVID-19 improves, so should the AI systems that draw from it. But that will take time.

The very first contact tracing app powered by Google and Apple's exposure notification APIs has gone live in Switzerland.

As announced on Twitter by EPFL yesterday, 'SwissCovid' is now undertaking a large scale pilot, with hopes that it will pave the way for public availability by mid-June.

As of today, employees at @EPFL, @ETH_en, @vbs_ddps, and some hospitals and cantonal administrations can download the digital proximity tracing application #SwissCovid. This large-scale pilot paves the way for public availability by mid-June. https://t.co/E9hl43g8Ca #COVID19 #DP3T

In an announcement the institute stated:

Several thousand people in Switzerland can now download "SwissCovid," the official application for tracing contacts at risk of transmission of COVID-19 if they wish. "This is the first time that the operating system updates from Google and Apple enable its deployment and testing on such a large scale," says Professor Edouard Bugnion, Vice-President for Information Systems at EPFL. He was at the heart of discussions with Google and Apple to have them adopt the "DP3T" protocol led by the two Swiss Federal Institutes of Technology. Alfredo Sanchez, project manager, notes that "this gives great responsibility to the Swiss testers, as many other countries intend to adopt the same protocol later on."

One important footnote is that while the pilot is ongoing, the Swiss parliament will deliberate revisions to the law on epidemics. MPs must debate and approve the scheme before it is offered to the public, however recent research has suggested that as many as 70% of Swiss residents support the program.

This is the first large-scale testing of an app that uses Apple and Google's exposure notification technology. As per the two companies' stipulations, the operation is also decentralized:
​
SwissCovid operates in a "decentralized" way, which means that the operations that are essential from a privacy point of view are not carried out on a centralized server, but on each phone. The app uses Bluetooth to exchange and record the ephemeral proximity identifiers of other phones in the vicinity. These identifiers are kept on the phone unless a person is tested positive for COVID-19. In that case, their doctor will give them a single-use code that allows them to voluntarily share the ephemeral keys on their own phone that correspond to the days when the person was contagious. These keys are sent to a server managed by the Swiss administration.

A company that makes internet-connected thermometers has followed the flu more closely than the C.D.C. can. Now the devices may be turning up cases of COVID-19.

A company that uses internet-connected thermometers to predict the spread of the flu says it is tracking the coronavirus in real-time – something that had been impossible, given the lack of testing for the disease.

Kinsa Healthhas sold or given away more than a million smart thermometers to households in which two million people reside, and thus can record fevers almost as soon as consumers experience them.

For the last few years, Kinsa’s interactive maps have accurately predicted the spread of flu around the United States about two weeks before the Centers for Disease Control and Prevention’s surveillance tool, the weekly FluView tracker.

The thermometer data “acts as an early warning system for illness spreading,” said Inder Singh, the company’s founder. The C.D.C.’s system lags because it relies on weekly reports from hundreds of doctors’ offices and hospital emergency rooms about what symptoms they are seeing in patients.

Company scientists are uniquely positioned to identify unusual clusters of fever because they have years of data for expected flu cases in each ZIP code. A sudden spike that far exceeds estimates for flu for a given date may well indicate the coronavirus has arrived.

Medical experts were enthusiastic about the possibility that smart thermometers could be used to track the virus in the United States. Having millions of data points allows Kinsa to produce daily maps showing which counties are seeing spiking fevers.

The most common symptoms of infection with the coronavirus is a fever – about 90% of patients suffer from it, according to the World Health Organization.

“This is very, very exciting,” said Dr. William Schaffner, a professor of preventive medicine at Vanderbilt University. “This is 21st-century disease surveillance, and we’ve been rooted in the mid-20th century with something very labor-intensive.”

Dr. Peter J. Hotez, dean of the National School of Tropical Medicine at Baylor College of Medicine in Houston, said: “If this tells you where there are new major clusters of fever, it tells you where to swoop in with your test kits.”

Kinsa’s latest map of fever spikes shows areas that are known to have many cases of COVID-19, the illness caused by the coronavirus. But the data also point to spots in Florida, Michigan, Arizona, and eastern Texas, where not as many cases have been reported.

Just last Saturday, Kinsa’s data indicated an unusual rise in fevers in South Florida, even though it was not known to be a COVID-19 epicenter. Within days, testing showed that South Florida had indeed become an epicenter.

Dr. Nirav Shah, a former New York State health commissioner who is an adviser to Kinsa, said real-time fever data “could speed up public health the way Twitter sped up the news cycle.”

Demand for Kinsa’s smart thermometers has skyrocketed since the coronavirus pandemic began, Mr. Singh said, and the company is now selling 10,000 a day, which is creating production problems but also multiplying the amount of data coming in each day.

The thermometers connect to a cellphone app that instantly transmits their readings to the company. Users can also enter other symptoms they feel. The app then gives them general advice on when to seek medical attention.
​
Because influenza usually produces higher, more protracted fevers than common colds do, the company’s software estimates which ZIP codes appear to be hit by flu rather than by other, milder cold viruses.