Discovering ways to non-invasively early detect COVID-19 from heart rate, sleep, or a cough sound, even among the asymptomatic

Heart rate, sleep quality, daily movement–cough sound frequency? Several studies in the US and UK are attempting to turn up ways to early diagnose mildly symptomatic, asymptomatic, or even pre-symptomatic COVID-19 cases, without the PCR swab or a blood test.

The more obvious of the two comes out of the Scripps Research Translational Institute. The DETECT study started in March (!) with 30,500 participants sending in data in the first six weeks of the study on heart rate, sleep quality, and daily movement. This information was then matched with self-reported symptoms and diagnostic tests taken if any. In this way, new infections and outbreaks could be detected at an earlier stage.  The study is attempting to confirm if changes in those metrics in an individual’s pattern can identify those even at a pre-symptomatic or asymptomatic stage. 3,811 reported symptoms, 54 reported testing positive, and 279 negative for COVID-19. The numbers seem small, but the analysis carries out that the combination of sensor and symptom data performed better in discriminating between positive and negative individuals than symptom reporting alone. The symptom data were taken from Fitbits and any device connected through Apple HealthKit or Google Fit data aggregators, then reported on the research app MyDataHelps. FierceBiotech, Nature Medicine (study)

Also using vital signs, back in August, Fitbit released early data on a 100,000+ study where changes in heart rate and breathing could detect about half of diagnosed cases at least one day to a week before diagnosis. Symptomatic cases were 1,100 in this sample. Heart rate and breathing were detected to become more frequent in the symptomatic, with the variability in time between each heartbeat dropping, resulting in a more steady pulse. The preferred tracking was at night during rest. However, there was a 30 percent false positive rate on the algorithm used, which is extremely high. FierceBiotech Related to this work, Fitbit was selected at the end of October by the US Army Medical Research and Development Command (USAMRDC) to receive nearly $2.5 million from the US Department of Defense through a Medical Technology Enterprise Consortium (MTEC) award to advance a wearable diagnostic capability for the early detection of a COVID-19 infection. Fitbit will be working with Northwell Health’s Feinstein Institutes for Medical Research to validate their early detection algorithm. Business Wire

And what about that ‘Covid Cough’? MIT is researching that this cough is different than other coughs, like from cold or allergy. Their research found that there’s a difference in the sound of an asymptomatic individual’s cough–and that sound frequency difference could not be heard by human ears. (Dog ears perhaps?) MIT researchers created “the largest audio COVID-19 cough balanced dataset reported to date with 5,320 subjects” out of 70,000 cough samples. The algorithm performed well. “When validated with subjects diagnosed using an official test, the model achieves COVID-19 sensitivity of 98.5% with a specificity of 94.2% (AUC: 0.97). For asymptomatic subjects it achieves sensitivity of 100% with a specificity of 83.2%.” This sure sounds like an AI screening tool that is inexpensive and convenient to use with multiple populations even daily. IEEE-EMB  BBC News reports that similar studies are taking place at Cambridge University, Carnegie Mellon University, and UK health start-up Novoic. The Cambridge study used a combination of breath and cough sounds and had an 80 percent success rate in identifying positive coronavirus cases from their base of 30,000 recordings.

All of these will be useful, but still need to be validated–and that takes time, for which this Editor thinks is short as this virus, like others, will eventually 1) mutate out or 2) be effectively treated as we do with normal flus. But down the road, these will serve as a template for new ways for early screening or even diagnosis of other respiratory diseases.

Connected Health Conference highlights (so far): FCC’s $100 million telehealth pilot, NIH’s ‘All of Us’, MIT’s social robots integrating AI

Expanding FCC connected health programs. FCC Chairman Ajit Pai in his keynote reinforced the agency’s interest and support of connected health initiatives, from rural to opioids. Most of the programs have a rural focus to bring broadband and telehealth/RPM to the ‘end of the line’ in underserved communities, something close to Mr. Pai’s heart as his parents were both rural physicians in Kansas..

  • This summer, the Connected Care Pilot Program was proposed and approved unanimously in August [TTA 9 Aug]. Funding for this is proposed at $100 million.
  • The spending cap for the rural healthcare program, which has been around since 1997’s dial-up days and now includes telemedicine and remote monitoring, was increased for 2017-2018 from  $400 million to $571 million, a 43 percent increase. The FCC has pledged to fully fund 2018 programs.
  • New initiatives were announced covering new uses for telehealth and remote patient monitoring:
    • Connected care at home via RPM as part of the Connected Care Pilot Program
    • Cancer care in partnership with the National Cancer Institute. The Launch program for rural and underserved communities aims to bring high-quality cancer care to where patients work and live through bringing together government, academia and community health providers.
    • For opioids, there are two programs. One is expanding the mapping broadband health platform to include critical drug use data. This will allow users to rapidly visualize, overlay, and analyze broadband and opioid data together at the national, state, and county level. The second is to launch a chronic pain management and opioid use challenge as part of the pilot program.  Mobihealthnews

A status report on NIH’s All of Us. Back in January as part of setting the stage for 2018, this Editor briefly mentioned the National Institute of Health’s massive All of Us program, part of the Federal Precision Medicine Initiative (PMI). All of Us needs almost all of us–their goal is to collect data on at least one million Americans for a major leap forward on data supporting population health. Dr. Dara Richardson-Heron, All of Us’ chief engagement officer, confirmed that over 100,000 participants have registered since the launch in May, with over 65,000 completing the full protocol. She mentioned that 75 percent of signups are from groups often underrepresented in modern medical research, with 50 percent from racial and ethnic minorities. The Mobihealthnews article ends on a ‘Debbie Downer’ note of doubting whether the program will reach enrollment goals, the cost will be justified, and whether the data will be kept private as promised.

MIT’s social robots may be the future of emotional support for wellbeing. MIT associate professor Cynthia Breazeal heads up the Personal Robots Group and is working on how to integrate AI into emotional robots for pediatric patients at Boston Children’s Hospital. The robots serve as a go-between child life specialists and the patient. The initial results were positive, with higher verbal scores (as a measure of engagement) than with stuffed bears or digital avatars. Professor Breazeal wants to extend the technology to older adults for wellbeing and engagement. Running against the conventional wisdom, their research found that older adults were more open to technology than the children. Following MIT’s work are companies like Hasbro and Embodied. Mobihealthnews.

No more smartwatches or connected tablets? Reading human vital signs through walls via a reverse Wi-Fi box and machine learning

A monitoring future without smartwatches, pendants, or transmitting readings through your tablet? A professor at MIT has developed a box, about the size of a Wi-Fi router, that can monitor a person’s vital signs throughout the house. Like Wi-Fi, the device emits a low-power wireless radio signal, but the device then measures the return on those radio signals from the bodies in the residence. The ‘neural network’ takes the data from the tiny changes in electromagnetic signals to track physiological signs as the person moves from room to room, even through walls, using machine learning to analyze those reflected signals and extract physiological data such as breathing, heart rate, posture, and gait. The device has also been tested on sleep patterns including sleep stages, which means it could replace the awkward and artificial electrodes in a lab which are usual for sleep testing.

Dina Katabi, a MIT professor of electrical engineering and computer science, built this box in her lab. So far it has been tested in over 200 homes around the US, tracking the baselines of healthy people and those with Parkinson’s, Alzheimer’s, depression, and pulmonary diseases. In the case of Parkinson’s, the data gathered by the device over eight weeks in the home of a patient indicated that his gait improved around 5 or 6 am, right around the time he took his medication. Data is encrypted and Professor Katabi has stated that the setup process requires a user to complete a series of specific movements before it’s possible to be tracked. She has also cofounded a startup, Emerald Innovations, to commercialize the technology. If it is workable beyond the test stage, it has the capability to revolutionize remote patient monitoring. Engadget, MIT Technology Review

Butterfly IQ handheld ultrasound offers clinical-quality body imaging for under $2,000

[grow_thumb image=”https://telecareaware.com/wp-content/uploads/2018/03/butterfly-iq.jpg” thumb_width=”200″ /]Butterfly IQ is a NYC and Connecticut-based company which has developed a handheld ultrasound that transmits images to a smartphone. Where it differs from current handhelds like GE’s VScan is that it uses a single transducer for all images both near-field and deeper in body, and connects to a iPhone loaded with their software.

Larger machines, even on portable carts like the Philips Lumify [TTA 27 Mar] operate on an older vibrating crystals-based technology. The IQ uses capacitive micro-machined ultrasound transducers or CMUTs. 

It claims to be FDA-cleared for 13 applications. All this is delivered for under $2,000, far under other handhelds or carts (VScan is above $12,000, Lumify about $6,000), with delivery this year (pre-order notification at present) in the US only. Butterfly is also working on problems such as the volume of blood a heart is pumping or detecting problems like aortic aneurysms.

The IQ has a brace of impressive testimonials from doctors at Yale, UC Irvine, Denver Health, Rocky Vista University, Mass General, St. Elizabeth’s (Boston), and Metrowest Medical Center. According to vascular surgeon and company chief medical officer Dr. John Martin, he used it on himself to diagnose a mass in his neck last year that turned out to be Stage 4 cancer, for which he is under treatment. Daily Mail, 9to5 Mac, MIT Technology Review  Hat tip to Editor Emeritus Steve Hards

Wearable haptic/Braille guidance system for the visually impaired

MIT researchers from their CSAIL (Computer Science and Artificial Intelligence Laboratory) unit have developed a system that is designed to aid the visually impaired in accurately navigating a room, with or without the assistance of a cane. It consists of a 3-D camera worn on the abdomen, a belt that has vibrational (haptic) motors, and an electronically controlled Braille interface worn on the side of the belt. The camera is worn on the chest as the optimum and least interfering body location. The pictures taken are analyzed by algorithms that quickly identify surfaces and their orientations from the planes in the photo, including whether or not a chair is unoccupied. The belt sends different frequency, intensity, and duration tactile vibrations to the wearer to help identify nearness to obstacles or to find a chair. The Braille interface also confirms the object and location through key initials (‘c’ for chair, ‘t’ for table) and directional arrows. According to the MIT study, “In tests, the chair-finding system reduced subjects’ contacts with objects other than the chairs they sought by 80 percent, and the navigation system reduced the number of cane collisions with people loitering around a hallway by 86 percent.” MIT News, Mashable, ‘Wearable Blind Navigation’ paper Hat tip to Toni Bunting of TASK Ltd.

 

Sonde Health using voice as a biomarker for diagnosis

Back in 2013, we profiled Max Little of the UK-based Parkinson’s Voice Initiative, who was in the fairly early stages of voice testing and analysis to aid early diagnosis of this disease. By 2015, he had over 17,000 voice samples, was partnering with the Michael J Fox Foundation, and was seeking to develop a non-invasive, quick, accurate test based on acoustic markers. Dr Little is an Oxford University PhD, currently a Wellcome Trust/MIT fellow at the MIT Media Lab. The Voice Initiative has additional support from PatientsLikeMe, Twilio and Aculabcloud.  But also developed at MIT, by Thomas Quatieri’s team at MIT’s Lincoln Laboratory, is a broader platform for voice diagnosis. This has been applied to mental health conditions such as depression, respiratory and cardiovascular conditions, and in pilots for TBI, cognitive impairment and…Parkinson’s. This has been licensed to Sonde Health, which hasn’t much on their website but is out of the Boston-based PureTech R&D/venture firm. The acoustic markers they cite are ‘dynamic changes in pitch and harmonics, articulation timing and hoarseness or breathiness that indicate and requires no analysis of words’. MedCityNews, MedTechBoston

Quick Tuesday takes on health tech

Long-term sensors, smart thermometers and the Scanadu Nirvana

The first study of long term use of carbon nanotubes as implanted sensors has been published in Nature Nanotechnology. The nanotubes were implanted for a year in animals to track nitrous oxide (NO), an indicator of inflammation which is important in and of itself, but the level of NO is also not understood long term in cancer. To detect NO, the tubes are wrapped in DNA with a particular sequence and wrapped in an alginate gel to stay in place for a recorded 400 days. The MIT team working on this is also working on nanotubes for real-time detection of glucose levels, towards an accurate insulin pump that would end the diabetic’s perpetual Battle of Stalingrad. MIT News and FierceHealthIT.

The Kinsa smart thermometer for iPhone and Android received a glowing article in Fast Company Design. (more…)

A selective look at health tech startups, toys and keeping it clean

Joan Justice, as Curator-in-Chief of HealthWorks Collective, always provides a quirky look at cool stuff in health tech. Her second round goes a bit afield of health, but what’s interesting: ClearMD (DIY provider videos for patients), Picmonic (medical student education audio-picture mnemonics), Cobalt Research (web-based Cognitive Behavior Therapy (CBT)) and Accessible Home Living (designing/remodeling for older adults/disabled needs). Health Start-Ups!: Another Round  And what motivates serial healthcare entrepreneurs to be..serial? Check out her video interview with John Deutsch, current CEO of New Wave Enterprises, LLC who has been part of several EMR startups.

Ready to DIY? MIT Little Devices Laboratory is now developing MEDIkits (Medical Education Design Invention Kits) in diagnostics and therapeutics: drug delivery, diagnostics, microfluidics, prosthetics, vital signs and surgical devices. And the devices are built from–Lego parts, the internal workings of other toys with electronic parts, LEDs, and more–all to enable creative thinking in device development from a wide number of people outside traditional labs. The Little Devices Lab also has a collection of videos and press on their blog hereCan Toys Decrease the Cost of Health Care Devices? (HealthWorks Collective)

And ready to get clean? In the US, it is estimated that 100,000 people yearly die because of hospital-originating infections, largely due to poor hand hygiene. IntelligentM, a bracelet for hospital staff who are in contact with patients, reminds and checks for cleanliness. The device determines through its built-in accelerometer that hand washing and sanitizer are being used–and correctly. In communicating with RFID sensors at hygiene stations, it also reports compliance. Currently being tested at a hospital in Sarasota, Florida with two other locations shortly to adopt, and with potential uses in food service and with children. MIT Technology Review.  Gizmag.

Healthcare IT–New York’s Next Big Thing

Sponsored by MIT’s Enterprise Forum and held on 8 May 2013, this event reviewed the efforts of entrepreneurs, investors, public entities and accelerators in changing the New York area from a ‘dead zone’  for health tech to a new hub of innovation–in what this Editor considers a record (two-three year) time. (Was it only July 2011 that 90% of local investment went to internet shopping and mobile?)

Moderator: Steven Krein, founder and CEO of health tech accelerator StartUpHealth (most recently in our news for their joint program with GE Ventures’ Healthymagination)

Panel: Jahan Ali, PhD, Senior Vice President, Partnership Fund for New York City; Serge Loncar, Founding President and CEO, CareSpeak Communications; Philippe Chambon, Managing Director, New Leaf Venture Partners

Steve Krein set the tone with predicting that NYC will be the hub of health IT. It is heading towards its tipping point; that healthcare is not only overdue for its time in investment but also where key factors are converging to make this possible–money, universities and companies within reach. Key factors are investors such as the Partnership Fund for NYC, which helped to fund the NY Digital Health Accelerator with the New York eHealth Collaborative (NYeC), which on the day of the meeting graduated eight startups (see ‘Related’ and video) with $300,000 of funding plus three provider pilots; and VC funds such as New Leaf Venture Partners. Updated 14 May (more…)