Author: admin

On paper, Ukraine should have one of the best healthcare systems in the world. This nation of 44 million people has 3.1 doctors for every 10,000 citizens. That’s better than the U.S. (2.6 doctors per 10,000 citizens) and Canada (2.4 doctors). The war, however, has taken a toll on Ukraine’s entire system. Medical supplies and equipment are scarce. Simple things like getting regular checkups are now fraught with danger in some parts of the country. Regular care and treatment are down across the board.

The situation is particularly evident in heart disease, which affects 35 percent of the world’s adult population. Disease progression leads to serious complications and a lower quality of life, making early detection and ongoing monitoring. But in-person screening is simply impossible in much of Ukraine, due to the war. This means more people who are at risk will see their conditions progress into acute states, leading to significant future hardship for them and their families. Doing something about this now will have a lasting impact.

Sparrow BioAcoustics is a medical software startup in Newfoundland, Canada. The company has ties to the people of Ukraine, both through our staff and our connections with Ukrainian doctors and engineers who have helped the company refine our initial prototypes into a viable clinical-grade product. Helping the people of Ukraine is one of our corporate priorities.

So we’re proud to announce that after an eight-month effort, Sparrow has won full regulatory approval from Ukraine to offer its Stethophone™ smartphone stethoscope app in the country.

“Stethophone allows for recording and secure transmission of cardiac signals from smartphones,” says Nadia Ivanova, chief product officer at Sparrow. “The system is designed to help doctors detect a host of common cardiac issues, such as valvular disease, cardiomyopathy, arrhythmias, and even acute symptoms of heart failure.”

Using Stethophone is easy. There’s nothing new to plug in, charge up, or find the right cable for. You download the Stethophone app like other smartphone apps. Then, all you need to do is press the smartphone to the patient’s chest (or your own chest) and follow the directions on the screen.

Stethophone uses advanced audio processing to listen to cardiac sounds and augment the quality of those signals to make the tiny, nuanced elements that doctors listen for more audible. It also helps doctors visualize and review anomalies in the scan and decide if further action needs to be taken. All without the need for a visit to the clinic or doctor’s office.

Stethophone has been cleared by the U.S. Food and Drug Administration as a Class II medical device, and it can currently be used by doctors, nurses, EMTs, and other medical professionals. We’re now working with the agency in the hopes of securing an additional clearance that will make it possible for patients and their caregivers at home to use Stethophone. Ukraine’s regulatory process is known for its emphasis on data and clinical rigor, making the approval there an important leadup to our efforts to secure approval for use by patients in the U.S.

As Dr. Yaroslav Shpak, chief medical officer at Sparrow, commented during one of his recent talks, “Often, the most obvious, and often first, sign of heart disease is often death.” But a simple examination with a stethoscope – called an auscultation – provides a wealth of diagnostic information on the condition and structure of the heart and lungs. Stethophone can capture information about the immediate condition of the heart when a person is experiencing symptoms including shortness of breath, fatigue, palpitations, pain and anxiety.

Stethophone also ensures that these people don’t experience the “used car syndrome.” You know – you have an old car that’s making a funny noise. But whenever you bring the car to the mechanic’s shop, it stops making the noise. Similarly, the symptoms of heart disease don’t always manifest when you’re at the doctor’s office. With Stethophone, you can capture those symptoms and share them securely with your care team.

Stethophone has already made an impact in Ukraine. On the first day, one of the first five patients using the device were found to have a prolonged vascular murmur at the carotid artery. Based on the assessment of the Stethophone data, a cardiologist was able to send the patient for an ultrasound that validated the findings. That test confirmed significant narrowing of the left carotid artery that was previously undiagnosed. Carotid stenosis is a dangerous condition that can cause stroke and death. Both are preventable if diagnosed early.

We want to make medical monitoring of the sounds of the heart and lung easy and ubiquitous. Cardiovascular disease kills 32 percent of people on earth. Early detection is critical, yet and estimated 40 percent of the population with cardiovascular disease remains undiagnosed in most countries. We’re gratified that Ukraine is the first country where patients can monitor their own heart and lung health with a smartphone app that functions as a clinical-grade stethoscope. Now, we’re working to bring this advance to more people around the world.

We think Stethophone will fit well into the care path in numerous countries by giving people a way to conduct preliminary assessments at home. Our unique ability to process a large amount of heart and lung auscultation data will also help improve the treatment of patients with these chronic conditions. Additional data will help doctors and population health specialists determine the best way to improve outcomes for patients both individually and at a population level. We think it’s a new way to attack the world’s No. 1 killer.

Mark Opauszky is CEO of Sparrow BioAcoustics of St. John’s, Newfoundland, Canada.

This piece was published in Medical Device News Magazine. See the online version here.

Healthcare has historically been an inconvenient and expensive service to access. Even basic or primary care has numerous barriers; not the least of which is booking appointments, taking time off work, waiting in waiting rooms, being sent for test-after-test etc.  The effects are magnified if you happen to feel ill or are symptomatic.  At the same time, millions of people in the US live in medically underserved areas in states like California, Texas and Illinois[i]; making this process almost insurmountable.

The fact remains that when we feel sick we want answers fast. One of the main questions that crosses our minds is – should I go (to the doctor), when do I go and what information do I bring with me so that I get the right care. People have to make these decisions all the time, for themselves and their loved ones. Depending on the situation, medical history and social determinants many people wind up in a cycle of multiple visits and unnecessary tests, while others don’t get help until their conditions advance to more acute levels. Both scenarios cost the medical system billions and severely affect the quality of life and outcomes for patients.  Arming the population with a way to make this better seems like something we should have had by now.  At the very least people should be able to do more to assess if they are sick or not – because today 65% of them ask Google. Our minds jump to technology that could easily scan and record vital signs at home, detect any red flags and then share that information with medical professionals.

Medical care has increased in leaps and bounds and with it the need for more screening, diagnosis and triage. Yet patients seeing doctors are answering the same questions and describing their symptoms the same way we did a hundred years ago. Patients can and should  be a bigger contributor to the process. Imagine seeing a specialist and bringing six months of your own cardiac and pulmonary data to go along with your concerns of light headedness and headaches. Getting more diagnostic information earlier has never been controversial in the medical industry. It was simply assumed that people were incapable of collecting their own medical data without specialized training. The same of course, used be said about making your own investments, booking your own travel, or even pumping your own gas.

Patients gathered health data (PGHD) are defined as “data created, recorded, and gathered by and from patients” often using technology such as smartphones and wearable devices.  It’s all part of what you would expect from any basic physical examination needed to even begin the process of determining if you are having a panic attack or is ischemic event, the flu or necrotizing fasciitis.  Back in 2011, Dr Gregory Abowd from the school of interactive computing at Georgia Tech gave a keynote to the American Medical Informatics Association on the near-future importance of PGHD. He predicted that the vast majority of information that a doctor might use to determine how a patient is doing will be things that are collected outside of that doctor’s office and that much of the data relevant to the medical records of an individual is going to be accumulated in their homes and elsewhere.

Since Dr. Abowd’s seminal prediction, wearable devices and specialize connected devices that record certain vitals or help you manage conditions have flooded consumer markets.  At the same time, there are now more ways that people gain electronic access to their medical records, test results, X-rays etc. Up until recently, however, the adoption of PGHD to support clinical decisions by doctors has been relatively slow. The pandemic did a lot to move healthcare institutions, medical practitioners, and insurers forward on this front. By way of example, over 500 health institutions now support Apple Health Records[ii], which enable patients to view important data such as immunizations, X-rays, and lab results in the Health app. In 2019, Tim Cook famously stated “I do think there will be a day when people looking back will say Apple’s greatest contribution to the world was healthcare.”  The promise here is that patients will ultimately have greater custody over their medical information, carrying it with them where they go. The ability for a patient to transmit this information instead of waiting for in-person visits or forwarding the information to specialists, means better access with fewer steps in a lot of cases. It also puts the patient in more control, something we are now used to in our consumer lives.

The question remains, however, how will patients record and share things like a lung sound or heartbeat in a way that is medically useful, accessible, and convenient? Will the general public  start purchasing specialized new consumer medical appliances for the home?  Some might, however, on the whole it may not be necessary.  The use of smartphones has hit an inflection point that is relevant to this question. Analysts today put smartphone adoption in the US at 88%, with almost 75% adoption in the 65 and older demographic[iii].Today, there are no comparable physical technologies that we interact with more. One study stated the average person touches their phone 1500 times week[iv].  The evolution of these devices have been guided by our desire to use them as proxies for our own senses: ultra-high-resolution video, stereo audio recording and playback capable of selective noise cancelling, physical feedback through haptics, geolocation, gyroscopes and more.  This is extremely important because it allows our smartphones to be applied as an extension of a doctor’s ability to touch, listen, see, measure and record anytime.

If all it took was a software download to transform a smartphone into a medical device, the convenience factor and accessibility for the consumer would skyrocket.  Consumerization and convenience have driven huge changes in how we manage finances, make important decisions and shop; healthcare is next. A recent study surfaced that now 60% of consumers expect a healthcare digital experience to mirror that of retail[v]. 

People using their personal devices as medical instruments to assess their health does not seem far-fetched; in fact it will likely become as normal as using a banking app instead of standing in line. Patient gathered data applied correctly would invariably fuel intelligent systems that could help both patient and doctor do a better job of making decisions outside of the structure of the traditional clinical environment.  As we have recently been reminded, a population’s overall health is heavily tied to the health of the economy.  Both employers and insurers benefit from people’s ability to be more proactively involved in their own health. At the same time, democratizing elements of the screening and assessing process and moving those partially into the patient’s control seems daunting.  Does the medical system get overwhelmed with consumers demanding attention because their phones told them they were sick?  Do employees gravitate to medical software on their devices in the hopes it will tell them they need more time off work?  At the very least companies would need to consider overhauling policies related to health, especially when every employee can now bring-their-own medical device to the office.

It’s easy to argue that the current balance does not need to shifted. But it’s important to remember that a large number of people, who have chronic illnesses or conditions, already manage their own care to a large degree every day.  For them, getting the best outcomes almost always has to do with being proactive, having the right information, tracking the progression of their conditions themselves and using this to navigate the medical system wisely.  It’s also a big part of the psychology of living with conditions and mentality around recovery.  People have always been capable of sound decisions about their own health when they know what they need to know.  Transforming the devices in our pockets into medical grade diagnostic tools refined for consumer use seems like something people are ready for.

The quadruple aim of healthcare as developed by the Institute of Healthcare Improvement (IHI) “advocates for: improving patient experience, reducing cost, advancing population health, and improving the provider experience.” Connecting the right expertise at the right time and place—utilizing technology that is highly familiar to the population—holds promise as a big step towards achieving this aim.

---

[i] US Health Resources & Services Administration 2020 report

[ii] https://techcrunch.com/2020/10/07/apple-brings-health-records-to-iphone-in-the-uk-and-canada/

[iii] Mercator Advisory Group : truth and data https://www.paymentsjournal.com/smartphone-adoption-in-the-u-s-by-age-group/

[iv] https://www.dailymail.co.uk/sciencetech/article-2783677/How-YOU-look-phone-The-average-user-picks-device-1-500-times-day.html?ito=social-twitter_mailonline#ixzz3FTEdxnvq

[v] Customer Experience Trends in Healthcare, 2018; NTT DATA Services

The sounds of your heart beating and your lungs filling and exhaling are something everyone is familiar with.  Your heartbeat is the sound of your heart valves opening and closing.  In between those familiar sounds is sound energy given off by the of blood rushing through your heart.  In most cases, these sounds can represent normal healthy operation; where valves close properly and at the right time, and blood flows in the right direction.  Abnormal functioning of the heart will produce abnormal sounds, for instance valves closing  insufficiently and  with irregular rhythm, blood moving in the wrong direction or wrong velocity.  There are dozens of conditions that can be detected by analyzing the kinetic mechanical energy radiating from the heart as is functions.  These sound waves carry with them a vast amount  diagnostic information about the structure and condition of the heart, but separating these sounds from the background is tricky.

The most medically interesting sounds are also some of the hardest to isolate and hear. Like trying to separate out a single wave in an ocean. Important symptoms, such as gallop tones S3 and S4, mitral stenosis murmur, Still’s murmur and Austin Flint murmur exist and extremely low-frequency which are thousands of times harder for humans to hear than everyday sounds we are used to. Some diseases like infectious endocarditis can be detected at very early stages through sound, but it requires that we detect by the presence of a (very low power) quiet cardiac noise.

The use of machine learning is going to change things dramatically. It’s possible to train AI to detect and assess these sounds – especially those that exist on the edge of human hearing ability. This will significantly augment the diagnostic capacity, early detection, and screening available to people. Of course the real work today is in making this audio data machine readable. Bioacoustics is what they call unstructured data. It needs to be annotated and organized and its key features identified well before AI can work. If you want the AI to work well (and we do) you need a huge amount of this data. Daunting as it may seem, it’s an enormously worthy pursuit and will lay the foundation for years of innovation in the detection of dozens of diseases of the heart. lungs and possibly other organs.

Left – A wave off the coast of New Zealand. Right – a spectrographic visualization of a cardiac murmur as a result of aortic regurgitation

Your ankle has been hurting for a while, and today it hurts a lot. Not knowing why you are in pain is making you anxious. If you could x-ray it in your living room, and send it to someone to look at, would you? What if instead, you had chest pains or heart palpitations? If you could send a recording of your heart sounds to a doctor, would you?

Most people who feel unwell want answers right away. They want to be examined when they are symptomatic, but it is rare to get an appointment with a medical professional instantly. If there are follow up tests or consultations with specialists, it feels like it will take weeks or even months before  anyone is ready to start solving your problem. For most of us, it seems that health care doesn’t move forward until you are examined, and your diagnostic health information is actually recorded.  These tests initiate the process of evidence collection around which clinicians can rally and move towards a diagnosis to treat your ailment.  Many times, however, you feel like you are going in circles until the right clinician listens to your chest or looks at your x-ray or sees your symptoms firsthand.

Now consider if the nearest medical clinic that can provide you with diagnostic and ambulatory testing services is three hours away and understaffed. What if you must take time off work or have other responsibilities? Effectively coordinating the doctor, clinician, patient and testing equipment in the right place, at the right time now gets a lot harder.   This burden ultimately rests with the patient or a concerned family member, yet there are few if any options other than waiting for appointments just to get the ball rolling. Troublingly, 53 million people in North America live in areas that are considered medically underserved; globally the number is in the billions.  Not surprisingly, these populations are at higher risk of complications due to undiagnosed conditions like CVD, heart failure and COPD. According to the Institute of Health Metrics and Evaluation in Washington DC, these conditions are the root cause of most deaths in both rich and poor nations.

Over the past 18 months, medical visits in the USA that were initiated using a telehealth or telemedicine platform to connect patients with healthcare professionals have increased 38 times more than before the pandemic.[1] And approximately 40% of surveyed consumers stated that they will continue to use telehealth to access healthcare services. In Canada, a 2020 report on consumer attitudes for telemedicine indicated that nearly 70% of surveyed consumers believed that virtual healthcare would allow people to be more proactive about their health and the health of their family members.[2] These and other reports suggest that remote and virtual access to healthcare services will soon become a normal and possibly preferred way to access care. This trend begs the question as to whether virtual healthcare consultations can be made more meaningful (and even rewarding for the patient) by also incorporating some of the diagnostic testing you would normally need to travel to a clinic for.    

Rina Carlini is President and CEO of Optimal Innovation Group. Her company consults with medical technology innovators who are developing digital and mobile health solutions and delivering better access to healthcare services. She sees things changing in a big way:

Rina, do you think there is room for a more democratized approach to healthcare – one where the patient can contribute to the process by providing diagnostic data they gatherd at home?

“Yes, I think the process has always been inefficient, requiring people to wait a long time for care – hours, days, even several weeks for specialist care. For those who live in rural or remote communities, the inconvenience and inefficiencies become a more significant barrier. Giving patients the ability to initiate more of their own care from home (rather than the waiting room) is long overdue.  Thankfully, we now have the technology solutions that offer virtual, mobile access to healthcare services for people wherever they are.  To realize the full potential here, we also need proactive and equitable healthcare policies, funding and educational support. The payoff is a true democratic access to healthcare for everyone.    

Do you have first-hand experience you can share ?

“Yes, as do many people. My mother had complained of occasional heart palpitations and feeling lightheaded since her mid-40s. Now that she’s elderly and living alone, the frequency of these incidences has increased. She’s undergone testing at clinics and hospital centers using the typical diagnostic tests – ECG, BP, etc. – but none had ever revealed a conclusive sign of an underlying condition. These palpitations were short-lived when they happened in her home, and by the time she got medical attention in a clinic (typically 1-3 days later), they had often passed. The physicians thought it was “in her mind” and suggested that she see a psychiatrist; for her, this was both disheartening and patronizing. If only she had the tools and ability to record her sensation of heart palpitations right when they happened. Recently she was hospitalized, and the internist physician finally determined she was living with mild arrhythmia and was prone to atrial fibrillations. The diagnosis set her on the right course of care with medication to regulate her heart rhythms. She would have been spared years of stress and anxiety if we could have gotten here sooner.  

Today we have available a wide range of clinically-validated digital health tools and mobile apps that can empower patients to perform diagnostic health tests. My mother and many other people across the world should be able to access these apps. This is a way to empower people through recorded evidence of their ailment. The test data could be shared by the patient to their healthcare provider and circle of care.  That is digital health equity, and it makes democratized access to healthcare possible.”    

What if the patient, or their caregiver, had the option to initiate simple tests like recording heart and lung sounds, or an ECG, instead of having to wait for a primary care physician or nurse-practitioner to do it in a clinic? Could simple home-based diagnostic tests qualify as an auditable record of the patient’s medical evidence that will lead to a faster diagnosis? What if all this could be done without the need or cost of special equipment, using just a normal smart phone or tablet?

At Sparrow, we think this type of democratized access to clinical-quality virtual healthcare is both inevitable and necessary. There are 3.3 billion smartphones in the world.  What if there was a specialized app that transformed these into “smart stethoscopes” –  augmenting virtual care examinations for patients anywhere, anytime.  Technology solutions like this can be a true liberator for many people, including physicians and clinicians who want to deliver the best evidence-based care for their patients without the traditional barriers. It’s not about replacing gold-standard tests or diagnostic skills with new technology; it’s about offering millions of people a faster and easier way to get the ball rolling when it really matters.

By Mark Attila Opausky

---

[1] McKinsey Report: “Telehealth: A quarter-trillion-dollar post-COVID-19 reality?”;  O. Bestsennyy, G. Gilbert, A. Harris, and J. Rost, July 9, 2021.

[2] Environics, 2020; “Canadian Attitudes on Healthcare and Telemedicine.”

The sound of a functioning heart, vessels, and lungs contains a surprising amount of information about their structure and function. These sounds are often sufficient to make an accurate diagnosis and conduct informative clinical monitoring. But there has always been a problem. Not surprisingly, mastering the ability to analyze these sounds has traditionally been a complex, long-term process. Add to that, the problem of so called low-frequency sounds. Low-frequency sounds are thousands of time harder for humans to hear so our consciousness leans towards ignoring them. Some think this is evolutionary. Most things in nature that could harm humans (angry bears, volcanoes, other humans etc.) tended to make sounds at much higher frequencies so we are predisposed to focusing on those. Yet a number of important auscultative symptoms, such as gallop tones S3 and S4, mitral stenosis murmur, Still’s murmur and Austin Flint murmur are exclusively low-frequency and extremely hard to perceive. With the help of modern analysis, sound processing and artificial intelligence technologies, this traditional limitation no longer exists and so neither do the barriers to using biological sounds to accurately, quickly and inexpensively diagnose conditions.

Modern echocardiography produces high quality medical insights but is not a panacea. Like all measurements, it has limitations based on the fundamental nature of the information it is based on; namely the shape and related mechanical movement of structures. To be clear it is a very rich information source from which to mine insights. But from a technical perspective, biological sound data is arguably just as rich if not more potentially informative. All moving (dynamic) systems emit energy as sound. What makes sound so rich is that it has two fundamental components: (1) Frequency: e.g. low-frequency oscillations, as a component of hemodynamic murmurs, are caused by movement of large blood volumes, and the high-frequency oscillations by high-speed blood flows etc. and (2) Amplitude. Amplitude considered alongside frequency provides additional information about the power of the sound. Power is interesting because we can use it to assess the severity of certain conditions (like mitral regurgitation). Diagnosis based on ultrasound or other tests can actually miss this because the underlying signals they process lack this information.

We think chest sound data is extremely valuable and, as it happens, potentially easier to collect and analyze than echocardiography for instance. And early accurate diagnosis matters. Diseases such as infectious endocarditis can be detected by the presence of quiet cardiac noise at an early stage but in practice it is often detected only much later with echocardiography, when the disease has caused catastrophic damage and the chances of survival are diminished.

The focus for providers and payers is shifting in pursuit of better value for the money spent. As such, the concept of value-based healthcare (VBHC), tabled more than a decade ago, is now an official part of the conversation; albeit far from being a reality.

On the surface, it’s a devastatingly simple model centered on patient value. Where value increases by improving outcomes or, at the very least maintaining outcomes at a reduced cost.

Patient Value = Outcomes/Cost to achieve Outcomes

The central ethos here is that health and not the volume of treatment is the defining outcome for medicine. For the math to work, the value of health is defined in terms of survival years gained or some other relative net improvement. So to allow this to be measured, and therefore paid for, we need better measurements or some proxy for patient and health outcomes; this is far from simple.

It seems many of the obstacles standing in the way of doing VBHC at scale have to do with alignment on which outcomes to measure and how to measure them. This alignment needs to be present between the patient, provider, payer, and the industry. First steps have been taken in areas such as better individual patient-reported outcome measures (PROMs or ePROs). Increased focus on the patient and the uniqueness seems like what we should be going for here. But this can break down when you over personalize the outcomes to each type of condition or individual patient. There also remains the issue that you need to deploy the right care in the right place as well as coordinating care where multiple conditions are present to avoid undesirable health inequalities and unnecessary costs. But the system fails economically if we add complexity while simultaneously trying to improve precision. Given these constraints, we still need leadership to realize a unifying, common set of value criteria and outcomes.

Data helps here a lot. The growing volume of available health data, both structured and unstructured, and the maturation of policies and infrastructure to allow for the pooling of that data will give us a resource to try to arrive at this alignment about outcomes. Simultaneously, we now have better understood and more efficient machine learning capabilities able to determine and decode meaningful information from this data and that helps model future outcomes based on today’s information.

Coded within the sounds made by the functioning heart is a wealth of diagnostic information. However, even to the best trained medical ear, these sounds are quiet and sometimes difficult or even impossible to perceive. When considering symptoms, one might think that the louder the sound the more significant the condition. This might be true with your failing car transmission or aging refrigerator but not always the case with your heart. Many critical sound symptoms are on the verge of perception and are easy to miss.

Clinical use of heart sounds has a very long history. Over time stethoscopes evolved to include the “bell” and “diaphragm” listening surfaces. Each aided differently in improving the audibility of difficult to perceive sounds. Modern digital stethoscopes essentially copy the sound filters of traditional stethoscopes.

One of the early things we did at Sparrow was to use spectral sound analysis to create a filter that greatly facilitates the perception of very quiet but important symptoms. In the process we removed the need for clinicians to have to switch between traditional filters to hunt for sounds. We call our filter a “Cinema filter” because it focuses attention on the most important things, making them clear and contrasted so you can pick out the nuances of the underlying story – kind of like going to a good movie.

Bronchial breath sounds are loud, harsh breathing sounds with a midrange pitch (300 to 600hz). They are normal when occurring over the trachea during exhalation. These sounds, when emanating from another location, can be an indicator of a lung issue.  There are three types of abnormal bronchial breath sounds:

Tubular breath sounds are a high pitched  (600 to 1,200 Hz) bronchial breath sound. Some common conditions that produce these are:

• Atelectasis: Partial or total collapse of a lung
• Consolidation:  Air spaces within the lungs fill with liquid
• Pleural effusion:  A buildup of fluid in the tissue  surrounding the lungs
• Pulmonary fibrosis:  Damage and scarring of the lung tissue
• Mediastinal tumor: A tumour in the area of the chest in between the lungs

Cavernous breath sounds are low pitched (100 to 300 Hz) bronchial breath sounds. Common conditions generating these are:

• Lung damage from bronchiectasis
• A lung abscess
• Cancerous changes

Amphoric respiration is a type of abnormal bronchial breathing that creates a strong reverberating sound with high pitched overtones. it is an indication of a cavity, cyst, bleb, or other air-containing space in the lung communicating with the bronchial system

A middle-aged man, prolapse of the right coronary aortic valve leaflet, severe aortic insufficiency. Rare musical diastolic murmur (1) and aortic ejection sound (2).