Steve Blank The Apple Watch – Health Changeover Time


I do not have an Apple Watch. I have a Fitbit. But the announcement of Apple Watch 4 'intrigued in a way that no other product has since the original iPhone. It was not just another Apple product announcement. It announced the entry of the FDA (Food and Drug Administration) in the United States in the 21stcentury. This is a pioneering sign of the future of health care and how the FDA approaches innovation.

Sooner than we think, virtually all home and outpatient diagnostics are done by mainstream devices such as the Apple Watch, cell phones, fitness trackers, etc., which have been approved by the FDA as medical devices or whose applications have been approved by the FDA. Consumer devices will become medical grade devices, with painful and well-known mistakes throughout the process.

Let's see how it goes for Apple.


Smart watches are the pinnacle of the most sophisticated electronics on the planet. And the Apple Watch is the most complex of all. A 64-bit computer, 16 GB of memory, Wi-Fi, NFC, cellular, Bluetooth, GPS, accelerometer, altimeter, gyroscope, heart rate sensor and ECG sensor are presented in a package 40 mm wide and 10 mm deep all on an OLED display 448 by 368.
When I was a kid, it was science fiction. Heck, until its first delivery in 2015, c & # 39; was science fiction.

As impressive as its technology, Apple's smartwatch is a product looking for a solution. At first, positioned as a fashion statement, it seemed that the watch was actually an excuse to sell expensive bracelets. Later versions were focused on fitness and sports (the watch looked like a Fitbit), plus the possibility of being annoyed by interruptions of your work. But now, the fourth version of the watch has just found the beginning of applications "you have to have" – ​​killers – health care – specifically medical diagnosis and screening.

Health care wrist
Big tech companies like Google, Amazon and Apple recognize that the multi-trillion The dollar health care market is ripe for disruption and has poured billions of dollars into space. Google has invested in a broad portfolio of health care, Amazon has invested in the distribution of pharmaceuticals and Apple …? Apple's goal is to make the Apple Watch a future in the field of health screening and diagnosis.

Apple's latest show – with three new diagnostic and screening applications in the healthcare sector – gives us insight into the future of diagnostics and screening in the healthcare sector.

The first new health care app on the watch is Fall detection. Perhaps you have seen old advertisements in which a person falls and can not get up and has a device that calls for help. Well that's it – built in the watch. The accelerometer and gyroscope built into the watch analyze the trajectory of your wrist and the acceleration of your impact to determine if you have suffered a sudden fall. You can ignore the alert or call it by dialing 911. If you do not move after a minute, he can call the emergency services and send a message with your location.

If you're part of the current Apple population, you may be wondering "Who cares?", But if you have an elderly parent, you might start asking yourself "How can I get them to wear this watch?" ?

The second new health care app also uses the existing optical sensor in the watch and runs in the background, collects cardiac data and has an algorithm detect irregular heart rhythms. If it detects that something is wrong, an alert will appear. A serious and common type of irregular heartbeat is atrial fibrillation (AFib). AFib occurs when the atria – the two upper chambers of the heart get out of sync – and instead of beating at 60 normal beats per minute, they can shudder at 300 beats per minute.

This fast heart rate allows blood to accumulate in the heart, which can cause clots to form and transport to the brain, causing a stroke. In the United States, between 2.7 and 6.1 million people have AFIB (2% of those under 65 have it, while 9% of those over 65 have it.) It places about 750,000 people a year at the hospital and contributes to about 130,000 deaths each year. But if you catch atrial fibrillation early, there is an effective treatment: anticoagulants.

If your watch is alerting you to an irregular heartbeat, you can launch the third new health app – the Electrocardiogram.

the Electrocardiogram (ECG or EKG) is a visual presentation indicating whether your heart is functioning properly. It records the electrical activity of the heart and tells doctors the rhythm of the heartbeat, the size and position of the heart cavities and any damage to the heart muscle. Today, electrocardiograms are done in the doctor's office by lying down and sticking 10 electrodes to the arms, legs and chest. The electrical signals of the heart are then measured under twelve angles (called "derivations").

With the Apple Watch, you can take an ECG by simply putting your finger on the crown for 30 seconds. For this to work, Apple has added two electrodes (the equivalent of a single wire), one on the back of the watch and another on the crown. The ECG can tell you that you may have atrial fibrillation and suggest that you consult a doctor. Since the ECG is saved in a PDF file (surprisingly, it is not in the FHIR format of the HL7), you can send it to your doctor, who can decide that no visit is necessary. .

These two applications, the electrocardiogram and irregular heartbeats, are serious screening tools. They are expected to be shipped to the United States by the end of 2018. By the end of next year, they can be on the wrists of tens of millions of people.

The question is whether they will create millions of unnecessary visits to the doctor of users unnecessarily worried or will they save thousands of lives? My bet is both – until traditional health care catches up with the fact that over the next decade, screening devices will be in the hands (or wrists) of everyone.

Apple and the FDA – Clinical tests
In the United States, drugs and diagnoses are regulated by the Food and Drug Administration – the FDA. The peculiarity of the Apple Watch is that the electrocardiogram and irregular heartbeat applications have forced Apple to obtain FDA clearance. It's a very big deal.

The FDA requires evidence that medical devices do what they claim. To gather this evidence, companies recruit volunteers into a study – called clinical test – to see if the device does what the company thinks it's going to do.

Stanford University has been conducting a clinical trial on Irregular Heart Rhythms for Apple since 2017, whose completion date is in 2019. The goal is to determine whether irregular pulse notification is actually a atrial fibrillation and how many people notified have contacted a doctor within 90 days. . (The Stanford study seems to use previous versions of the Apple Watch only with the optical sensor and not with the new ECG sensors.It used the heart monitor of someone else to detect atrial fibrillation. )

Update of November 1, 2018 – Stanford Apple Watch's study design published here

To obtain FDA clearance, Apple reportedly submitted two studies to the FDA (so far, none of the data has been published or peer reviewed). In an essay with 588 people, half of whom were known to have IBF and the other half healthy, the application could not read 10% of the records. But for the remaining 90%, he was able to identify more than 98% of patients with IBF and over 99% of patients with healthy heart rate.

The second set of data sent to the FDA by Apple was part of the Stanford Apple Heart Study. The application first identified 226 people with irregular heartbeat. The goal was to see how far the Apple Watch could detect an event that looked like atrial fibrillation compared to a portable heart monitor. Traditional monitors have identified 41% of people with an atrial fibrillation event. In 79% of these cases, the Apple application also found a problem.

It was good enough for the FDA.

FDA – Difficult to deal with disruptions
And "good enough" is a great idea for the FDA. In the past, the FDA was considered inflexible and dogmatic by new businesses, but insufficiently protective by surveillance organizations.

For the FDA, this announcement was as important to them as it was to Apple.

The FDA must decide between a multitude of constituents and conflicting priorities. Its goal is to ensure that drugs, devices, diagnostics and software do not harm thousands or even millions of people, so the FDA wants a process to ensure everything is done right. It is a permanent compromise between patient safety, sufficiently good data and decision making, and complete clinical evidence. In addition, for a company, an FDA authorization can be worth hundreds of millions or even billions of dollars. And a disapproval or delayed authorization can put a start-up bankrupt. Finally, the pace of innovations in medical devices, diagnostics and digital health has been faster than the FDA's ability to adapt its regulatory processes. Frustrated by the 20 FDAth century process for 21st In the last century, companies have hired lobbyists to impose an amendment to the FDA's regulatory laws.

The announcement made by Apple is therefore a visible sign in Washington that the FDA encourages innovation. Over the past two years, the FDA has been trying to prove that it can track rapid advances in digital health, devices and diagnoses, while trying to prevent another Theranos.

Since the appointment of the new FDA manager, very substantial progress has been made in speeding up mobile and digital device approvals with new guidelines and policies. For example, over the past year, the FDA has announced its Pre-Cert pilot program, which allows companies that manufacture software as medical devices to manufacture products without each new device being subjected to the process. FDA approval. The pilot program allowed nine companies, including Apple, to begin developing products (such as Watch) using this regulatory shortcut. (The FDA has also proposed new rules for clinical support software stating that if physicians can review and understand the basis of the software decision, the tool does not need to be regulated by the FDA.)

This fast clearance process as a standard – rather than the exception – is a radical change for the FDA. We are on the verge of de facto adopting a Lean decision-making process and quick approvals for the issues that are least harmful to health. This is how China will approach approvals and allow US companies to remain competitive in a field (medical devices) where China has said it wants to dominate.

Has Apple cut in front of the line?
Some complained that the FDA had been too comfortable with Apple for this announcement.

Apple got its two FDA Class II approvals through what's known as a de novo procedure, which means that Apple claimed that these features were the first of their kind. (It may be the first built in shows, but it's not the first ECG application for Apple Watch approved by the FDA – AliveCorobtained the over-the-counter authorization in 2014 and Cardiac Designs in 2013.) Critics have stated that the Novo process should only be used in the absence of predicate (substantial equivalence with respect to a device already erased.) But Apple cited at least one so if they followed the conventional 510k approval process, it should have taken at least 100 days. Yet Apple has obtained two software permissions in less than 30 days, strangely emerging the day before the announcement of their product.

To be fair to Apple, they have probably held pre-submission meetings with the FDA for a period of time or even years. Presumably they have consulted the FDA Pre-Cert pilot program on the design of the clinical trial, the trial judgment criteria, the criteria for conduct, inclusion and exclusion, and so on. approach and work with the FDA to obtain erased devices or software. And that's exactly how the FDA should consider its future.

Since Apple sells about 15 million Apple watches a year, the company is about to embark on a large-scale public trial of these features – with an initial patient population showing the least risk of contracting these affections. It will be interesting to see what happens. Will young people between the ages of 20 and 30, who are extremely worried, flood doctors with false positives? Or are we going to read about lives saved?

Why Most Consumer Hardware Manufacturers Are Not Manufacturers of Medical Devices and Diagnostics
Historically, consumer electronics companies and medical device and diagnostic companies were very different companies. In the United States, medical devices and diagnostic products require both regulatory authorization from the FDA and refund approval by different private and public insurers to be paid for the products.

These regulatory and reimbursement agencies have very different timelines and priorities than for-profit companies. Therefore, to obtain clearance from the FDA, an essential part of a medical device business is devoted to building staff and hiring consultants, such as Clinical research organizations, able to master and navigate FDA regulations and clinical trials.

And it's not because a company asks the FDA to clean its device / diagnostic / software that it will be paid for it. In the United States, medical devices are reimbursed by private insurance companies (Blue Cross / Blue Shield, etc.) and / or by the US government through the Centers for Medicare & Medicaid Services (CMS). ). Obtaining these permissions to get the product covered, coded and paid for is as difficult as obtaining FDA clearance, which often takes 2 to 3 years. Controlling the repayment path requires that one company ask another group of specialists to conduct costly studies on clinical costs.

The Watch announcement telegraphed something interesting about Apple – it's one of the few consumer products companies to have defeated the FDA approval process (the other being Philips). And in the future, unless these new applications are catastrophic, it will give them the ability to add to the watch FDA-approved diagnostic and diagnostic tools (and, by extension, a multitude of of AI-based imaging diagnostics (detection of melanoma, etc.) the iPhone.) This in itself is a key differentiator for the watch as a health care device.

Another interesting observation: unlike other medical device manufacturers, Apple's current business model is do not depend on having insurers to pay the watch. Today, consumers pay directly for the watch. However, if the Apple Watch becomes an eligible device for refundThere is huge revenue potential for Apple. When and if this happens, your insurance will pay all or part of an Apple Watch as a diagnostic tool.

(After conducting cost studies, insurers believe that preventative measures, such as staying in shape, reduce their overall expenses in various conditions.Today, some life insurance companies principal the use of an activity tracker like Apple Watch.)

The future of smart watches in health care
Very few companies (probably less than five) have the ability to integrate sensors, silicon and software with FDA regulatory approval in a small box like Apple Watch.

So what can / will Apple offer on future versions of the watch? After reviewing Apple's patents, here is my view of the list of medical diagnostic and screening applications that Apple could add.

Sleep monitoring and detection of sleep apnea
Compared to the Fitbit, the lack of a sleep tracking application on the Apple Watch is a mystery (although third-party sleep apps are available.) Its absence is surprising because the Watch can theoretically do a lot more than sleep monitoring – it can potentially detect sleep apnea. Sleep apnea occurs when you sleep and your upper airways are clogged, which reduces or completely stops the air in your lungs. This can lead to a host of complications, including type 2 diabetes, high blood pressure, liver problems, snoring, daytime fatigue. Today, the diagnosis of sleep apnea often requires an overnight stay in a sleep study clinic.. Screening for sleep apnea does not appear to require new sensors and would be an excellent application for the watch. Maybe the application is missing because you have to remove the watch and recharge it every night?

Pulse oximetry
Pulse oximetry is a test used to measure the level of oxygen (oxygen saturation) in the blood. The current Apple Watch can already determine the amount of oxygen in your blood depending on the amount of infrared light absorbed. But for some reason, Apple has not released this feature – the FDA regulations? Inconsistent readings? Another vital application of Watch Health that may or may not require new sensors.

Respiration rate
The respiration rate (the number of breaths a person takes per minute), as well as the blood pressure, heart rate and temperature are the vital signs of the person. Apple has patented this watch feature but has not released it for any reason – FDA regulation? Inconsistent readings? Another vital application of Watch Health that does not seem to require new sensors.

Blood pressure
About 1/3rd Americans have high blood pressure. Hypertension increases the risk of heart disease and stroke. It often has no warning signs or symptoms. Many people do not know that they have them and only half of them have them under control. Traditionally, measuring blood pressure requires a cuff on the arm and produces a single measurement at a given time. We have never had the ability to constantly monitor the blood pressure of a person in a state of stress or sleep. Apple has filed two patents in 2017 to measure blood pressure by holding the watch against your chest. It's hard to do, but it would be another great health app for the watch that will or will not require new sensors.

Sunburn / UV detector
Apple has patented a new type of sensor – a sunscreen sensor that lets you know which exposed areas of the skin may pose a high risk of UV exposure. I'm not a big fan of this, but the use of more and more powerful sunscreens has quadrupled, while the incidence of skin cancer has also quadrupled, so there could be a market.

Diagnosis and monitoring of Parkinson's disease
Parkinson's disease is a brain disorder that causes tremors, stiffness and difficulty walking, balance and coordination. It affects 1% of people over 60 years old. There is currently no diagnostic test for the disease (blood test, brain scan or EEG). Instead, doctors are looking for four signs: tremor, stiffness, Bradykinesia / Akinesia, and postural instability. Today, patients must have tests with a doctor to assess the severity of their symptoms and keep a diary of their symptoms.

Apple has added a new "motion-related API" to its ResearchKit framework, which supports motion and tremor detection. It allows an Apple Watch to constantly monitor the symptoms of Parkinson's disease; Dyskinesia, a side effect of treatments for Parkinson's disease causing nervous and flickering movements in patients. The researchers created a prototype of Parkinson's detection application. It seems that screening for Parkinson's disease would not need new sensors – but conclusive clinical trials and FDA clearance – and would be an excellent application for the watch.

Glucose monitoring
More than 100 million American adults live with diabetes or prediabetes. If you have diabetes, it is essential to monitor your blood sugar to control the disease. However, you have to stick your finger to take a blood test several times a day. The holy grail of glucose monitoring is a sensor that can detect glucose levels through the skin. This sensor was the cemetery of tons of startups that crashed and burned to achieve it. Apple has a patent application that looks suspiciously like a non-invasive glucose monitoring sensor for Apple Watch. It's a very difficult technical problem to solve, and even if the sensor worked, the clinical permissions would be long, but this app would change the deal for diabetic patients – and Apple – they could. happen.

Challenges of sensors and data
With many of these sensors, it's easy to receive a signal. Correlating this particular signal to an underlying condition and avoiding being confused with other factors is what makes it difficult to realize the claims of a medical device.

As the acquisition of medical-grade data becomes possible, continuous or real-time transmission will store and report basic data on tens of millions of "healthy people" who will be essential for learning algorithms and, possibly, for the prediction of the disease. This will eventually allow more accurate diagnoses on less data, and will make the data itself – especially the transition from healthy to sick – incredibly valuable.

However, this eliminates the electrons from the batteries and plays on advanced electrical design and the laws of physics, but Apple's prowess in this field is about to make this possible.

What does not work?
Apple has sought to ensure that medical researchers create new applications for health by developing ResearchKit, an open source framework for researchers. Good idea. However, given the enormous potential of diagnostic intelligence, ResearchKit and the recruitment of senior researchers feels seriously underfunded. (It took three years to go from ResearchKit 1.0 to 2.0). Currently, there are only 11 ResearchKit applications on the ITunes store. This effort – Apple software development and development of third-party applications – seems inadequate and underfunded. Given the potential size of the opportunity, the rhetoric does not match the results and the results so far are at least 10 times worse.

Apple needs to be more proactive and directly fund some of these projects by providing grants to specific lead researchers. build a sc programale. (Similar to NIH's SBIR program.) There should be a sustained commitment to at least several new FDA-approved diagnostic / diagnostic applications each year for Watch and iPhone. d & # 39; Apple.

L & # 39; s future
Although the current demographics of the Apple watch for youth, the populations of the United States, China, Europe and Japan continue to age, which can overload health systems. Real-time streaming of medical data to clinicians will change the current paradigm of "one-point data diagnosis and appointment". Portable diagnostics and screening applications for the healthcare sector open up a whole new segment for Apple and will forever change the shape of healthcare.

Imagine a future when you get an Apple Watch (or equivalent) from your insurer to monitor your health and detect early signs of heart attack, stroke, Parkinson's disease and help you monitor and manage diabetes as well as to remind you of medications and follow-up. your exercise. And when paired with an advanced iPhone with additional FDA-approved filtering applications for early detection of skin cancer, glaucoma, cataracts and other diseases, the Future of your health will really be in your hands.

Outside the United States, China is moving in this direction with the support of the government, private and public financing, and a Chinese FDA approval process (CFDA) that favors local Chinese solutions. In China alone, there are more than 100 companies specializing in this field, many of which receive significant financial and technical support.

Let's hope that Apple accumulates the missing resources for diagnostic and screening applications and seizes the opportunity.

Lessons learned

  • Apple's new watch has two FDA-validated cardiac diagnostic applications
  • In a few years, home and outpatient diagnoses will be made using portable consumer devices: Apple Watch, mobile phones or fitness follow ups.
    • Collect and send health data to physicians as needed
    • Collect baseline data on tens of millions of healthy people to form disease prediction algorithms
  • In the United States, the FDA has changed its guidelines and policies for mobile and digital devices to make this possible.
  • Insurers will eventually pay for diagnostic wearables
  • Apple has a series of patents for additional Apple Watch sensors – blood glucose monitoring, blood pressure, UV detection, breathing
    • The watch is already able to detect the level of oxygen in the blood, sleep apnea, Parkinson's disease
    • Getting the signal from a sensor is the easiest part. Correlate this signal to an underlying condition is difficult
    • They need to step up their game – money, software, people – with the medical research community
  • China has made the construction of a local device and diagnostic industry one of its key national initiatives

Classified in: Life Sciences (NIH), Technology |