Robin Farmanfarmaian is a Silicon Valley entrepreneur who works in technology and artificial intelligence. He has been involved with more than 20 early-stage healthcare and biotech startups, including those working in medical devices and digital health.
With more than 180 speaking engagements in 15 countries, he has educated audiences on many aspects of technology that intersect with healthcare, including artificial intelligence and the shift in healthcare delivery to the patient’s home.
He has written four books, including The Patient as CEO: How Technology Empowers the Healthcare Consumer and, more recently, How AI can democratize healthcare: The rise of digital care.
Healthcare IT News spoke with Farmanfarmaian to discuss where AI is impacting remote patient monitoring today and how AI can democratize healthcare.
Q. Where is remote patient monitoring today? Where do you see RPM in five and 10 years?
A. Remote patient monitoring is still in its first five years of adoption and integration into the healthcare system, and the pandemic accelerated this trend by illustrating the need and value of RPM. There are now many clinical-grade devices that patients can purchase or use to measure and monitor various vital signs, including EKGs, heart rate, heart rate variability, blood pressure, and blood oxygen level.
The Centers for Medicare & Medicaid Services is one of the organizations that sets the standard of care in the US health care system, and CMS released CPT codes for remote physiological monitoring more than four years ago. CMS has expanded coverage and specificity in recent years with additional and updated CPT codes.
In 2022, CMS released CPT codes for remote therapeutic monitoring (RTM). These codes cover RTM for respiratory and musculoskeletal (MSK) conditions, such as remote physical therapy and COPD inhaler monitoring. Considering that most medical care happens in a patient’s daily life, not the occasional visit to the clinic, this is a big step forward in helping patients use their treatments in the best possible way every day. the days.
Many major corporations have released their own FDA-approved wearable devices, blurring the lines between healthcare companies and consumer-facing technology companies. Apple, Amazon, Google and Samsung are some of the giants that can change the habits of consumers on a national scale, and all have launched conventional portable devices.
For example, the Apple Watch outsold the entire Swiss watch industry for several years in a row, and the device has an electrocardiogram monitor approved by the FDA for use by people over the age of 22 with no history of arrhythmia.
This trend is great news because many people may already be monitoring something about their health, whether it’s blood pressure monitoring, continuous glucose monitoring, or even a simple accelerometer to count steps. That makes it significantly more likely that a patient will continue to use the device if their healthcare professional recommends it and has access to the data.
In 10 years, remote patient monitoring will be widespread and likely to be reimbursed by all major payers. We are already seeing that RPM has the ability to detect hospital readmissions days before they happen. The healthcare industry is experiencing a revolution in vital signs measurement devices, with many companies innovating ways to collect vital signs.
New innovations include taking vital signs with a smart watch, using only a smartphone camera or laptop, standard vital signs breathalyzer devices such as BP and Sp02, wearable sensors, epidermal sensors, and subcutaneous sensors.
Within 10 years, monitoring of vital signs will be more seamless and effortless for the patient, like subcutaneous sensors that last five years. Eversense already has an FDA-cleared implantable sensor for continuous glucose monitoring that passively records glucose levels 24/7.
Q. How did artificial intelligence first appear with RPM? What was the connection?
A. Some of these newer FDA-approved devices measure vital signs continuously, meaning they collect thousands of data points a day from each patient. BiolntelliSense has a rechargeable, medical-grade sensor that attaches to the chest and passively measures more than 20 vital signs, recording 1,440 measurements per day.
Humans do not have the ability to analyze and interpret thousands of data points every day for every patient. That’s why these clinical-grade wearables and sensors have an AI software component to manage, monitor, analyze, and interpret the thousands of daily data points per patient. AI software typically flags or alerts the healthcare team and patient when vital signs fall outside of predetermined ranges customized for the individual.
While it’s still early in this trend, there are examples of new innovations that only exist because of continuous, personalized data collection. January AI uses data from the previous three days from a continuous glucose monitor combined with vital signs data to predict real-time glucose response to individual foods, educating the patient at the point of decision making.
This helps manage diabetes in a more personalized and predictive way, rather than the standard reactive way diabetes is currently managed. But the January AI isn’t just for people with diabetes. They work with athletes, people with prediabetes or metabolic syndrome, and people who just want to be as healthy as possible.
This real-time education doesn’t just assume that the standard diabetes diet is right for each individual, or that there is a healthy diet that works for everyone. People do not react to food in the same way as others, or even themselves.
Everyone has a unique glucose response to food based on many factors, including activity level that day, sleep, amount of fiber, stress, weight, age, and many more data points. AI-based software combined with RPM enables personalized attention 24/7.
Q. Today, how is AI working with RPM to improve patient care and outcomes?
A. When RPM is used for serious conditions, it can be the difference between life and death. VitalConnect conducted a study on its single-lead VitalPatch EKG and was able to predict hospital readmission for cardiac patients 6.5 days in advance.
Alacrity Care is working on RPM for oncology that combines vital signs taken with FDA-approved devices, including the Omron blood pressure watch and Oxitone pulse oximeter watch with an oncology doctor’s daily log and blood work on the home.
This is to detect serious life-threatening problems, such as neutropenia, sepsis, and cytokine storm, days before a cancer patient has serious medical problems. Early detection of these three conditions can be the difference between life and death.
New AI-based software tools are being approved by the FDA, including one earlier this year for TytoCare that analyzes lung sounds for the patient and remote doctor using a connected stethoscope in the home.
There are other companies that work with sensors in clothing that are covered by Medicare. SirenCare has socks available by prescription that control temperature on the bottom of the foot.
For patients with diabetes, a hot spot on the bottom of the foot could cause a skin ulcer, which could eventually lead to amputation if the wound doesn’t heal. With access to continuous data, the software can alert the patient and doctor when there is a problem so it can be treated before the skin is broken.
RPM’s promise and goal is to keep patients safe at home and catch problems early, before they become serious or emergency problems.
Q. You have a new book with Michael Ferro, “How AI Can Democratize Healthcare.” How does that theme fit in with the combination of AI and RPM?
A. When it comes to AI, life begins at a billion data points. There are some major problems with the traditional healthcare datasets that exist today for training software. Most healthcare data is locked in silos, whether it’s the EHR, faxes, payer, or clinic notes.
In fact, when I get lab results from my doctor through the hospital patient portal, they are uploaded as a scanned fax and saved as a PDF that is not machine-readable and sometimes not even human-readable. While we are seeing interoperability progress, there is still a long way to go.
Typical healthcare data is collected on people at a point in time, such as their annual physical exam or if they are hospitalized. That often means the data doesn’t include an individual’s baseline, taken in their daily environment. It also means that most clinical-grade vital signs data is from people who are already sick enough to be in a hospital.
By shifting data collection into the daily life of the patient, RPM has the ability to collect clinical-grade data when people are at all stages of health and at all ages. When continuously compiled into machine-readable databases, once RPM is fully adopted, those databases have the ability to dwarf the EHR data of a hospital or health system.
That’s the kind of training data that can give healthcare a much deeper insight and understanding of normal vital signs across all ages, genders, and genetics.
RPM helps democratize healthcare in a way never before possible. Many people do not live with easy access to a doctor or clinic. Trying to get to a clinic during its office hours can be nearly impossible for some people due to many factors, from not being able to leave work, school, finding transportation, distance, child care, and other barriers to travel to a clinic. clinic.
Even for established patients, specialist doctors typically book a month or three in advance, giving a medical problem time to progress and potentially worsen. That, in turn, reduces the chances of a successful outcome when and if that patient is ever seen and treated by a health professional.
Rather than trying to physically get to a clinic, RPM can be used to determine when someone needs to see a healthcare professional and can make a virtual care visit much more effective.
The best medical care is medical care that is actually performed. RPM enables passive healthcare in someone’s everyday environment, 24/7.
Twitter: @SiwickiHealthIT
Email the writer: [email protected]
Healthcare IT News is published by HIMSS Media.
