Why digital healthcare is increasingly popular with both doctors and patients

en español

This article looks at factors driving the growth in digital health care, remote monitoring and wearable devices. It considers the role of wearable devices and AI within the digital healthcare infrastructure, and provides examples of such devices. It then reviews the major challenges facing wearable device manufacturers, and describes some of the semiconductor and passive component solutions available.

Advances in IoT technology, 5G communications, miniaturisation of electronic components, and developments in AI are allowing medical equipment manufacturers to develop increasingly powerful, yet compact and unobtrusive wearable devices. Healthcare professionals, patients and the general population alike are enjoying the benefits; this is reflected in a report by Grand View Research, which valued the global wearable medical device market size at USD 26.8 billion in 2022 and expects it to grow at a compound annual growth rate (CAGR) of 25.7% from 2023 to 2030 .

The COVID pandemic had a significant impact on the devices’ uptake. To ensure social distancing and avoid infection, healthcare practices in many countries shifted from in-person consultations to telemedicine. The growing prevalence of chronic diseases along with increasing mortality rates is a major area of concern among people as well as government organizations. Thus, healthcare providers are offering personalised care including home care, and continuous, remote patient monitoring.

In the clinical environment, wearable devices can be regarded as integral components of wireless health information systems, which are a fast-growing factor in improving patient comfort.

Meanwhile, rising public awareness of the need to live a healthy and active lifestyle, and to use personal health monitoring, has increased market demand for wearable activity trackers and smartwatches. Wearables that track heart rate, sleep, and physical activity levels are already widely used for sports and fitness purposes, and now diagnostic wearables are primed to deliver innovation for more challenging wellness and medical applications. Opportunities for diagnostic wearables range from diet tracking to cancer detection.

This means that wearable technology is progressing on multiple fronts, with use cases in the consumer market, telehealth and in clinical settings. Many applications have already found notable success, including:

Fitness, e.g., activity tracking, performance monitoring and heart rate tracking
Wellness, e.g., sleep tracking, sun exposure and weight monitoring
Medical, e.g., vital sign monitoring, glucose monitoring and remote EEG/ECG/EMG

What is a wearable device?

Wearable technologies provide a practical way to monitor physiological symptoms as well as a wide range of medical treatments. These gadgets are easy to use and also provide real-time data for doctors to evaluate. Wearable medical technology has a wide range of possible applications in healthcare, from the ECG functions of the Apple Watch to innovative continuous glucose monitoring systems. In addition, the FDA recently approved Current Health’s wearable artificial intelligence (AI) gadget that measures multiple vital signs for patients to use at home.

Wearable medical devices are used to diagnose and monitor patients’ vital health signals, such as heart rate and rhythm, respiratory rate, blood pressure, and a variety of other parameters. These devices are placed on the patient’s body to collect personal data. Using wireless technology, the wearable medical device provides the patient with independence and convenience. Wearable medical devices are also used for therapeutic purposes.

Wearable devices such as smart watches, smart bracelets, and finger rings have been around for some time, but COVID-19 has caused a significant increase in demand for them. Wearables are essential in the fight against COVID-19 and potential future pandemics. Wearable gadgets can also transmit health information, and provide mental health care by monitoring an individual’s cognition and mood in real time, allowing for individualised intervention. Wearable devices are becoming more popular as a result of these and other comparable uses.

Examples of wearable devices

Wearable fitness trackers: These wristband devices are equipped with sensors to keep track of users' physical activity and heart rate. Many fitness trackers provide health and wellness recommendations by syncing to various smartphone apps. Fitbit’s Charge 4, for example, comes equipped with a built-in GPS and a 24/7 heart rate monitor. The Garmin vivosmart 4 fitness band monitors users' heart rates and includes tools such as all-day stress tracking, a relaxation breathing timer, and VO2 max readings .

Smart health watches: Once only used to count steps and tell time, smartwatches have transformed into clinically viable tools for healthcare. Accompanied by Apple's iconic movement rings and dozens of workout modes, the Apple Watch Series 6 can monitor a user's heart rate and blood oxygen level, take an ECG anywhere, at any time, and notify users if something is wrong.

Wearable ECG monitors: Wearable ECG monitors measure electrocardiograms, or ECGs—helping users track their heart rhythm and rate, as well as measure other vital parameters, including blood pressure. AliveCor’s KardiaMobile 6L portable EKG monitor is FDA-cleared to detect atrial fibrillation (AF), bradycardia, and tachycardia. The handheld monitor can also be worn as a chest strap and be used either with or without a smartphone. The Wellue DuoEK continuously records EKG up to 15 minutes and can detect early signs of arrhythmia, heart pauses, AF, tachycardia, bradycardia, and premature atrial contractions (PACs).

VivaLink has designed a small ECG monitor for in-clinic and remote patient monitoring (RPM) applications. It records data on heart rate, RR interval, and respiratory rate.

Wearable blood pressure monitors: In 2019, Omron Healthcare launched HeartGuide, the first wearable blood pressure monitor. It measures blood pressure and daily activity, including steps taken and calories burned. Over the past few years Omron has developed more wearable blood pressure monitors in an effort to remain a leader in the increasingly competitive space.

Withings BPM Connect is an armband that measures a user's blood pressure and shows results immediately on the screen with colour-coded feedback. Users can connect their device with the company's companion Health Mate app, where they can then share blood pressure results with their doctor.

Wearable biosensors are still in their infancy in regard to large-scale development and adoption, yet they hold potential to revolutionise telemedicine and remote healthcare. These devices are portable sensors implemented as gloves, clothing, bandages, or implants. They create two-way feedback between users and their doctors and enable continuous and non-invasive disease diagnosis and health monitoring from physical motion and biofluids.

The Phillips Biosensor BX100 measures vital signs, posture, and activity. It is a single-use wearable patch that should be incorporated into existing clinical workflows—supporting surveillance of higher acuity patients moving from intensive care units into lower acuity general care areas. In 2020 the Philips Biosensor BX100 earned 510(k) clearance from the US Food and Drug Administration (FDA) to help manage confirmed and suspected COVID-19 patients in a hospital.

The Biovitals platform developed by Biofourmis collects population metadata and compares it to real-time patient physiological signals via the Everion wearable armband. It's designed to help healthcare providers predict and prevent serious medical events. However, to access the platform patients must seek advice from their clinician and get a prescription. Once the BiovitalsHF app is prescribed, the clinician will register and onboard them to the program.

Wearable devices as components of a healthcare infrastructure

Some wearable devices like Smartwatches are available for consumer purchase, and can work in standalone mode to keep their users informed about their health and fitness levels. Others, however, are designed to be deployed by healthcare professionals as part of a comprehensive digital healthcare system.

Biofourmis’ ‘Hospital at Home’ system, for example, uses dynamic care pathways, continuous monitoring, care coordination tools, and configurable services to enable clinicians to deliver inpatient-level care at home .

Biofourmis Care can help their healthcare partners to:

Improve clinical outcomes with lower rates of mortality
Increase bed-days saved and create capacity for more acute patients
‍Increase patient satisfaction by treating patients where they are most comfortable
Deliver remote care similar to inpatient workflows through electronic medical record (EMR) integration
Utilise a coordinated network of in-home partners providing services such as: nursing, phlebotomy, infusion, wound care, and other ancillary services
Maximise patient-to-staff ratios with a scalable, technology-enabled platform

How AI can improve digital healthcare and patient outcomes

According to Statista, the artificial intelligence (AI) healthcare market, valued at $11 billion in 2021, is projected to be worth $187 billion in 2030. That massive increase means we will likely see considerable changes in how medical providers, hospitals, pharmaceutical and biotechnology companies, and others in the healthcare industry, operate .

Better machine learning (ML) algorithms, more access to data, cheaper hardware and the availability of 5G have contributed to the increasing application of AI in the healthcare industry, accelerating the pace of change. AI and ML technologies can sift through enormous volumes of health data—from instruments and wearable devices, health records and clinical studies to genetic information—and analyse it much faster than humans .

Here are some typical examples:

Dosage error reduction: AI can help identify errors in how a patient self-administers medications, leading to better patient health outcomes and reduced healthcare costs and hospitalisations. One example comes from a study in Nature Medicine, which found that up to 70% of patients don’t take insulin as prescribed . Using an AI system of wireless sensing, a tool that sits in the patient’s background (much like a Wi-Fi router) can flag errors in how the patient administers an insulin pen or inhaler.

Increased efficiency in healthcare diagnoses: According to Harvard’s School of Public Health, although it’s early days for this use, using AI to make diagnoses may reduce treatment costs by up to 50% and improve health outcomes by 40% .

One use case example comes from the University of Hawaii, where a research team found that deploying deep learning AI technology can improve breast cancer risk prediction . More research is needed, but the lead researcher pointed out that an AI algorithm can be trained on a much larger set of images than a radiologist—as many as a million or more radiology images. Also, that algorithm can be replicated at no cost except for hardware.

An MIT group developed an ML algorithm to determine when a human expert is needed. In some instances, such as identifying cardiomegaly in chest X-rays, they found that a hybrid human-AI model produced the best results.

Another published study found that AI recognised skin cancer better than experienced doctors. US, German and French researchers used deep learning on more than 100,000 images to identify skin cancer. Comparing the results of AI to those of 58 international dermatologists, they found AI did better .

Better health monitoring and preventive care: As health and fitness monitors become more popular and more people use apps that track and analyse details about their health, they can share these real-time data sets with their doctors to monitor health issues and provide alerts in case of problems.

AI solutions—such as big data applications, machine learning algorithms and deep learning algorithms—can also analyse large data sets to assist in clinical and other decision-making. AI also detects and tracks infectious diseases, such as COVID-19, tuberculosis and malaria.

Connecting disparate healthcare data: One benefit of AI for health systems is making gathering and sharing information easier. AI can track patient data more efficiently than humans can. Through AI and machine learning, health organisations can connect disparate information that previously might not have been gathered and analysed, allowing a more unified look at patients’ health.

One example is diabetes. According to the Centers for Disease Control and Prevention, 10% of the US population has diabetes . Patients can now use wearable and other monitoring devices that provide feedback about their glucose levels to themselves and their medical team. AI can gather that information, store and analyse it, and provide data-driven insights from vast numbers of people, unlike anything available before. Leveraging this information can help determine how to better treat and manage diseases.

Some practical aspects of building wearable devices - challenges and solutions

Hardware designers have always been challenged to package high-functionality electronics into the relatively small spaces available within wearable devices. Along with the core electronic design, attention must be given to providing environmental protection, power and thermal management, and good signal quality.

Worse yet, pressure for further miniaturisation is always present – either to build smaller, lighter, less obtrusive devices, or to cram more functionality into the existing package. Under these circumstances, wearable device OEMs look to semiconductor and passive component manufacturers for the latest, smallest and best products to help overcome their challenges.

In September 2022 Molex/Avnet produced a survey titled ‘Diagnostic wearables: The future of medical monitoring’ . One question this survey posed was: ‘What is the most difficult part of making wearable diagnostics smaller?’. The respondents’ ranking of the relevant factors is shown below:

Figure 1: Molex/avnet survey question

This chart shows that sensors, connectors, and power management present the biggest miniaturisation challenges. Accordingly, we now look at some of the products currently available to help engineers solve these problems.

Sensors

Accelerometer: The key specification for accelerometers used in battery-powered, wearable applications is ultra-low power consumption, typically in the µA range, to ensure that battery life is prolonged for as long as possible. Other key criteria are size and integrated features, such as spare ADC channels and a deep FIFO to help with power management and functionality in the end application. For these reasons, MEMS accelerometers are typically used in wearable applications.

Accelerometers used in wearable applications typically classify motion; provide freefall detection; measure the presence or absence of motion to provide system power up, down, or sleep; and help with data fusion for ECG and other vital sign monitoring (VSM) measurements .

Figure 2: Analog devices ADXL362BCCZ-R2 MEMS accelerometer

The Analog Devices ADXL362 is an ultra-low power, 3-axis MEMS accelerometer that consumes less than 2µA at a 100Hz output data rate and 270nA when in motion triggered wake-up mode. Unlike accelerometers that use power duty cycling to achieve low power consumption, the ADXL362 does not alias input signals by undersampling; it samples the full bandwidth of the sensor at all data rates. In addition to its ultra-low power consumption, the device has many features to enable true system level power reduction.

It includes a deep multimode output FIFO, a built-in micropower temperature sensor, and several activity detection modes including adjustable threshold sleep and wake-up operation that can run as low as 270nA at a 6Hz (approximate) measurement rate. A pin output is provided to directly control an external switch when activity is detected, if desired. Typical applications are hearing aids, home healthcare devices, motion enabled power save switches, wireless sensors, and motion enabled metering devices.

Pulse oximeters/SpO2 sensors: Optical SpO2 sensors use red and infrared light sensors to detect blood oxygen levels, sensing changes in those levels by looking at the colour of the wearer’s blood.

It measures the volume of oxygen based on the way the light passes through their finger and delivers the data to the device's screen, which will display the percentage of oxygen in the blood.

An oxygen saturation percentage greater than 95% is considered to be a normal reading. A score of 92% or less could warrant further investigation to determine whether it's related to an as yet undetected health issue.

It can be used to check whether someone needs assistance with their breathing via a ventilator, measure a person's ability to handle intensive physical activities, or check whether the wearer is experiencing breathing issues when sleeping.

While COVID-19 has put the focus on blood oxygen on the map, SpO2 monitoring is also used for less extreme reasons, for example by athletes spending time at altitude.

Above all, SpO2 sensors can also detect sleep apnoea; a condition which if left undetected can lead to an increase in the risk of high blood pressure and obesity and can even cause a heart attack .

Figure 3: Analog devices MAX30110ACCEVKIT# pulse oximeter evaluation kit

SpO2 device development can be helped with the Analog Devices MAX30110ACCEVKIT# evaluation kit (EV kit) for the MAX30110. It allows for the quick evaluation of the MAX30110 and MAX30112 optical analogue front end (AFE) for applications at various sites on the body, particularly the wrist. MAX30110 supports a standard SPI compatible interface whereas MAX30112 supports an I2C compatible interface.

The EV kit allows flexible configurations to optimise measurement signal quality at minimal power consumption. The EV kit consists of three boards: MAX30110_UC_EVKIT main data acquisition board, MAX30110_SFH7050_EVKIT and MAX30110_OSB_EVKIT sensor daughter boards. The EV kit comes with a MAX30110EWG+ in a 24-bump wafer-level package (WLP). Typical application includes fitness wearable devices, in-ear wearable devices, SpO2 monitoring devices and wrist-worn wearable devices.

Connectors

In today’s fast-growing medical wearable markets, designers must create safe devices that provide effective performance in astoundingly small form factors. Ultra-miniaturised interconnect solutions support these products’ power and signal requirements. However, the selection or development of connectors for wearables depends on unique parameters that apply to specific applications.

Wearable medical devices prioritise user safety and comfort, making miniature, rugged, IP sealed, high performance connectors the right choice. Meanwhile, the devices and mechanisms that charge these products may have different needs. Miniaturisation and reliability are key for both sides of the equation.

High density micro board-to-board connectors: Amphenol’s 103 series are 0.35mm pitch micro board-to-board connectors designed for high density applications. They support extreme low profile 0.60mm stack height, and are offered with 6 to 64 positions.

These low profile connector designs with fine pitch have a high current rating up to 5A. Double contact points ensure enhanced contact stability, and the connectors have a wide temperature operating range from -40°C to +85°C. They meet USB 3.1 Gen 2 signal transmission rates and are ideal for consumer applications such as mobile phone, smart watch, smart glasses and VR/AR devices.

Figure 4: Amphenol 0.35 pitch – 0.60 stack height, BTB, 103 Series

Power management

Power management within wearable devices calls for many components, including DC to DC converters, voltage references, power diodes, low drop out (LDO) regulators, wireless power receivers and battery chargers, and ESD suppression and protection.

Transferring power into wearable devices to charge their batteries is always a challenge, because of the devices’ small size and need to operate reliably in unpredictable, demanding environments. These devices are typically small and thin, with varying form factors and industrial design. Battery sizes might range from 100- to 300-mAh capacity, which determines the required charge rates. The plug-and-jack style or micro-USB types of connectors have traditionally been used to charge such devices; however, even these relatively small connectors are now too large for some of the new ultra-thin wearable applications. Connector contamination is an even greater problem due to the outdoor wearable environment.

Wireless charging is a solution to these problems and offers additional opportunities to designers. Existing semiconductor devices used for the Qi standard established by the Wireless Power Consortium (WPC) can be easily adapted for this lower-power application. The technology uses two planar coils to transfer power though a sealed case. For low-power wearable devices, a small, thin low-power receiver coil easily could fit into the back of the case or wristband area. Qi-compliant devices are a mature solution that can shorten development time, and the products are supported by the existing WPC infrastructure.

One solution can be based on NXP’s NXQ1TXH5/101J single chip wireless transmitter for a 5V Qi-certified/compliant low power wireless charger. It offers a fully integrated solution that includes a 5V full-bridge power stage, as defined in WPC 5V Qi standards A5, A11, A12 and A16. The device uses dedicated analogue ping circuitry to detect devices. The IC is optimised to operate from a 5V USB power supply and uses Smart Power Limiting (SPL) to adjust the output power automatically to compensate for power-limited supplies. The device supports Foreign Object Detection (FOD). Typically used in smartphones, toys, shavers, pads and other handheld devices, smartwatches and other wearables.

Figure 5: NXP NXQ1TXH5/101J BQ51050BRHLR single chip wireless transmitter for a 5V Qi-certified/compliant low power wireless charger

Managing the internal power architecture: The Analog Devices MAX20360 is a highly integrated and programmable power management solution designed for ultra-low-power wearable applications. It is optimised for size and efficiency to enhance the value of the end product by extending battery life and shrinking the overall solution size. A flexible set of power-optimised voltage regulators, including multiple buck, boost and buck-boost converters, and linear regulators, provides a high level of integration and the ability to create a fully optimised power architecture. The quiescent current of each regulator is ultra-low targeted at extending battery life in always-on applications.

The MAX20360 includes a complete battery management solution with battery seal, charger, power path, and fuel gauge. Both thermal management and input protection are built into the charger.

Figure 6: Analog devices MAX20360 PMIC with ultra-low IQ regulators, charger, fuel gauge, and haptic driver for small Li+ system

What is the outlook for the future of digital healthcare?

In Smart Data Solutions’ view , the outlook for the future of healthcare is more connected, interoperable, data-driven, and prevention-focused. Today’s healthcare system operates disconnectedly, with health plans, hospital systems, pharmaceutical companies, and medical device manufacturers functioning separately. According to Deloitte, by 2040, the healthcare industry will be much more connected, with interoperable and secure technology streamlining the sector.

This interoperable technology, powered by AI, will use consumer data to “help identify illness early, enable proactive intervention, and improve the understanding of disease progression.” There will be a focus more on prevention and less on treatment. According to Formstack, genetic testing and genomic profiling will likely be widely used in addition to wearable devices and interoperable technology. This is another factor to support data-rich, patient-customised care, which will contribute once again to the idea of prevention as opposed to treatment.