The COVID-19 pandemic, while causing immense global disruption and loss, paradoxically accelerated advancements in scientific discovery, data dissemination, and technology within the healthcare sector. With over 5 million lives lost, the pandemic served as a stark reminder of the ever-present threat of global health crises. The question is no longer if but when the next pandemic will strike. Our preparedness hinges on how effectively we learn to leverage technology and data management to build resilient ecosystems that foster collaboration, equitable care, and rapid innovation. This article delves into the critical lessons learned from the pandemic, focusing on the emerging challenges and the technological innovations that enabled healthcare systems to adapt and continue providing patient care. It underscores the urgent need for a paradigm shift in healthcare delivery and technology adoption, particularly addressing the digital divide and ensuring health literacy to maximize the potential of digital health interventions and improve health outcomes for all. We will explore advancements in telemedicine, remote patient monitoring (RPM), and the burgeoning field of wearable technologies. Crucially, while celebrating the promise of digital health, we will also emphasize the importance of acknowledging and mitigating its limitations, including interpretation challenges, data accuracy, and the nuances of artificial intelligence (AI)-driven algorithms. Furthermore, we will summarize the latest recommendations from the Virtual Care Task Force for scaling virtual medical services, offering a roadmap for a more digitally integrated healthcare future. Finally, we propose a comprehensive model for the optimal implementation of digital health innovations, built upon five core tenets: robust data management, stringent data security, the strategic use of digital biomarkers, the application of purposeful artificial intelligence, and seamless clinical integration.
Unmasking Inequities: Technology as a Bridge Across the Digital Divide
The COVID-19 pandemic starkly revealed the deep-seated disparities in healthcare access and outcomes that persist globally. While race-based disparities in COVID-19 hospitalization and mortality rates have been observed, studies suggest these differences are often attenuated when socioeconomic status, insurance coverage, and care setting are considered. However, the pandemic disproportionately affected marginalized communities, including Black, Hispanic, and Indigenous populations, who experienced higher rates of hospitalization and mortality. In the United States, for instance, Indigenous and Black Americans have died at significantly higher rates compared to White Americans. These communities often face a confluence of risk factors, including reliance on high-risk employment, delayed healthcare seeking due to financial constraints, multigenerational living arrangements, and inequities in healthcare treatment. Despite widespread stay-at-home orders, essential workers, disproportionately represented by minority groups, were unable to work remotely, increasing their exposure to the virus in workplaces and communities.
Early in the pandemic, increased morbidity and mortality were observed among patients with pre-existing cardiovascular disease (CVD). These high-risk individuals were advised to shield at home, but socioeconomic realities often made this impossible. The pandemic also led to a significant decrease in hospital visits for patients with comorbidities, raising concerns about missed or postponed care and the potential for long-term negative health consequences. The pandemic underscored the urgent need for fundamental changes in healthcare paradigms and the strategic deployment of technology to facilitate this transformation. The following sections will delve into the challenges that surfaced during the COVID-19 era and explore how technology can be leveraged to overcome them.
Navigating the Hurdles: Challenges in Pandemic Healthcare Delivery
The Digital Divide: Access and Adoption
The rapid shift towards telehealth during the pandemic, intended to protect both patients and healthcare providers and to manage overwhelming hospital workloads, brought to light significant challenges related to the adoption of digital solutions. These challenges primarily revolved around the digital divide, encompassing both access to reliable internet connectivity and the varying levels of readiness to embrace virtual care, particularly among minority groups and older populations.
Bridging the Internet Access Gap
Reliable, high-speed internet access has become indispensable, functioning as a critical infrastructure for remote work, telemedicine, online commerce, and social interaction. It is increasingly recognized as a social determinant of health. However, significant disparities in internet access persist. In Canada, for example, only a fraction of Indigenous communities have access to broadband internet compared to near-universal access in urban centers. Similarly, in the United States, rural communities, Black and Hispanic populations, and low-income households experience the highest levels of digital disenfranchisement. While mobile devices offer internet access, home-based internet access declines sharply among Canadians over 65. Rural and remote communities, including First Nations reserves, often suffer from limited broadband and mobile network coverage.
Fostering Readiness for Virtual Care Adoption
Access to the internet is only one piece of the puzzle; actual adoption and effective utilization are equally crucial. A recent study revealed that a significant proportion of seniors, particularly those over 85, were unable to participate in video consultations. This unreadiness was more prevalent among older single men, non-White individuals, those with lower education levels, and residents of non-urban areas. Barriers to video consultations included lack of technological familiarity, unstable internet connections, sensory impairments (hearing/vision), difficulties handling devices, and language barriers.
Health Literacy in the Digital Age
Health literacy, defined as the ability to access, understand, evaluate, and communicate health information, is fundamental to promoting and maintaining health across diverse settings and throughout life. Low health literacy is disproportionately prevalent among older adults, individuals with lower educational attainment, and minority populations. Critically, low health literacy is a significant determinant of health outcomes, associated with a substantially increased risk of mortality, even after accounting for confounding factors. Limited health literacy can manifest in various ways, including medication errors and a reduced understanding of health conditions, hindering timely help-seeking behaviors.
The COVID-19 pandemic demanded rapid adaptation to new information, particularly digital information, as understanding of the virus evolved. Patients were also required to navigate new models of care. Vaccination efforts exemplified the challenges, with initial lags observed, particularly among low-income and rural communities, often correlating with lower health literacy levels. Data indicates a substantial portion of the population struggles with health literacy, impacting their ability to navigate the healthcare system and proactively manage their health. These literacy challenges posed significant hurdles during the evolving care paradigms of the COVID-19 pandemic.
Evolving Healthcare Practices: Bridging the Digital Skills Gap
Transforming patient care during a pandemic necessitates a parallel evolution in how healthcare professionals (HCPs) deliver care. However, current professional training often lacks comprehensive education on effectively utilizing digital health technologies. While digital health innovation is often championed by enthusiasts, systematic integration into routine clinical workflows is frequently overlooked. Medical curricula, at both undergraduate and postgraduate levels, and continuing medical education opportunities often lack adequate training in the practical application of digital technologies for routine patient care. Surveys have revealed a lack of confidence and a desire for telemedicine-focused education among medical trainees. Accelerated telemedicine curricula, incorporating communication principles, technical skills, and virtual examination techniques, have shown promise and are transferable to various healthcare settings. Studies demonstrate that healthcare professionals trained with digital health technologies are more proficient and likely to utilize them in their practice. Beyond incorporating digital health competencies into training frameworks, educational models must also facilitate rapid knowledge translation and dissemination of new concepts and care paradigms that emerge swiftly in response to evolving health challenges.
Reassuringly, initial reports suggest that the shift to telehealth and virtual clinics did not lead to increased overall morbidity or mortality. However, the long-term impact of these digital innovations on patient outcomes compared to traditional care models remains to be fully understood. Realizing the full potential of digital health requires a workforce proficient in digital health delivery and visionary leaders to champion and implement practice changes.
Innovation Sparked by Necessity: Digital Health Triumphs During COVID-19
Telemedicine’s Pivotal Role During COVID-19
Telemedicine, despite its long-standing promise, had seen limited widespread adoption prior to COVID-19. Before the pandemic, virtual care constituted a minuscule fraction of billable healthcare services. Its use was primarily confined to the private sector, with services offered directly to patients and providers for a fee. While patients stood to benefit from increased access, cost efficiency, and convenience, providers faced barriers such as reimbursement uncertainties, jurisdictional licensing restrictions, and interoperability challenges with electronic health records. COVID-19 triggered an unprecedented, almost overnight, universal adoption of telemedicine. This rapid shift was driven by the imperative to minimize in-person ambulatory visits due to pandemic restrictions and was facilitated by temporary provincial billing codes. The post-COVID-19 era is expected to usher in a “blended” care model, integrating both in-person and virtual care modalities, including RPM, advanced AI, and algorithm-based care, where clinically appropriate.
The pivot to virtual visits during COVID-19 was essential for ensuring timely and appropriate care. Moving forward, we need to refine patient selection criteria for virtual care and RPM and rigorously evaluate their outcomes and quality to define benchmarks for “good” virtual care. The question of “Remote Patient Monitoring—Overdue or Overused?” highlights that while RPM offers potential benefits like cost reduction, reduced preventable admissions, and enhanced surveillance, further research is crucial to identify which patient populations will benefit most from RPM in the long term. The subsequent section will explore the advantages and limitations of RPM, using heart failure (HF) management as a prime example.
Telemonitoring in Heart Failure: Lessons in Effective RPM
Managing patients with HF necessitates frequent clinical assessments and laboratory tests to initiate and optimize guideline-directed medical therapy (GDMT) and to monitor for acute decompensation. RPM, by engaging patients as active participants in their care, holds theoretical appeal for both providers and patients with HF.
However, despite initial enthusiasm, many trials employing traditional physiological metrics (weight, blood pressure, heart rate) in RPM for HF have not demonstrated improved outcomes. The Tele-HF study, involving high-risk HF patients, found that daily monitoring of weight and symptoms combined with coaching did not reduce hospitalizations compared to usual care. Similarly, the TIM-HF study, despite high technology adherence rates, showed no difference in all-cause mortality. Common factors contributing to these neutral outcomes include low adherence to technology, inaccurate data, and delayed or absent clinical action based on received data. For instance, a significant proportion of patients in the Tele-HF trial never utilized the monitoring device, and device usage declined over time.
Table 1. Noninvasive heart failure remote patient monitoring trials
| Trial (country of origin) | Study population | Intervention | Results | Explanations given for results |
|---|---|---|---|---|
| Tele-HF (2010)Chaudhry et al. (USA)32 | 1653 HF patients enrolled within 30 days of hospitalisation for HF decompensation | Daily telephone call to automated interactive voice response system providing information on symptoms, clinical status, and weight | No difference in readmission or death from any cause within 180 days compared with usual care | Underuse of the telemonitoring system: only 86% of patients made any calls and only 55% making 3 calls weekly at 6 months |
| TIM-HF (2011)Koehler et al. (Germany)33 | 710 patients in NYHA II/III with LVEF ≤ 25%, or 25%-35% with decompensation requiring intravenous diuretics in previous 24 months | Patients used portable devices for ECG, blood pressure, and body weight measurements and reported self-assessed health status sent to telemedicine monitoring centre | No reduction in mortality, CV death, or HF hospitalisation compared with usual care | Stable and well managed group of patients in usual care group: only 10% experienced a cardiac event during the 24 months of the study |
| INH (2012)Angermann et al. (Germany)37 | 715 patients with signs and symptoms of HF decompensation and LVEF ≤ 40% | Nurse-delivered disease management programs of education, remote monitoring through structured telephone support and medical optimisation of GDMT | No reduction in primary composite end point of death or rehospitalisation compared with usual care; significant reduction in death from any cause (secondary end point) | Early hospitalisation may have allowed better care for patients in intervention group leading to a reduction in mortality |
| WISH (2012)Lynga et al. (Sweden)38 | 344 patients with NYHA III/IV symptoms, on diuretic and HF medication with LVEF | Daily electronic weight transmission to HF clinic vs standard scale and no automatic transmission of data; all patients advised to contact clinic if > 2 kg weight gain in 3 days | No reduction in all-cause hospitalisation or death, or composite cardiac hospitalisation or death | Despite better adherence to daily weight checking in intervention group (75% vs 32% in usual-care group), no difference, suggesting that weight alone may not be a useful monitoring metric |
| TEHAF (2012)Boyne et al. (The Netherlands)39 | 382 HF patients with NYHA II-IV symptoms, previous use of diuretics, and impaired cardiac function on echocardiography | Daily preset dialogue on symptoms, knowledge, and behaviour; device collected and provided tailored patient- and disease-specific information; no vital signs measured | No significant reduction in time to first HF hospitalisation | Trial underpowered for primary outcome and well treated and rather stable population |
| CHAT (2013)Krum et al. (Australia)40 | 405 patients with NYHA II-IV HF, LVEF | At least monthly use of telephone-based automated telemedicine system which assessed clinical status and medical management of their condition, sending alerts to HF nurses | No reduction in primary end point of Packer clinical composite score; significant reduction in HF hospitalisation compared with usual care | Possible useful intervention for those in rural locations without local access to community-based multidisciplinary care |
| BEAT-HF (2016)Ong et al. (USA)41 | 1427 patients aged > 50 years discharged home after hospitalisation for HF | Coaching telephone calls and telemonitoring including blood pressure, heart rate, symptoms, and weight | No reduction in readmission for any cause | Limited efficacy in use of weight as a surrogate of HF deterioration |
| TIM-HF2 (2018)Koehler et al. (Germany)36 | 1571 patients in NYHA II/III, LVEF ≤ 45% (or > 45% treated with diuretic) and HF hospitalisation during previous 12 months | Web-based daily remote monitoring of weight, blood pressure, pulse, ECG, peripheral capillary oxygen saturation, and self-reported health status | Reduction in the weighted average of % of days lost due to unplanned CV hospital admissions or death: HR 0.80, 95% CI 0.65-1.00 | Very high usage rate among participants: 97% of patients were 70% compliant with daily data transfer |
Implantable RPM technologies in HF have demonstrated utility in patient monitoring, but challenges related to cost, workflow integration, and consistent alert response persist. Often, clear protocols for action following alerts are lacking, diminishing system effectiveness if alerts are not followed by appropriate clinical interventions, such as medication adjustments or reinforcement of lifestyle modifications.
Successful RPM hinges on patient adherence to data transmission schedules, requiring consistent technology engagement. The TIM-HF2 trial, a notable exception with positive outcomes, reported a high patient compliance rate with daily data transfer. This trial demonstrated a modest reduction in days lost to death or cardiovascular hospitalization in the RPM group, but no significant mortality difference. Interestingly, the benefits of RPM waned after the technology was discontinued, suggesting that sustained patient and clinician engagement is crucial for long-term benefits.
COVID-19: A Heart Failure RPM Use Case
During the COVID-19 pandemic, hospitalizations for HF declined during lockdown periods. Concerns arose that this decrease might lead to increased mortality due to delayed care. However, recent data suggest no significant difference in HF mortality compared to pre-pandemic levels. It is plausible that the expanded adoption of telemonitoring mitigated potential indirect mortality in HF patients during the pandemic.
Medly, a Health Canada-approved remote patient management program, was utilized to monitor HF patients. Medly employs an algorithm to deliver personalized self-care messages based on daily patient-reported data. These messages range from reassurance of stable condition to recommending medication adjustments or seeking emergency care. Nurse coordinators manage clinical alerts, escalating to cardiologists as needed. Studies have shown Medly’s association with a significant reduction in HF-related hospitalizations and improved GDMT optimization.
During the pandemic, Medly facilitated remote HF patient management, with both patients and clinicians valuing care continuity and the strengthened patient-provider relationship. This experience underscored the importance of contextualizing RPM within the clinic setting; patients who understood the rationale for enrollment demonstrated more positive engagement, highlighting the ongoing need to cultivate strong remote patient-provider relationships.
Emerging Technologies: Reshaping Pandemic Care and Beyond
The expanding landscape of digital health is generating numerous opportunities for patient management. While not as widely deployed during the pandemic as RPM for HF, emerging technologies hold significant promise for future care enhancement. These technologies, including wearable devices for continuous monitoring and AI for patient management, have the potential to revolutionize healthcare delivery in future pandemics and beyond.
Wearables: The Era of Continuous Monitoring
Interest in wearable health monitoring technologies has surged in recent years. Smart wearables are consumer-grade devices equipped with sensors, integrated into accessories or clothing. These include smartwatches, rings, and wristbands. Common sensors in wearables are detailed in Table 2. Data from these devices can be processed to provide insights into personal health. Notably, wearables have often been introduced to consumers before rigorous validation of their effectiveness, safety, and reliability in healthcare settings.
Table 2. Engineering principles of wearable sensors50,53
| Engineering sensor | Sensor type | Description | Measurement | Examples of consumer wearable |
|---|---|---|---|---|
| Activity | Triaxial accelerometer | Evaluates linear acceleration along 3 planes based on the principle of a seismic mass attached to a mechanical suspension system | StepsActivity intensityActivity minutesEEPosture when worn on torso | Apple Watch SE, Series 3-6Fitbit Flex, One, Charge, SenseGarmin Vivoactive, VenuHuawei Watch GTOmron HeartGuideWithings Steel HR, Move, ScanOura RingMotiv Ring |
| Gyroscope | Measures angular motion | |||
| GPS | Uses satellite system to identify precise orbital position | Distance | ||
| Barometer | Uses diaphragm on a vacuum chamber that compresses proportionally to pressure | Change in altitude, stair count, and detection of falls | ||
| Heart rate and rhythm | PPG | Measures the microvascular blood volume that translates into pulse waves and a tachygram recording | ArrhythmiaHRHRVHRRCuffless BP | |
| Single-lead ECG | Contralateral finger on crown serves as negative electrode and back of the watch serves as positive electrode | Atrial fibrillation vs sinus rhythm | Apple Watch Series 4-6Fitbit SenseKardiaMobile (AliveCor)Scanwatch (Withings) | |
| Blood pressure | Oscillometry | Wrist-cuff BP | Ambulatory cuff BP monitoring | HeartGuide (Omron) |
| Fluid content | Cloth-based nanosensors | Phonocardiography, impedance cardiography, multichannel ECG, and accelerometer | Cardiac outputStroke volumeHRHRVRRThoracic impedanceActivityPosture | SimpleSENSE (Nanowear) |
Currently, a significant portion of adults regularly use smartwatches or fitness trackers. Usage is more prevalent among women, certain racial and ethnic groups, and higher-income individuals. The subsequent sections will explore the application of wearables in routine cardiovascular care.
Wearable Applications in Routine Cardiovascular Care
Activity Monitoring and Cardiac Rehabilitation
Physical inactivity contributes to millions of deaths annually worldwide. Increased physical activity at a population level could significantly impact chronic disease burden and longevity. COVID-19 related lockdowns limited opportunities for physical activity. Digital health solutions, including wearables, gained traction for maintaining activity levels during the pandemic and are likely to remain relevant post-pandemic. However, pre-pandemic studies evaluating wearable efficacy have yielded mixed results. Some studies suggest wearables alone may not outperform standard behavioral approaches for weight loss. Wearables combined with gamification strategies have shown more promising short-term results for improving physical activity. Systematic reviews indicate that wearable activity monitors can improve cardiorespiratory fitness but may have limited impact on sedentary behavior.
Cardiac rehabilitation, already underutilized, faced further access limitations during COVID-19. Virtual cardiac rehabilitation emerged as a priority, with programs leveraging home monitoring and individualized exercise prescriptions. Wearables can monitor “moderate” activity levels and assist clinicians in setting step count and heart rate goals.
Heart Failure Management with Wearables
Physical activity assessment is crucial in HF management. Wearables offer objective measures to complement subjective assessments like the NYHA functional class. Studies have demonstrated the ability of daily step counts to differentiate between HF symptom classes and predict prognosis. Ongoing research, such as the TRUE-HF study, is evaluating the predictive capabilities of smartwatch data for cardiopulmonary exercise testing in HF patients. Wearable technologies are also being explored for GDMT optimization. The NanoSense study is investigating a wearable undergarment with nanosensors for identifying patients at risk of HF decompensation, monitoring parameters like cardiac output and stroke volume. With further evidence, wearables may play a more significant role in managing future pandemics and chronic conditions.
Atrial Fibrillation (AF) Detection and Monitoring
AF, with its paroxysmal nature and stroke risk, is well-suited for remote monitoring. Smartwatches with PPG technology and arrhythmia detection algorithms can play a role in AF screening. The TeleCheck-AF project utilized teleconsultations and a PPG-based heart rhythm monitoring app to manage AF patients during the pandemic. Studies have demonstrated the utility of wearables in detecting arrhythmias. The Huawei Heart Study and the Apple Heart Study, large-scale virtual studies, demonstrated the potential of PPG-based smartwatches for AF screening, achieving reasonable positive predictive values.
Hypertension and Blood Pressure Monitoring
Hypertension remains a major CVD risk factor. The pandemic led to a reduction in blood pressure monitoring and management. Home blood pressure monitoring technologies could bridge this care gap. However, concerns exist regarding the validation and accuracy of commercially available home blood pressure devices, particularly wrist-worn devices. Recommendations emphasize developing comprehensive blood pressure management programs integrated with data transmission to clinics for informed patient management. Emerging technologies, such as smartphone video-based blood pressure estimation, show promise for improving hypertension management.
Diabetes and Blood Glucose Monitoring
Continuous glucose monitoring (CGM) devices have been available for diabetes management for nearly a decade. These devices enable continuous blood glucose monitoring, alerts, and data-driven diabetes management. While not widely deployed during the pandemic, CGM data suggested improved diabetes control during lockdowns, potentially due to lifestyle changes or increased self-care focus.
Artificial Intelligence (AI) in Pandemic Response and Healthcare Enhancement
AI, particularly machine learning (ML) and deep learning, holds immense potential in healthcare, especially during pandemics. AI can augment clinical assessments, particularly when specialist access is limited. Technology-enhanced medical devices, like digital stethoscopes with AI-powered murmur detection, can aid both novice and expert clinicians in remote assessments.
Echocardiography, a specialized field, is often limited in remote settings. AI-guided image acquisition is emerging, especially with point-of-care ultrasound. Algorithms trained on vast ultrasound datasets can guide novice operators in acquiring diagnostic-quality images, improving cardiac care access in remote and pandemic scenarios.
Challenges in Digital Health Technology Adoption
Interpretation Challenges and Data Overload
The accuracy and validation data for many consumer wearables are not publicly available. Lifestyle-focused devices may not undergo the same rigorous review as medical-grade devices. Accuracy assessments of wearables reveal variability, particularly for metrics like energy expenditure. While heart rate and step count measurements are generally more accurate, data quality and interpretation remain challenges.
Accuracy Limitations of Wearable Findings
Concerns exist regarding the accuracy of wearable devices, particularly PPG-based technologies. Studies have reported data quality issues and exclusions due to poor PPG recordings. AF detection can be challenging at higher heart rates, and device effectiveness can be context-dependent. Inaccuracies in PPG-based heart rate and oxygen saturation measurements can arise from factors like skin tone, motion artifacts, and signal crossover. Future efforts should focus on defining target user populations, establishing sensor evaluation standards, and collaborating with industry to improve device accuracy and inclusivity.
Clinical Implications and Actionability
A crucial challenge is the lack of robust evidence on the clinical outcomes and appropriate management strategies for wearable-detected abnormalities. For example, the clinical significance and treatment thresholds for wearable-detected arrhythmias remain unclear. While continuous glucose monitoring has demonstrated clear clinical benefits, evidence supporting the broader clinical utility of wearable-detected parameters in conditions like HF is still evolving. Further research is needed to establish the clinical value and patient acceptability of wearables for mainstream cardiovascular patient management.
AI-Driven Algorithm Limitations and Biases
AI and ML were utilized during the pandemic for early COVID-19 detection, but many studies suffered from methodological limitations, hindering generalizability. Algorithms were often trained on small, biased datasets with limited diversity. Similar challenges exist in AI-driven cardiology research. Despite the excitement surrounding AI in healthcare, including pandemic response, its practical solutions have been limited. Biases in training data can perpetuate and amplify existing healthcare disparities. AI-enhanced clinical decision support tools hold promise, but current AI technologies in cardiology are largely in the “hype” phase and require rigorous validation in diverse populations to ensure safety and generalizability.
Implementation Hurdles and the Maturation Lifecycle
Effective digital health innovation requires a robust implementation plan outlining timelines, resources, and deliverables. Digital health interventions (DHIs) progress through a maturation lifecycle, starting with prototype usability and feasibility evaluations, progressing to efficacy and effectiveness assessments, and culminating in economic and health technology assessments. Many DHIs fail to achieve large-scale real-world implementation, and this maturation process can be lengthy. Bridging the gap between digital health innovation and routine clinical practice requires evidence-based implementation strategies.
Lessons Learned and Future Directions: Charting a Course for Digital Health Integration
Digital health offers a powerful tool to mitigate the impact of future pandemics, provided we learn from the COVID-19 experience. Healthcare systems demonstrated agility in adopting technology-enhanced solutions, but the long-term effectiveness of this shift requires further evaluation. Key factors facilitating this change and areas needing improvement include addressing health inequities and ensuring equitable access to digital health benefits. Recommendations to mitigate pandemic impacts include addressing social determinants of health and expanding access to technology and internet connectivity to bridge the digital divide.
Changes in care delivery, including increased telehealth and digital innovation, should be co-designed with patient input to ensure patient-centeredness. Existing frameworks, such as the Virtual Care Task Force recommendations, provide valuable guidance for scaling virtual medical services.
Table 3. Recommendations of the Virtual Care Task Force91
| Develop national standards for patient health information access. |
|---|
| Support the efforts of the Federation of Medical Regulatory Authorities of Canada to simplify the registration and licensure processes for qualified physicians to provide virtual care across provincial and territorial boundaries. |
| Encourage provincial and territorial governments and provincial and territorial medical associations to develop fee schedules that are revenue neutral between in-person and virtual encounters. |
| Engage the CanMEDS consortium in incorporating and updating virtual care competencies for undergraduate, postgraduate, and continuing professional development learners. |
| Develop a standardised pan-Canadian lexicon for virtual care. |
A review of digital health solutions used during COVID-19 highlighted perceived benefits, including reduced burden on hospitals and HCPs, reduced infection risk, and support for vulnerable populations. However, implementation barriers included equity concerns, internet access limitations, health literacy challenges, the need for best-practice guidelines for RPM, and resource requirements for technology development and support. While digital health innovation showed promise, a gap remains between innovation and routine clinical integration. Bridging this gap requires a multi-faceted approach, encompassing data management, data security, digital biomarkers, purposeful AI, and clinical integration, as depicted in Fig. 1.
Figure 1. Model for optimal implementation of digital health innovations. AI, artificial intelligence.
Data Management: Taming the Data Deluge
Many digital health solutions generate vast amounts of patient data, often requiring manual review by clinicians. Automated data preprocessing and analysis are crucial to highlight important findings and prevent data overload. Without effective data organization and filtering, clinicians may become overwhelmed and disengaged. Furthermore, current patient record systems often lack the infrastructure to effectively archive and retrieve data from wearables, hindering longitudinal data analysis. System-wide approaches to data management are essential for effective digital health deployment.
Data Security and Patient Empowerment
Robust data security and patient data access are paramount. Patients must trust that their data is securely stored and accessible only to authorized healthcare team members. Patients should also have access to their own data, empowering them to actively participate in their care. Cloud-based data storage solutions are likely to be essential, requiring stringent security standards and interoperability frameworks to ensure data privacy and meaningful use. Affordable and accessible internet is also crucial for effective data flow and digital health equity. Initiatives aimed at closing the digital divide are vital for promoting digital transformation in healthcare.
Digital Biomarkers: Personalized Health Insights
Digital biomarkers, derived from wearable and sensor data, offer the potential to personalize healthcare by providing objective, continuous measures of physiological and behavioral parameters. These biomarkers can be used to explain, influence, or predict health outcomes, creating a personalized “digitome.” Examples include activity patterns, sleep metrics, and physiological responses. Data preprocessing and contextualization are crucial for deriving clinically meaningful digital biomarkers. Validation of digital biomarkers in diverse populations, including underserved communities, is essential to ensure equitable application.
Purposeful and Ethical Artificial Intelligence
Realizing the promise of AI requires a systematic approach to algorithm development and validation, underpinned by rigorous methodology and ethical considerations. Addressing biases in training data, ensuring data privacy, and promoting algorithm transparency are crucial. Frameworks like PRIME (Proposed Recommendations for Cardiovascular Imaging–Related Machine Learning Evaluation) provide valuable guidance for standardizing AI and ML applications in healthcare. The concept of “ethical AI” necessitates careful consideration of data privacy, ownership, and accountability in AI-driven decision-making. While complex neural networks can offer diagnostic and prognostic accuracy, algorithm explainability and interpretability are important for clinical trust and adoption. Open access to algorithm code for scrutiny and review, while balancing intellectual property rights, can foster trust and accelerate innovation. Public funding initiatives may be necessary to ensure equitable access to trustworthy AI-driven technologies.
Clinical Pathway Integration and Reimbursement
Seamless integration of digital health technologies into existing clinical workflows is essential for successful adoption. Addressing data management, storage, analysis workflows, clinical decision-making processes, and management plan implementation is crucial. Current care models may need to be adapted to effectively leverage digital health tools. Finally, appropriate reimbursement models for both HCPs and healthcare organizations are necessary to incentivize digital health implementation. Demonstrating the value of digital health through robust clinical evaluation studies can encourage regulatory and payer adoption of evidence-based digital health technologies.
Conclusion: Embracing the Digital Future of Healthcare
COVID-19 highlighted both the devastating impact of pandemics and the transformative potential of digital health. Digital health technologies must be held to the same rigorous standards as traditional healthcare tools, with embedded quality measures, validation, ethical AI, and secure data management. Digital health has the potential to deliver safe, efficient, and equitable care, reaching underserved populations and reducing health disparities.
Looking ahead to a post-COVID-19 future, digital health is poised to transform healthcare systems. Blended care models, permanent reimbursement for virtual care, and technology-driven solutions to health inequities are anticipated. Realizing this vision requires sustained effort, collaboration, and a commitment to responsible digital health innovation.
Funding Sources
Dr Brahmbhatt is supported by postdoctoral fellowship funding from TRANSFORM HF.
Disclosures
The authors have no conflicts of interest to disclose.
Footnotes
See page 289 for disclosure information.
