AI, telemedicine and mHealth drive global shift toward digital healthcare systems

Artificial intelligence (AI), mobile health applications, telemedicine, and data-driven systems are not only improving access and efficiency but also redefining how care is delivered, monitored, and managed across settings, reveals a new study published in Healthcare.

The editorial study titled "Healthcare Goes Digital: mHealth, eHealth, Artificial Intelligence, and Emerging Digital Technologies Within Digital Health Transformation," evaluates nine contributions within a special issue, offering a structured view of how digital health technologies are converging to reshape clinical workflows, patient engagement, and healthcare delivery models.

The findings suggest that digital health is no longer a peripheral innovation. Instead, it is becoming embedded across healthcare systems, influencing diagnosis, treatment, rehabilitation, and professional training. It also highlights that technological progress alone is not sufficient, with human, organisational, and regulatory factors emerging as critical determinants of successful implementation.

AI, mHealth and telemedicine drive a new healthcare delivery model

The study identifies a broad transformation driven by the integration of AI, mHealth, and telemedicine into routine care pathways. These technologies are enabling a shift from episodic, hospital-based treatment toward continuous, remote, and patient-centred care.

Mobile health and telemedicine have established themselves as key pillars of this transition. They support remote consultations, continuous monitoring, and improved patient engagement, particularly in chronic disease management and outpatient care. Evidence reviewed in the study shows that such interventions can improve clinical outcomes and optimise healthcare utilisation when properly integrated into existing systems.

Artificial intelligence is playing an increasingly central role in this evolution. The paper highlights its expanding use in diagnostic support, risk prediction, and clinical decision-making. AI systems are being integrated into workflows ranging from medical history collection using chatbots to advanced diagnostic processes such as digital cytology and cognitive assessment in acute care environments.

The emergence of generative AI and large language models marks a further leap. These systems are already being applied to clinical documentation, summarisation of medical information, and patient interaction. While early evidence suggests strong performance in knowledge-based tasks, the study notes ongoing concerns around reliability, hallucination risks, and safe integration into clinical settings.

Wearable devices and remote monitoring technologies are also reshaping care delivery. By enabling continuous data collection, they support a transition toward preventive and personalised medicine, allowing clinicians to track patient conditions in real time and intervene earlier.

These technologies are collectively pushing healthcare systems toward a more data-driven and proactive model. However, the study emphasises that their effectiveness depends heavily on how well they are integrated into real-world clinical workflows.

Adoption barriers reveal gap between technological potential and real-world use

The study finds that the adoption of digital health solutions is uneven and often constrained by non-technical factors. A key theme across the nine contributions is the gap between what technology can achieve and what is actually implemented in clinical practice.

• Human, organisational, and cultural factors: The acceptance of AI-supported tools, such as chatbot-based medical history-taking, depends heavily on user trust, digital literacy, and perceived reliability. Similarly, the adoption of telehealth services is influenced by demographic and behavioural factors that shape access and competence.
• Critical role of healthcare professionals in determining whether digital tools are successfully integrated: Resistance can arise when technologies disrupt established workflows or when users lack sufficient training. This is particularly evident in areas such as AI-assisted diagnostic workflows, where professional perception and readiness significantly affect implementation.
• System-level readiness: Healthcare institutions often struggle with infrastructure limitations, data governance issues, and interoperability constraints. These factors can slow down the deployment of otherwise promising technologies, preventing them from reaching their full potential.
• Variability in the level of evidence supporting different digital health interventions: While some technologies have demonstrated clear benefits, others remain at the pilot or experimental stage, highlighting the need for further validation and long-term outcome assessment.
• Education and training models: Digitally mediated approaches, such as telementoring systems like Project ECHO, are expanding access to specialist knowledge and supporting continuous professional development. These models demonstrate how digital tools can extend expertise beyond traditional institutional boundaries.

The findings suggest that successful digital health transformation requires more than technological innovation. It demands alignment between tools, users, and organisational structures to ensure effective and sustainable adoption.

Data-driven, personalised healthcare emerges amid safety and governance challenges

The study shows how digital tools are enabling more longitudinal approaches to patient management, moving beyond reactive treatment toward proactive health monitoring.

Technologies such as automated assessment systems, digital clinical workflows, and AI-driven decision support are contributing to more standardised and scalable care processes. In acute settings, for example, automated cognitive and mood assessment systems are improving consistency in clinical evaluation. In long-term care, digitalised geriatric assessment tools are supporting more efficient and comprehensive patient monitoring.

Rehabilitation and patient support are being redefined through digital interventions. Home-based telematic exercise programmes and mHealth applications are expanding access to care and enabling patients to engage more actively in their treatment.

However, the study underscores that this transformation brings new challenges. The integration of AI into clinical practice raises critical questions about reliability, generalisability, and safety. Ensuring that AI systems perform consistently across different populations and settings remains a major concern.

Data governance and cybersecurity also emerge as key issues. As healthcare becomes increasingly dependent on digital systems, the need for secure data management and robust regulatory frameworks becomes more urgent. The study reinforces calls for balancing innovation with safeguards to protect patient information and ensure ethical use of technology.

Another challenge lies in scalability and integration. While many digital health solutions show promise in controlled settings, translating these results into large-scale, real-world applications remains complex. Differences in healthcare systems, resource availability, and organisational structures can affect how technologies are implemented and their overall impact.

The study calls for stronger interdisciplinary collaboration to address these challenges. Integrating expertise from medicine, engineering, data science, and policy is seen as essential for developing solutions that are both technologically advanced and clinically effective.