JMIR Publications

ABSTRACT

Background:

Digital platforms are transforming healthcare and life sciences by enhancing operational efficiency, improving patient outcomes, and accelerating product development and market access. These platforms facilitate telemedicine, remote patient monitoring, and data-driven care delivery, while in life sciences, they streamline research, optimize manufacturing, and support regulatory compliance. However, current Artificial Intelligence (AI) based solutions remain fragmented and domain-specific, lacking the integration necessary to address complex challenges within and across these industries. While AI excels in specialized areas—such as radiology image analysis, sepsis-detection predictive analytics, and AI-driven drug discovery—these solutions often operate in isolation.

Objective:

This scoping review aims to critically analyze the current landscape of digital platforms in healthcare and life sciences, identify existing gaps and opportunities, and explore the feasibility of developing a comprehensive, universal AI-based platform.

Methods:

A scoping review was conducted following PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive search of peer-reviewed literature, industry reports, and regulatory documents was performed across databases including PubMed, Embase, CINAHL, PsycINFO, Scopus, IEEE Xplore, and Web of Science. Inclusion criteria focused on studies, reports, and documents published from 2014 to 2024, addressing digital platforms, AI integration, healthcare and life science applications, regulations, and professional ethics. Data were charted and synthesized to identify themes related to platform capabilities, gaps, and integration potential.

Results:

The review identified seven common digital platform types utilized across healthcare and life sciences, alongside a growing trend in the implementation of AI, including generative AI. Significant gaps were found in interoperability, cross-sector collaboration, and platform utilization. AI technologies showed promise in accelerating drug discovery and improving diagnostic accuracy while reducing healthcare costs. Despite these advances, differences in data standards, regulatory constraints, and proprietary formats hinder seamless integration with existing electronic health record systems and healthcare workflows. Moreover, AI applications often neglect comprehensive, personalized treatment plans that integrate genomics, lifestyle factors, comorbidities, and social determinants of health. Organizations like World Health Organization, Massachusetts Institute of Technology, and Microsoft are exploring integrated solutions, but challenges in data standardization, privacy, regulatory, and ethical considerations remain.

Conclusions:

A universal AI-based digital platform could revolutionize healthcare and life sciences by improving efficiency, patient outcomes, and research innovation. By addressing current fragmentation and fostering integration across sectors, such a platform could enable continuous improvement and innovation in healthcare delivery and treatment development. However, overcoming challenges related to interoperability, regulatory compliance, and ethical standards is critical. Collaborative efforts across sectors are essential to develop connected, responsive, and effective national and global healthcare systems. Future research should focus on defining the universal platform's structure and scope, developing comprehensive design strategies, and aligning AI applications with healthcare ethics to ensure equitable and effective integration.