Exploring the Role of Artificial Intelligence in Smart Healthcare: A Capability and Function-Oriented Review

Abstract

Artificial Intelligence (AI) is transforming smart healthcare by enhancing diagnostic precision, automating clinical workflows, and enabling personalized treatment strategies. This review explores the current landscape of AI in healthcare from two key perspectives: capability types (e.g., Narrow AI and AGI) and functional architectures (e.g., Limited Memory and Theory of Mind). Based on capabilities, most AI systems today are categorized as Narrow AI, performing specific tasks such as medical image analysis and risk prediction with high accuracy. More advanced forms like General Artificial Intelligence (AGI) and Superintelligent AI remain theoretical but hold transformative potential. From a functional standpoint, Limited Memory AI dominates clinical applications by learning from historical patient data to inform decision-making. Reactive systems are used in rule-based alerts, while Theory of Mind (ToM) and Self-Aware AI remain conceptual stages for future development. This dual perspective provides a comprehensive framework to assess the maturity, impact, and future direction of AI in healthcare. It also highlights the need for ethical design, transparency, and regulation as AI systems grow more complex and autonomous, by incorporating cross-domain AI insights. Moreover, we evaluate the viability of developing AGI in regionally specific legal and regulatory frameworks, using South Korea as a case study to emphasize the limitations imposed by infrastructural preparedness and medical data governance regulations.

Keywords: AI capabilities; AI functionalities; AI in healthcare; Theory of Mind; medical decision support; narrow AI; smart healthcare.

Figure 1

Key applications and benefits of generative AI in healthcare. This schematic illustrates the multifaceted contributions of generative AI, including enhanced diagnostic capabilities, predictive patient outcomes, personalized treatment plans, drug discovery, and support for the human dimension of therapy. These interconnected functions highlight the potential of generative AI to transform both clinical practice and biomedical research.

Figure 2

Proposed architecture of a General Artificial Intelligence (AGI) system for smart healthcare. The system integrates multimodal inputs (e.g., speech, vision, and physiological signals) through a perception engine, followed by emotion fusion and neuro-symbolic state inference. Episodic-context memory allows longitudinal tracking, while reasoning and ethical alignment modules ensure explainability, transparency, and value-sensitive behavior. Privacy-aware federated learning and explainable AI components enable secure, personalized, and human-centric policy-based responses for patient care.

Figure 3

It highlights a structured approach from defining research objectives and search strategies to applying selection criteria, extracting and analyzing data, and conducting quality assessment.

Figure 4

Collaborative integration of AI across clinical specialties. The Venn diagram illustrates how AI functions at the intersection of key medical roles—radiologist, pathologist, surgeon, medicine physician, and primary care physician. AI supports each domain through diagnostic assistance, image interpretation, treatment planning, and decision support, fostering a multidisciplinary approach to smart healthcare.

Figure 5

ToM applications in AI-driven healthcare and human–computer interaction. These include virtual mental health companions, empathetic healthcare assistance, personalized recommendations, emotional intelligence education, interactive storytelling, and dynamic patient engagement. ToM-enabled systems aim to understand and respond to user emotions, intentions, and social cues, enhancing contextual and human-centered care.

Figure 6

Representative applications of AI in medical imaging and diagnostic prediction. On the left, AI-driven medical imaging tasks include tumor detection, lesion segmentation, anomaly classification, and organ boundary detection. On the right, diagnostic prediction applications include disease risk scoring, sepsis prediction, hospital readmission forecasting, and comorbidity detection. These use cases demonstrate how AI enhances precision and efficiency in both image-based and data-driven clinical workflows.