Abstract:
Background: Artificial Intelligence (AI) is playing an expanding role in public healthcare because of its greater precision, efficiency, accessibility, and potential to reduce costs. This study investigates how AI can support healthcare systems by improving diagnostic accuracy, optimizing workflows, and expanding access. Post- COVID-19, health systems globally have accelerated digital transformation, including AI integration in strategic planning.
Aim: This study aimed to explore whether AI can help address key healthcare challenges.
Methods: This paper presents a narrative review of recent literature examining the integration of AI in public healthcare, focusing on service delivery, diagnostic innovation, and public health management.
Results: The analysis revealed that many patients remain dissatisfied, especially in tertiary public hospitals. persistent issues such as limited access, diagnostic delays, and communication gaps remain across public healthcare systems. However, AI offers promising interventions: Diagnosis: AI-powered tools in radiology and pathology improve early detection and diagnostic precision, particularly through machine learning and neural networks.
Triage: While few countries have adopted large-scale AI triage tools, pilot models demonstrate improved patient prioritization and emergency response.
Telehealth: AI-enhanced platforms, such as symptom checkers and virtual health assistants, increase remote access and facilitate patient engagement.
Personalized Treatment: AI contributes to individualized care plans through genomic data analysis and predictive modeling, especially in oncology and chronic disease management Robotic Procedures: Robotic-assisted surgeries, though still a minority practice, show improved procedural outcomes and reduced recovery times.
Patient Education & Monitoring: Virtual assistants aid in medication adherence, health literacy, and remote follow-up, supported by AI-driven alerts and monitoring systems.
Public Health Surveillance: AI assists in tracking disease outbreaks, modeling epidemiological trends, and guiding policy through real-time data analysis.
Research & Support Services: AI accelerates literature synthesis, clinical trial recruitment, and patient referral coordination.
Despite advances, challenges remain: bias in training data, resistance to adoption, ethical concerns, budgetary constraints, and the irreplaceable value of human empathy in care. AI should be viewed as a supportive tool, not a substitute for ethical and compassionate medical practice. Regulatory oversight and clear ethical frameworks are necessary for safe implementation.
Conclusions: AI is increasingly embedded in healthcare, particularly in diagnostics, predictive modeling, and patient- specific treatment. If implemented responsibly and equitably, it can improve outcomes, optimize workflows, and strengthen public health. Ultimately, AI has the potential to alleviate clinician shortages, long wait times, and rising service demands, contributing to more inclusive, efficient, and future-ready healthcare.
