BACKGROUND The construction of artificial intelligence (AI) platforms in hospitals forms the basis of the modern healthcare revolution. While traditional hospital information systems have facilitated digitalization, they are still limited by data siloes, fragmented workflows and insufficient clinical intelligence that impede organizations from realizing the promise of data-led decision-making. OBJECTIVE This review aims to provide a strategic roadmap for hospitals to build comprehensive AI platforms, moving beyond siloed AI applications toward infrastructure at the system level that supports sustainable, scalable, and interoperable intelligent services across clinical, operational, and administrative domains. METHODS A systematic literature search was performed in Web of Science, EMBASE, PubMed, and Scopus. The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies were screened and selected for full text review by two independent reviewers with reference to AI platform construction, hospital informatics integration, and institutional deployment strategies. RESULTS A total of 30 high-quality studies were included in the final analysis. Based on the synthesis of evidence, a five-layer hospital AI platform architecture is proposed, consisting of: (1) infrastructure layer, (2) data layer, (3) algorithm layer, (4) application layer, and (5) security and compliance layer. The review highlights key implementation strategies such as modular deployment, real-world scenario validation, and interdepartmental collaboration. It also identifies critical challenges, including legacy system integration, lack of data standardization, computing resource limitations, organizational resistance, regulatory uncertainty, and economic sustainability. CONCLUSIONS The successful construction of hospital AI platforms requires not only advanced technologies but also institutional readiness, strategic planning, and cultural adaptation. Intelligent hospitals of the future must emphasize privacy-preserving computing, seamless AI integration into clinical workflows, and dynamic performance evaluation systems. Building organizational capacity and fostering cross-disciplinary collaboration will be essential to achieving long-term impact and scalability.