The Collaborations among Healthcare Systems, Research Institutions, and Industry on Artificial Intelligence Research and Development

2025-08-26

AI Summary

This study addresses critical barriers hindering industry–academia–healthcare collaboration in medical AI development, particularly low clinical engagement despite high interest among radiologists, driven by data privacy concerns and an underdeveloped regulatory framework. Method: Leveraging a national cross-sectional survey of radiologists, complemented by multi-source data from the Chinese Society of Radiology and the Medical Imaging AI Innovation Alliance, we employed a mixed-methods approach to analyze collaborative networks, stakeholder relationships, and clinical participation levels. Contribution/Results: We identify lesion screening, AI-assisted diagnosis, and workflow optimization as top clinical priorities. Innovatively, we propose three systemic solutions: (1) hospital-based AI research units, (2) trusted, federated data-sharing platforms, and (3) cross-institutional technical standards. Additionally, we emphasize AI literacy training and co-governance mechanisms. These evidence-based recommendations provide actionable insights for policymakers and stakeholders to enhance the translational efficiency and clinical integration of medical AI.

Technology Category

• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Computer Vision: Medical and Biological Imaging

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Objectives: The integration of Artificial Intelligence (AI) in healthcare promises to revolutionize patient care, diagnostics, and treatment protocols. Collaborative efforts among healthcare systems, research institutions, and industry are pivotal to leveraging AI's full potential. This study aims to characterize collaborative networks and stakeholders in AI healthcare initiatives, identify challenges and opportunities within these collaborations, and elucidate priorities for future AI research and development. Methods: This study utilized data from the Chinese Society of Radiology and the Chinese Medical Imaging AI Innovation Alliance. A national cross-sectional survey was conducted in China (N = 5,142) across 31 provincial administrative regions, involving participants from three key groups: clinicians, institution professionals, and industry representatives. The survey explored diverse aspects including current AI usage in healthcare, collaboration dynamics, challenges encountered, and research and development priorities. Results: Findings reveal high interest in AI among clinicians, with a significant gap between interest and actual engagement in development activities. Despite the willingness to share data, progress is hindered by concerns about data privacy and security, and lack of clear industry standards and legal guidelines. Future development interests focus on lesion screening, disease diagnosis, and enhancing clinical workflows. Conclusion: This study highlights an enthusiastic yet cautious approach toward AI in healthcare, characterized by significant barriers that impede effective collaboration and implementation. Recommendations emphasize the need for AI-specific education and training, secure data-sharing frameworks, establishment of clear industry standards, and formation of dedicated AI research departments.

Problem

• Characterizing collaborative networks in AI healthcare initiatives
• Identifying challenges and opportunities in healthcare AI collaborations
• Elucidating priorities for future AI research and development

Innovation

• Cross-sector collaboration networks for AI healthcare
• National survey methodology across multiple stakeholder groups
• Secure data-sharing frameworks and AI education priorities