Exploring Clinicians Perspectives Towards Ai-Radiology & Its Clinical Adoption: A Qualitative Study From Pakistan

1.AI is already finding its way into the diagnostic radiology realm of various regions around the world, but there is still a lack of evidence on the situation in LMICs. This qualitative study examined the research problem through the perspectives of clinicians regarding the adoption of AI-Radiology in Karachi, Pakistan, using the Technology Acceptance Model and interpreting the results into practice and policy using the Problem Driven Iteration Adaptation lens. 13 clinicians (radiologists, tertiary care hospitals) were interviewed between May and August 2025. The semi structured interviews were audio recorded, transcribed and coded in NVivo 14. TAM constructs of perceived usefulness and perceived ease of use were analyzed in a deductive content analysis, and interpretation of implementation pathways was informed by PDIA. Four themes emerged. Implementation attitudes were realistic optimism. The subjects put AI in terms of an assistant and second reader, and clinical judgment and accountability could not be delegated. Issues centered on privacy of data, and over dependence. Perceived ease of use was based on training, infrastructure, fit in workflow and trust. Costs, poor connectivity, the lack of institutional capacity, and generational resistance were the barriers whereas triage acceleration, mass screening support, workload reduction, and time saving were the facilitators. For adoption, education, practical upskilling, guidelines, and local clinical approval were requirements. The greatest perceived usefulness was in situations where AI was applied to specific bottlenecks like quick screening, quantitative measurements, remote-area reporting, and trainees decision support; the constraints included data quality, generalizability, and algorithm error, the risk of confidentiality, and the impossibility to substitute contextual clinical reasoning. Such priorities as national and institutional data protection policies, formal vetting of tools, smooth integration with radiology information systems and AI literacy in the curriculum were included. The sample is limited to one city and the qualitative design does not enhance generalizability but the results provide practical recommendations. The mixed resource setting of Karachi is a potential place where AI can be a reliable collaborator in the field of radiology in case of adequate infrastructure and training of clinicians and a long-term human control. Perceived usefulness can be converted to routine and safe clinical use with strategic and staged implementation.